diff --git a/README.md b/README.md
index 651ba1b..e450921 100644
--- a/README.md
+++ b/README.md
@@ -81,12 +81,22 @@ SLC_masking_algo: str = 'mask_scl_dilation'
         Masking method for Sentinel-2 optical data ('satio', 'mask_scl_dilation', None)
         Note: if set to None, no masking is applied and the S2 L2A data is used as is.
 
-apply_cloud_mask : bool = True
+apply_cloud_mask: bool = True
         if True, the Sentinel-2 or PlanetScope data is masked for clouds (based on Sentinel-2 QA band). 
-        If False, no masking is applied but the mask band is still created and added to the cube.
-        Note: no effect when 'mask_scl_dilation' parameter is set to None.     
-
-append : bool = True
+        If False, no masking is applied but the mask band is still created and added to the cube. (Note: the cloud 
+        mask band is removed from the feature cube as soon the time domain is aggregated.)
+        Note: no effect when 'mask_scl_dilation' parameter is set to None.
+
+get_NVBT: bool = False 
+        Number of Valid Binned Timesteps: Specifies the count of valid timesteps after temporal binning. 
+        This can be used as an input data quality indicator.
+        if True, NVBT is calculated for optical data after cloud masking and temporal binning and radar data after
+        sar_backscatter correction and temporal binning.
+        (if both were activated) but without linear interpolation (if activated).
+        Note: 'band' S1_NVBT and/or S2_NVBT is only added to cubes with removed time domain (feature cubes). 
+        Note: algorithm is applied even when cloud masking was deactivated or temporal aggregation was skipped.
+
+append: bool = True
         if the VI's are appended to the reflectance/radar time series cube OR replace them
 
 S2_scaling: list = [0, 10000, 0, 1.0]
diff --git a/notebooks/test_nobs.ipynb b/notebooks/test_nobs.ipynb
new file mode 100644
index 0000000..eae896e
--- /dev/null
+++ b/notebooks/test_nobs.ipynb
@@ -0,0 +1,460 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d46e36dcd1f7a0ef",
+   "metadata": {},
+   "source": [
+    "# example how to generate the WEED standard feature cube based on EO data (Sentinel-1 and Sentinel-2)\n",
+    "this tests include the generation of the feature cube with and without NVBT band. The NVBT band is a measure of the number of valid input data timesteps after cloud masking and the internal temporal binning.\n",
+    "The NVBT band can be useful for identifying areas with high or low levels of observation, which can be important for a variety of applications, such as monitoring changes in land use or assessing the quality of data in a given area."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:10:45.301457300Z",
+     "start_time": "2026-07-01T10:10:43.592557200Z"
+    }
+   },
+   "source": [
+    "from eo_processing.utils.helper import init_connection\n",
+    "from eo_processing.openeo.processing import generate_master_feature_cube\n",
+    "from eo_processing.config.settings import get_advanced_options, get_job_options, get_collection_options"
+   ],
+   "outputs": [],
+   "execution_count": 1
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c9abe4dec39f3145",
+   "metadata": {},
+   "source": [
+    "#### declare space and time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "1c319454e1c292f1",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:10:48.565131400Z",
+     "start_time": "2026-07-01T10:10:48.548481800Z"
+    }
+   },
+   "source": [
+    "# the time context is given by start and end date\n",
+    "year = 2024\n",
+    "start = f'{year}-01-01'\n",
+    "end = f'{year+1}-01-01'   # the end is always exclusive\n",
+    "\n",
+    "# the space context is defined as a bounding box dictionary with south,west,north,east and crs\n",
+    "# we take as example an 10x10km tile in EU LAEA grid around Vienna\n",
+    "AOI = {'west': 4780000, 'east': 4790000, 'south': 2830000, 'north': 2840000, 'crs': 3035}"
+   ],
+   "outputs": [],
+   "execution_count": 2
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39fc1ee260fa1492",
+   "metadata": {},
+   "source": [
+    "### get processing_options for the eo_processing functions, collection_options and job_options"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "fa16159203be2475",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:11:06.858284600Z",
+     "start_time": "2026-07-01T10:11:06.842773300Z"
+    }
+   },
+   "source": [
+    "processing_options = get_advanced_options(provider='cdse', skip_check_S1=False, skip_check_S2=True)\n",
+    "job_options = get_job_options(provider='cdse', task='feature_generation')\n",
+    "collection_options = get_collection_options(provider='cdse')\n",
+    "processing_options.update({'openeo_chunk_size': 64})"
+   ],
+   "outputs": [],
+   "execution_count": 3
+  },
+  {
+   "cell_type": "code",
+   "id": "72616c9c-4583-4132-a38c-23988aeb8434",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:11:08.354813700Z",
+     "start_time": "2026-07-01T10:11:08.305942900Z"
+    }
+   },
+   "source": [
+    "processing_options"
+   ],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'provider': 'cdse',\n",
+       " 's1_orbitdirection': 'DESCENDING',\n",
+       " 'target_crs': 3035,\n",
+       " 'resolution': 10.0,\n",
+       " 'time_interpolation': False,\n",
+       " 'ts_interval': 'dekad',\n",
+       " 'S2_temporal_reducer': 'median',\n",
+       " 'S1_temporal_reducer': 'mean',\n",
+       " 'SLC_masking_algo': 'mask_scl_dilation',\n",
+       " 'S2_max_cloud_cover': 95,\n",
+       " 'S2_bands': ['B02',\n",
+       "  'B03',\n",
+       "  'B04',\n",
+       "  'B05',\n",
+       "  'B06',\n",
+       "  'B07',\n",
+       "  'B08',\n",
+       "  'B8A',\n",
+       "  'B11',\n",
+       "  'B12'],\n",
+       " 's2_tileid_list': None,\n",
+       " 'skip_check_S1': False,\n",
+       " 'skip_check_S2': True,\n",
+       " 'apply_cloud_mask': True,\n",
+       " 'get_NVBT': False,\n",
+       " 'optical_vi_list': ['ABDI1',\n",
+       "  'ABDI2',\n",
+       "  'AWEInsh',\n",
+       "  'AVI',\n",
+       "  'BLFEI',\n",
+       "  'CIRE',\n",
+       "  'EVI',\n",
+       "  'IRECI',\n",
+       "  'MBWI',\n",
+       "  'MNDWI',\n",
+       "  'MNDVI',\n",
+       "  'NDMI',\n",
+       "  'NDVI',\n",
+       "  'NDVIMNDWI',\n",
+       "  'NDWI',\n",
+       "  'NMDI',\n",
+       "  'NIRv',\n",
+       "  'S2WI',\n",
+       "  'S2REP',\n",
+       "  'WRI'],\n",
+       " 'radar_vi_list': ['VHVVD', 'VHVVR', 'DpRVIVV'],\n",
+       " 'S2_scaling': [0, 10000, 0, 1.0],\n",
+       " 'S1_db_rescale': True,\n",
+       " 'append': True,\n",
+       " 'openeo_chunk_size': 64}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 4
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a05d287923cf93eb",
+   "metadata": {},
+   "source": [
+    "### establish connection to openEO"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "d06f89bea20dce40",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:11:15.268379200Z",
+     "start_time": "2026-07-01T10:11:14.743118500Z"
+    }
+   },
+   "source": "con = init_connection(provider='cdse')",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Authenticated using refresh token.\n"
+     ]
+    }
+   ],
+   "execution_count": 5
+  },
+  {
+   "cell_type": "markdown",
+   "id": "adcab1031cc5e6c2",
+   "metadata": {},
+   "source": [
+    "### run the feature cube generation WITHOUT NVBT band"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "f32c4461ec4331a5",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:11:21.277193500Z",
+     "start_time": "2026-07-01T10:11:21.260122500Z"
+    }
+   },
+   "source": [
+    "# update job_options due toBerts setting from last inference runs\n",
+    "# ToDO: optimize the job settings for feature_cube_generation_with_nobs & feature_cube_generation and put in settings + add correct task to 'get_job_options'\n",
+    "job_options.update({\n",
+    "    \"driver-memory\": \"4G\",\n",
+    "    \"driver-memoryOverhead\": \"4G\",\n",
+    "    \"executor-memory\": \"5G\",\n",
+    "    \"executor-memoryOverhead\": \"3g\",\n",
+    "    \"max-executors\": 10,\n",
+    "    \"python-memory\": \"disable\",\n",
+    "    \"allow_empty_cubes\": True,\n",
+    "    \"soft-errors\": 0.05})"
+   ],
+   "outputs": [],
+   "execution_count": 6
+  },
+  {
+   "cell_type": "code",
+   "id": "fc107ebf279499cf",
+   "metadata": {},
+   "source": [
+    "# get master cube without nobs\n",
+    "data = generate_master_feature_cube(con, AOI, start, end, **collection_options, **processing_options)"
+   ],
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "id": "f0b7c0577d597daf",
+   "metadata": {},
+   "source": "data.execute_batch(r'C:\\Users\\buchhorm\\Downloads\\test_cube\\features_cube_v5.tif', title='feature without nobs (10x10km)', job_options=job_options)",
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3f775e9b75ec1382",
+   "metadata": {},
+   "source": [
+    "## run with activated NVBT generation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "id": "95a0e6270cf65cc3",
+   "metadata": {},
+   "source": [
+    "# now we run same with nobs_perc band\n",
+    "processing_options.update({'get_NVBT': True})\n",
+    "data2 = generate_master_feature_cube(con, AOI, start, end, **collection_options, **processing_options)"
+   ],
+   "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "data2.execute_batch(r'C:\\Users\\buchhorm\\Downloads\\test_cube\\features_cube_with_nobs_v5.tif', title='feature with nobs (10x10km)', job_options=job_options)",
+   "id": "b522dd0e9b4adaa5"
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": [
+    "## now we run this 10x10km test in a bigger context - we generate the full EO feature cube with NVBT band\n",
+    "Note: since the new ECDC version and alphaEarth STACs are not complete THIS loading has to be tested later"
+   ],
+   "id": "3684f8b64901068a"
+  },
+  {
+   "cell_type": "code",
+   "id": "bcb5d1b835c659eb",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:12:04.872738900Z",
+     "start_time": "2026-07-01T10:11:27.488000800Z"
+    }
+   },
+   "source": [
+    "from habitat_mapping.openeo.feature_cubes import create_EOfeature_cube_WEED_V1\n",
+    "processing_options.update(target_crs = 3035)\n",
+    "processing_options.update({'get_NVBT': True})\n",
+    "processing_options.update({'openeo_chunk_size': 16})\n",
+    "job_options.update({\"allow_empty_cubes\": True})\n",
+    "job_options.update({\n",
+    "    \"driver-memory\": \"4G\",\n",
+    "    \"driver-memoryOverhead\": \"4G\",\n",
+    "    \"executor-memory\": \"5G\",\n",
+    "    \"executor-memoryOverhead\": \"3G\",\n",
+    "    \"max-executors\": 10,\n",
+    "    \"python-memory\": \"disable\",\n",
+    "    \"soft-errors\": 0.05,\n",
+    "})\n",
+    "data3 = create_EOfeature_cube_WEED_V1(con, AOI, start, end, collection_options, processing_options)"
+   ],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Deriving band listing from unordered `item_assets`\n",
+      "The specified bands ['precipitation-flux', 'temperature-mean'] in `load_stac` are not a subset of the bands [] found in the STAC metadata (unknown bands: ['precipitation-flux', 'temperature-mean']). Working with specified bands as is.\n"
+     ]
+    }
+   ],
+   "execution_count": 7
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2026-07-01T10:42:53.609735700Z",
+     "start_time": "2026-07-01T10:12:16.483423100Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "data3.execute_batch(r'C:\\Users\\buchhorm\\Downloads\\test_cube\\eo_feature_cube_beta2_10x10.tif', title='eo_feature cube (10x10km)', job_options=job_options)",
+   "id": "641442d062a77b1e",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0:00:00 Job 'j-2607011012174934aeec7870e2685f99': send 'start'\n",
+      "0:00:07 Job 'j-2607011012174934aeec7870e2685f99': queued (progress 0%)\n",
+      "0:00:13 Job 'j-2607011012174934aeec7870e2685f99': queued (progress 0%)\n",
+      "0:00:19 Job 'j-2607011012174934aeec7870e2685f99': queued (progress 0%)\n",
+      "0:00:27 Job 'j-2607011012174934aeec7870e2685f99': queued (progress 0%)\n",
+      "0:00:37 Job 'j-2607011012174934aeec7870e2685f99': queued (progress 0%)\n",
+      "0:00:50 Job 'j-2607011012174934aeec7870e2685f99': queued (progress 0%)\n",
+      "0:01:05 Job 'j-2607011012174934aeec7870e2685f99': running (progress 8.9%)\n",
+      "0:01:24 Job 'j-2607011012174934aeec7870e2685f99': running (progress 11.5%)\n",
+      "0:01:48 Job 'j-2607011012174934aeec7870e2685f99': running (progress 14.5%)\n",
+      "0:02:19 Job 'j-2607011012174934aeec7870e2685f99': running (progress 18.0%)\n",
+      "0:02:56 Job 'j-2607011012174934aeec7870e2685f99': running (progress 22.0%)\n",
+      "0:03:43 Job 'j-2607011012174934aeec7870e2685f99': running (progress 26.5%)\n",
+      "0:04:41 Job 'j-2607011012174934aeec7870e2685f99': running (progress 31.4%)\n",
+      "0:05:41 Job 'j-2607011012174934aeec7870e2685f99': running (progress 35.8%)\n",
+      "0:06:41 Job 'j-2607011012174934aeec7870e2685f99': running (progress 39.7%)\n",
+      "0:07:42 Job 'j-2607011012174934aeec7870e2685f99': running (progress 43.1%)\n",
+      "0:08:42 Job 'j-2607011012174934aeec7870e2685f99': running (progress 46.2%)\n",
+      "0:09:42 Job 'j-2607011012174934aeec7870e2685f99': running (progress 49.0%)\n",
+      "0:10:43 Job 'j-2607011012174934aeec7870e2685f99': running (progress 51.5%)\n",
+      "0:11:43 Job 'j-2607011012174934aeec7870e2685f99': running (progress 53.7%)\n",
+      "0:12:43 Job 'j-2607011012174934aeec7870e2685f99': running (progress 55.8%)\n",
+      "0:13:44 Job 'j-2607011012174934aeec7870e2685f99': running (progress 57.7%)\n",
+      "0:14:44 Job 'j-2607011012174934aeec7870e2685f99': running (progress 59.4%)\n",
+      "0:15:44 Job 'j-2607011012174934aeec7870e2685f99': running (progress 61.0%)\n",
+      "0:16:44 Job 'j-2607011012174934aeec7870e2685f99': running (progress 62.4%)\n",
+      "0:17:45 Job 'j-2607011012174934aeec7870e2685f99': running (progress 63.8%)\n",
+      "0:18:45 Job 'j-2607011012174934aeec7870e2685f99': running (progress 65.1%)\n",
+      "0:19:45 Job 'j-2607011012174934aeec7870e2685f99': running (progress 66.3%)\n",
+      "0:20:45 Job 'j-2607011012174934aeec7870e2685f99': running (progress 67.4%)\n",
+      "0:21:45 Job 'j-2607011012174934aeec7870e2685f99': running (progress 68.4%)\n",
+      "0:22:45 Job 'j-2607011012174934aeec7870e2685f99': running (progress 69.4%)\n",
+      "0:23:46 Job 'j-2607011012174934aeec7870e2685f99': running (progress 70.3%)\n",
+      "0:24:46 Job 'j-2607011012174934aeec7870e2685f99': running (progress 71.1%)\n",
+      "0:25:46 Job 'j-2607011012174934aeec7870e2685f99': running (progress 72.0%)\n",
+      "0:26:47 Job 'j-2607011012174934aeec7870e2685f99': running (progress 72.7%)\n",
+      "0:27:47 Job 'j-2607011012174934aeec7870e2685f99': running (progress 73.5%)\n",
+      "0:28:49 Job 'j-2607011012174934aeec7870e2685f99': running (progress 74.2%)\n",
+      "0:29:50 Job 'j-2607011012174934aeec7870e2685f99': finished (progress 100%)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<BatchJob job_id='j-2607011012174934aeec7870e2685f99'>"
+      ],
+      "text/html": [
+       "\n",
+       "    <script>\n",
+       "    if (!window.customElements || !window.customElements.get('openeo-job')) {\n",
+       "        var el = document.createElement('script');\n",
+       "        el.src = \"https://cdn.jsdelivr.net/npm/@openeo/vue-components@2/assets/openeo.min.js\";\n",
+       "        document.head.appendChild(el);\n",
+       "\n",
+       "        var font = document.createElement('font');\n",
+       "        font.as = \"font\";\n",
+       "        font.type = \"font/woff2\";\n",
+       "        font.crossOrigin = true;\n",
+       "        font.href = \"https://use.fontawesome.com/releases/v5.13.0/webfonts/fa-solid-900.woff2\";\n",
+       "        document.head.appendChild(font);\n",
+       "    }\n",
+       "    </script>\n",
+       "    <openeo-job>\n",
+       "        <script type=\"application/json\">{\"currency\": \"credits\", \"federation\": null, \"job\": {\"allow_empty_cubes\": true, \"costs\": 42, \"created\": \"2026-07-01T10:12:17Z\", \"driver-cores\": 1, \"driver-memory\": \"4G\", \"driver-memoryOverhead\": \"4G\", \"executor-cores\": 1, \"executor-memory\": \"5G\", \"executor-memoryOverhead\": \"3G\", \"id\": \"j-2607011012174934aeec7870e2685f99\", \"log_level\": \"info\", \"logging-threshold\": \"info\", \"max-executors\": 10, \"process\": {\"process_graph\": {\"aggregatetemporalperiod1\": {\"arguments\": {\"data\": {\"from_node\": \"mask1\"}, \"period\": \"dekad\", \"reducer\": {\"process_graph\": {\"median1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"median\", \"result\": true}}}}, \"process_id\": \"aggregate_temporal_period\"}, \"aggregatetemporalperiod2\": {\"arguments\": {\"data\": {\"from_node\": \"resamplespatial3\"}, \"period\": \"dekad\", \"reducer\": {\"process_graph\": {\"mean1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"mean\", \"result\": true}}}}, \"process_id\": \"aggregate_temporal_period\"}, \"apply1\": {\"arguments\": {\"data\": {\"from_node\": \"aggregatetemporalperiod1\"}, \"process\": {\"process_graph\": {\"linearscalerange1\": {\"arguments\": {\"inputMax\": 65534, \"inputMin\": 0, \"outputMax\": 65534, \"outputMin\": 0, \"x\": {\"from_parameter\": \"x\"}}, \"process_id\": \"linear_scale_range\", \"result\": true}}}}, \"process_id\": \"apply\"}, \"apply2\": {\"arguments\": {\"data\": {\"from_node\": \"apply1\"}, \"process\": {\"process_graph\": {\"linearscalerange2\": {\"arguments\": {\"inputMax\": 10000, \"inputMin\": 0, \"outputMax\": 1.0, \"outputMin\": 0, \"x\": {\"from_parameter\": \"x\"}}, \"process_id\": \"linear_scale_range\", \"result\": true}}}}, \"process_id\": \"apply\"}, \"apply3\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension2\"}, \"process\": {\"process_graph\": {\"linearscalerange3\": {\"arguments\": {\"inputMax\": 65534, \"inputMin\": 1, \"outputMax\": 65534, \"outputMin\": 1, \"x\": {\"from_parameter\": \"x\"}}, \"process_id\": \"linear_scale_range\", \"result\": true}}}}, \"process_id\": \"apply\"}, \"applydimension1\": {\"arguments\": {\"data\": {\"from_node\": \"apply2\"}, \"dimension\": \"bands\", \"process\": {\"process_graph\": {\"add1\": {\"arguments\": {\"x\": {\"from_node\": \"subtract4\"}, \"y\": {\"from_node\": \"multiply5\"}}, \"process_id\": \"add\"}, \"add10\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"add\"}, \"add11\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"add\"}, \"add12\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"add\"}, \"add13\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"add\"}, \"add14\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"add\"}, \"add15\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement1\"}}, \"process_id\": \"add\"}, \"add16\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"subtract26\"}}, \"process_id\": \"add\"}, \"add17\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"add\"}, \"add18\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement6\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"add\"}, \"add19\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement8\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"add\"}, \"add2\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"add\"}, \"add20\": {\"arguments\": {\"x\": 705.0, \"y\": {\"from_node\": \"multiply13\"}}, \"process_id\": \"add\"}, \"add21\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"add\"}, \"add22\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"add\"}, \"add3\": {\"arguments\": {\"x\": {\"from_node\": \"add2\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"add\"}, \"add4\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"add\"}, \"add5\": {\"arguments\": {\"x\": {\"from_node\": \"add4\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"add\"}, \"add6\": {\"arguments\": {\"x\": {\"from_node\": \"divide4\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"add\"}, \"add7\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"multiply9\"}}, \"process_id\": \"add\"}, \"add8\": {\"arguments\": {\"x\": {\"from_node\": \"subtract10\"}, \"y\": 1.0}, \"process_id\": \"add\"}, \"add9\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"add\"}, \"arctan1\": {\"arguments\": {\"x\": {\"from_node\": \"divide1\"}}, \"process_id\": \"arctan\"}, \"arctan2\": {\"arguments\": {\"x\": {\"from_node\": \"divide2\"}}, \"process_id\": \"arctan\"}, \"arrayelement1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 6}, \"process_id\": \"array_element\"}, \"arrayelement2\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 8}, \"process_id\": \"array_element\"}, \"arrayelement3\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 9}, \"process_id\": \"array_element\"}, \"arrayelement4\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 1}, \"process_id\": \"array_element\"}, \"arrayelement5\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 2}, \"process_id\": \"array_element\"}, \"arrayelement6\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 3}, \"process_id\": \"array_element\"}, \"arrayelement7\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 0}, \"process_id\": \"array_element\"}, \"arrayelement8\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 5}, \"process_id\": \"array_element\"}, \"arrayelement9\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 4}, \"process_id\": \"array_element\"}, \"arraymodify1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 10, \"values\": [{\"from_node\": \"multiply1\"}, {\"from_node\": \"multiply2\"}, {\"from_node\": \"add1\"}, {\"from_node\": \"power1\"}, {\"from_node\": \"divide5\"}, {\"from_node\": \"subtract8\"}, {\"from_node\": \"divide7\"}, {\"from_node\": \"divide9\"}, {\"from_node\": \"subtract15\"}, {\"from_node\": \"divide10\"}, {\"from_node\": \"divide11\"}, {\"from_node\": \"divide12\"}, {\"from_node\": \"divide13\"}, {\"from_node\": \"subtract22\"}, {\"from_node\": \"divide16\"}, {\"from_node\": \"divide17\"}, {\"from_node\": \"multiply12\"}, {\"from_node\": \"divide19\"}, {\"from_node\": \"add20\"}, {\"from_node\": \"divide22\"}]}, \"process_id\": \"array_modify\", \"result\": true}, \"divide1\": {\"arguments\": {\"x\": {\"from_node\": \"subtract1\"}, \"y\": 0.7680000000000001}, \"process_id\": \"divide\"}, \"divide10\": {\"arguments\": {\"x\": {\"from_node\": \"subtract16\"}, \"y\": {\"from_node\": \"add9\"}}, \"process_id\": \"divide\"}, \"divide11\": {\"arguments\": {\"x\": {\"from_node\": \"subtract17\"}, \"y\": {\"from_node\": \"add10\"}}, \"process_id\": \"divide\"}, \"divide12\": {\"arguments\": {\"x\": {\"from_node\": \"subtract18\"}, \"y\": {\"from_node\": \"add11\"}}, \"process_id\": \"divide\"}, \"divide13\": {\"arguments\": {\"x\": {\"from_node\": \"subtract19\"}, \"y\": {\"from_node\": \"add12\"}}, \"process_id\": \"divide\"}, \"divide14\": {\"arguments\": {\"x\": {\"from_node\": \"subtract20\"}, \"y\": {\"from_node\": \"add13\"}}, \"process_id\": \"divide\"}, \"divide15\": {\"arguments\": {\"x\": {\"from_node\": \"subtract21\"}, \"y\": {\"from_node\": \"add14\"}}, \"process_id\": \"divide\"}, \"divide16\": {\"arguments\": {\"x\": {\"from_node\": \"subtract23\"}, \"y\": {\"from_node\": \"add15\"}}, \"process_id\": \"divide\"}, \"divide17\": {\"arguments\": {\"x\": {\"from_node\": \"subtract25\"}, \"y\": {\"from_node\": \"add16\"}}, \"process_id\": \"divide\"}, \"divide18\": {\"arguments\": {\"x\": {\"from_node\": \"subtract27\"}, \"y\": {\"from_node\": \"add17\"}}, \"process_id\": \"divide\"}, \"divide19\": {\"arguments\": {\"x\": {\"from_node\": \"subtract28\"}, \"y\": {\"from_node\": \"add18\"}}, \"process_id\": \"divide\"}, \"divide2\": {\"arguments\": {\"x\": {\"from_node\": \"subtract2\"}, \"y\": 1.3479999999999999}, \"process_id\": \"divide\"}, \"divide20\": {\"arguments\": {\"x\": {\"from_node\": \"add19\"}, \"y\": 2.0}, \"process_id\": \"divide\"}, \"divide21\": {\"arguments\": {\"x\": {\"from_node\": \"subtract29\"}, \"y\": {\"from_node\": \"subtract30\"}}, \"process_id\": \"divide\"}, \"divide22\": {\"arguments\": {\"x\": {\"from_node\": \"add21\"}, \"y\": {\"from_node\": \"add22\"}}, \"process_id\": \"divide\"}, \"divide3\": {\"arguments\": {\"x\": {\"from_node\": \"add3\"}, \"y\": 3.0}, \"process_id\": \"divide\"}, \"divide4\": {\"arguments\": {\"x\": {\"from_node\": \"add5\"}, \"y\": 3.0}, \"process_id\": \"divide\"}, \"divide5\": {\"arguments\": {\"x\": {\"from_node\": \"subtract7\"}, \"y\": {\"from_node\": \"add6\"}}, \"process_id\": \"divide\"}, \"divide6\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement6\"}}, \"process_id\": \"divide\"}, \"divide7\": {\"arguments\": {\"x\": {\"from_node\": \"multiply8\"}, \"y\": {\"from_node\": \"add8\"}}, \"process_id\": \"divide\"}, \"divide8\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement6\"}, \"y\": {\"from_node\": \"arrayelement9\"}}, \"process_id\": \"divide\"}, \"divide9\": {\"arguments\": {\"x\": {\"from_node\": \"subtract11\"}, \"y\": {\"from_node\": \"divide8\"}}, \"process_id\": \"divide\"}, \"multiply1\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arctan1\"}}, \"process_id\": \"multiply\"}, \"multiply10\": {\"arguments\": {\"x\": 7.5, \"y\": {\"from_node\": \"arrayelement7\"}}, \"process_id\": \"multiply\"}, \"multiply11\": {\"arguments\": {\"x\": 2.0, \"y\": {\"from_node\": \"arrayelement4\"}}, \"process_id\": \"multiply\"}, \"multiply12\": {\"arguments\": {\"x\": {\"from_node\": \"divide18\"}, \"y\": {\"from_node\": \"arrayelement1\"}}, \"process_id\": \"multiply\"}, \"multiply13\": {\"arguments\": {\"x\": 35.0, \"y\": {\"from_node\": \"divide21\"}}, \"process_id\": \"multiply\"}, \"multiply2\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arctan2\"}}, \"process_id\": \"multiply\"}, \"multiply3\": {\"arguments\": {\"x\": 4.0, \"y\": {\"from_node\": \"subtract3\"}}, \"process_id\": \"multiply\"}, \"multiply4\": {\"arguments\": {\"x\": 0.25, \"y\": {\"from_node\": \"arrayelement1\"}}, \"process_id\": \"multiply\"}, \"multiply5\": {\"arguments\": {\"x\": 2.75, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"multiply\"}, \"multiply6\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"subtract5\"}}, \"process_id\": \"multiply\"}, \"multiply7\": {\"arguments\": {\"x\": {\"from_node\": \"multiply6\"}, \"y\": {\"from_node\": \"subtract6\"}}, \"process_id\": \"multiply\"}, \"multiply8\": {\"arguments\": {\"x\": 2.5, \"y\": {\"from_node\": \"subtract9\"}}, \"process_id\": \"multiply\"}, \"multiply9\": {\"arguments\": {\"x\": 6.0, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"multiply\"}, \"power1\": {\"arguments\": {\"base\": {\"from_node\": \"multiply7\"}, \"p\": 0.3333333333333333}, \"process_id\": \"power\"}, \"subtract1\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"subtract\"}, \"subtract10\": {\"arguments\": {\"x\": {\"from_node\": \"add7\"}, \"y\": {\"from_node\": \"multiply10\"}}, \"process_id\": \"subtract\"}, \"subtract11\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement8\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}, \"subtract12\": {\"arguments\": {\"x\": {\"from_node\": \"multiply11\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}, \"subtract13\": {\"arguments\": {\"x\": {\"from_node\": \"subtract12\"}, \"y\": {\"from_node\": \"arrayelement1\"}}, \"process_id\": \"subtract\"}, \"subtract14\": {\"arguments\": {\"x\": {\"from_node\": \"subtract13\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"subtract\"}, \"subtract15\": {\"arguments\": {\"x\": {\"from_node\": \"subtract14\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"subtract\"}, \"subtract16\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"subtract\"}, \"subtract17\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"subtract\"}, \"subtract18\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"subtract\"}, \"subtract19\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}, \"subtract2\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"subtract\"}, \"subtract20\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}, \"subtract21\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"subtract\"}, \"subtract22\": {\"arguments\": {\"x\": {\"from_node\": \"divide14\"}, \"y\": {\"from_node\": \"divide15\"}}, \"process_id\": \"subtract\"}, \"subtract23\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement1\"}}, \"process_id\": \"subtract\"}, \"subtract24\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement2\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"subtract\"}, \"subtract25\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"subtract24\"}}, \"process_id\": \"subtract\"}, \"subtract26\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement2\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"subtract\"}, \"subtract27\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}, \"subtract28\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement6\"}, \"y\": {\"from_node\": \"arrayelement3\"}}, \"process_id\": \"subtract\"}, \"subtract29\": {\"arguments\": {\"x\": {\"from_node\": \"divide20\"}, \"y\": {\"from_node\": \"arrayelement6\"}}, \"process_id\": \"subtract\"}, \"subtract3\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement4\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"subtract\"}, \"subtract30\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement9\"}, \"y\": {\"from_node\": \"arrayelement6\"}}, \"process_id\": \"subtract\"}, \"subtract4\": {\"arguments\": {\"x\": {\"from_node\": \"multiply3\"}, \"y\": {\"from_node\": \"multiply4\"}}, \"process_id\": \"subtract\"}, \"subtract5\": {\"arguments\": {\"x\": 1.0, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}, \"subtract6\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}, \"subtract7\": {\"arguments\": {\"x\": {\"from_node\": \"divide3\"}, \"y\": {\"from_node\": \"arrayelement2\"}}, \"process_id\": \"subtract\"}, \"subtract8\": {\"arguments\": {\"x\": {\"from_node\": \"divide6\"}, \"y\": 1}, \"process_id\": \"subtract\"}, \"subtract9\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement1\"}, \"y\": {\"from_node\": \"arrayelement5\"}}, \"process_id\": \"subtract\"}}}}, \"process_id\": \"apply_dimension\"}, \"applydimension2\": {\"arguments\": {\"data\": {\"from_node\": \"aggregatetemporalperiod2\"}, \"dimension\": \"bands\", \"process\": {\"process_graph\": {\"add23\": {\"arguments\": {\"x\": {\"from_node\": \"multiply14\"}, \"y\": 83.0}, \"process_id\": \"add\"}, \"add24\": {\"arguments\": {\"x\": {\"from_node\": \"multiply15\"}, \"y\": 83.0}, \"process_id\": \"add\"}, \"arraycreate1\": {\"arguments\": {\"data\": [{\"from_node\": \"if1\"}, {\"from_node\": \"if2\"}]}, \"process_id\": \"array_create\", \"result\": true}, \"arrayelement10\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 0}, \"process_id\": \"array_element\"}, \"arrayelement11\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 0}, \"process_id\": \"array_element\"}, \"arrayelement12\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 1}, \"process_id\": \"array_element\"}, \"arrayelement13\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 1}, \"process_id\": \"array_element\"}, \"divide23\": {\"arguments\": {\"x\": {\"from_node\": \"add23\"}, \"y\": 20.0}, \"process_id\": \"divide\"}, \"divide24\": {\"arguments\": {\"x\": {\"from_node\": \"add24\"}, \"y\": 20.0}, \"process_id\": \"divide\"}, \"if1\": {\"arguments\": {\"accept\": 1, \"reject\": {\"from_node\": \"power2\"}, \"value\": {\"from_node\": \"isnodata1\"}}, \"process_id\": \"if\"}, \"if2\": {\"arguments\": {\"accept\": 1, \"reject\": {\"from_node\": \"power3\"}, \"value\": {\"from_node\": \"isnodata2\"}}, \"process_id\": \"if\"}, \"isnodata1\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement11\"}}, \"process_id\": \"is_nodata\"}, \"isnodata2\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement13\"}}, \"process_id\": \"is_nodata\"}, \"log1\": {\"arguments\": {\"base\": 10, \"x\": {\"from_node\": \"arrayelement10\"}}, \"process_id\": \"log\"}, \"log2\": {\"arguments\": {\"base\": 10, \"x\": {\"from_node\": \"arrayelement12\"}}, \"process_id\": \"log\"}, \"multiply14\": {\"arguments\": {\"x\": 10.0, \"y\": {\"from_node\": \"log1\"}}, \"process_id\": \"multiply\"}, \"multiply15\": {\"arguments\": {\"x\": 10.0, \"y\": {\"from_node\": \"log2\"}}, \"process_id\": \"multiply\"}, \"power2\": {\"arguments\": {\"base\": 10, \"p\": {\"from_node\": \"divide23\"}}, \"process_id\": \"power\"}, \"power3\": {\"arguments\": {\"base\": 10, \"p\": {\"from_node\": \"divide24\"}}, \"process_id\": \"power\"}}}}, \"process_id\": \"apply_dimension\"}, \"applydimension3\": {\"arguments\": {\"data\": {\"from_node\": \"apply3\"}, \"dimension\": \"bands\", \"process\": {\"process_graph\": {\"arraycreate2\": {\"arguments\": {\"data\": [{\"from_node\": \"subtract31\"}, {\"from_node\": \"subtract32\"}]}, \"process_id\": \"array_create\", \"result\": true}, \"arrayelement14\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 0}, \"process_id\": \"array_element\"}, \"arrayelement15\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 1}, \"process_id\": \"array_element\"}, \"log3\": {\"arguments\": {\"base\": 10, \"x\": {\"from_node\": \"arrayelement14\"}}, \"process_id\": \"log\"}, \"log4\": {\"arguments\": {\"base\": 10, \"x\": {\"from_node\": \"arrayelement15\"}}, \"process_id\": \"log\"}, \"multiply16\": {\"arguments\": {\"x\": 20.0, \"y\": {\"from_node\": \"log3\"}}, \"process_id\": \"multiply\"}, \"multiply17\": {\"arguments\": {\"x\": 20.0, \"y\": {\"from_node\": \"log4\"}}, \"process_id\": \"multiply\"}, \"subtract31\": {\"arguments\": {\"x\": {\"from_node\": \"multiply16\"}, \"y\": 83.0}, \"process_id\": \"subtract\"}, \"subtract32\": {\"arguments\": {\"x\": {\"from_node\": \"multiply17\"}, \"y\": 83.0}, \"process_id\": \"subtract\"}}}}, \"process_id\": \"apply_dimension\"}, \"applydimension4\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension3\"}, \"dimension\": \"bands\", \"process\": {\"process_graph\": {\"add25\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement17\"}, \"y\": {\"from_node\": \"arrayelement16\"}}, \"process_id\": \"add\"}, \"arrayelement16\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 0}, \"process_id\": \"array_element\"}, \"arrayelement17\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 1}, \"process_id\": \"array_element\"}, \"arraymodify2\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"index\": 2, \"values\": [{\"from_node\": \"subtract33\"}, {\"from_node\": \"divide25\"}, {\"from_node\": \"divide26\"}]}, \"process_id\": \"array_modify\", \"result\": true}, \"divide25\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement16\"}, \"y\": {\"from_node\": \"arrayelement17\"}}, \"process_id\": \"divide\"}, \"divide26\": {\"arguments\": {\"x\": {\"from_node\": \"multiply18\"}, \"y\": {\"from_node\": \"add25\"}}, \"process_id\": \"divide\"}, \"multiply18\": {\"arguments\": {\"x\": 4.0, \"y\": {\"from_node\": \"arrayelement16\"}}, \"process_id\": \"multiply\"}, \"subtract33\": {\"arguments\": {\"x\": {\"from_node\": \"arrayelement16\"}, \"y\": {\"from_node\": \"arrayelement17\"}}, \"process_id\": \"subtract\"}}}}, \"process_id\": \"apply_dimension\"}, \"applydimension5\": {\"arguments\": {\"context\": {\"TileSize\": 16, \"parallel\": true}, \"data\": {\"from_node\": \"mergecubes1\"}, \"dimension\": \"t\", \"process\": {\"process_graph\": {\"arrayconcat1\": {\"arguments\": {\"array1\": {\"from_node\": \"quantiles1\"}, \"array2\": [{\"from_node\": \"mean2\"}, {\"from_node\": \"sd1\"}, {\"from_node\": \"sum1\"}, {\"from_node\": \"subtract34\"}, {\"from_node\": \"subtract35\"}]}, \"process_id\": \"array_concat\", \"result\": true}, \"mean2\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"mean\"}, \"quantiles1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"probabilities\": [0.02, 0.05, 0.25, 0.5, 0.75, 0.95, 0.98]}, \"process_id\": \"quantiles\"}, \"quantiles2\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"probabilities\": [0.75]}, \"process_id\": \"quantiles\"}, \"quantiles3\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"probabilities\": [0.25]}, \"process_id\": \"quantiles\"}, \"quantiles4\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"probabilities\": [0.95]}, \"process_id\": \"quantiles\"}, \"quantiles5\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"probabilities\": [0.05]}, \"process_id\": \"quantiles\"}, \"sd1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"sd\"}, \"subtract34\": {\"arguments\": {\"x\": {\"from_node\": \"quantiles2\"}, \"y\": {\"from_node\": \"quantiles3\"}}, \"process_id\": \"subtract\"}, \"subtract35\": {\"arguments\": {\"x\": {\"from_node\": \"quantiles4\"}, \"y\": {\"from_node\": \"quantiles5\"}}, \"process_id\": \"subtract\"}, \"sum1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"sum\"}}}, \"target_dimension\": \"bands\"}, \"process_id\": \"apply_dimension\"}, \"applydimension6\": {\"arguments\": {\"context\": {\"parallel\": true}, \"data\": {\"from_node\": \"loadcollection5\"}, \"dimension\": \"t\", \"process\": {\"process_graph\": {\"arrayconcat2\": {\"arguments\": {\"array1\": [{\"from_node\": \"mean3\"}], \"array2\": [{\"from_node\": \"max1\"}, {\"from_node\": \"min1\"}, {\"from_node\": \"subtract36\"}]}, \"process_id\": \"array_concat\", \"result\": true}, \"max1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"max2\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"mean3\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"mean\"}, \"min1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"min2\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"subtract36\": {\"arguments\": {\"x\": {\"from_node\": \"max2\"}, \"y\": {\"from_node\": \"min2\"}}, \"process_id\": \"subtract\"}}}, \"target_dimension\": \"bands\"}, \"process_id\": \"apply_dimension\"}, \"applydimension7\": {\"arguments\": {\"context\": {\"parallel\": true}, \"data\": {\"from_node\": \"loadcollection6\"}, \"dimension\": \"t\", \"process\": {\"process_graph\": {\"arrayconcat3\": {\"arguments\": {\"array1\": [{\"from_node\": \"mean4\"}], \"array2\": [{\"from_node\": \"max3\"}, {\"from_node\": \"min3\"}, {\"from_node\": \"subtract37\"}]}, \"process_id\": \"array_concat\", \"result\": true}, \"max3\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"max4\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"mean4\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"mean\"}, \"min3\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"min4\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"subtract37\": {\"arguments\": {\"x\": {\"from_node\": \"max4\"}, \"y\": {\"from_node\": \"min4\"}}, \"process_id\": \"subtract\"}}}, \"target_dimension\": \"bands\"}, \"process_id\": \"apply_dimension\"}, \"applydimension8\": {\"arguments\": {\"context\": {\"parallel\": true}, \"data\": {\"from_node\": \"loadcollection7\"}, \"dimension\": \"t\", \"process\": {\"process_graph\": {\"arrayconcat4\": {\"arguments\": {\"array1\": [{\"from_node\": \"mean5\"}], \"array2\": [{\"from_node\": \"max5\"}, {\"from_node\": \"min5\"}, {\"from_node\": \"subtract38\"}]}, \"process_id\": \"array_concat\", \"result\": true}, \"max5\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"max6\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"mean5\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"mean\"}, \"min5\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"min6\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"subtract38\": {\"arguments\": {\"x\": {\"from_node\": \"max6\"}, \"y\": {\"from_node\": \"min6\"}}, \"process_id\": \"subtract\"}}}, \"target_dimension\": \"bands\"}, \"process_id\": \"apply_dimension\"}, \"applydimension9\": {\"arguments\": {\"context\": {\"TileSize\": 16, \"parallel\": true}, \"data\": {\"from_node\": \"resamplespatial8\"}, \"dimension\": \"t\", \"process\": {\"process_graph\": {\"arrayconcat5\": {\"arguments\": {\"array1\": [{\"from_node\": \"mean6\"}], \"array2\": [{\"from_node\": \"max7\"}, {\"from_node\": \"min7\"}, {\"from_node\": \"subtract39\"}]}, \"process_id\": \"array_concat\", \"result\": true}, \"max7\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"max8\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"max\"}, \"mean6\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"mean\"}, \"min7\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"min8\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"min\"}, \"subtract39\": {\"arguments\": {\"x\": {\"from_node\": \"max8\"}, \"y\": {\"from_node\": \"min8\"}}, \"process_id\": \"subtract\"}}}, \"target_dimension\": \"bands\"}, \"process_id\": \"apply_dimension\"}, \"filterbands1\": {\"arguments\": {\"bands\": [\"B02_p2\", \"B02_p5\", \"B02_p25\", \"B02_median\", \"B02_p75\", \"B02_p95\", \"B02_p98\", \"B02_mean\", \"B02_sd\", \"B02_sum\", \"B02_iqr\", \"B02_iqr0595\", \"B03_p2\", \"B03_p5\", \"B03_p25\", \"B03_median\", \"B03_p75\", \"B03_p95\", \"B03_p98\", \"B03_mean\", \"B03_sd\", \"B03_sum\", \"B03_iqr\", \"B03_iqr0595\", \"B04_p2\", \"B04_p5\", \"B04_p25\", \"B04_median\", \"B04_p75\", \"B04_p95\", \"B04_p98\", \"B04_mean\", \"B04_sd\", \"B04_sum\", \"B04_iqr\", \"B04_iqr0595\", \"B05_p2\", \"B05_p5\", \"B05_p25\", \"B05_median\", \"B05_p75\", \"B05_p95\", \"B05_p98\", \"B05_mean\", \"B05_sd\", \"B05_sum\", \"B05_iqr\", \"B05_iqr0595\", \"B06_p2\", \"B06_p5\", \"B06_p25\", \"B06_median\", \"B06_p75\", \"B06_p95\", \"B06_p98\", \"B06_mean\", \"B06_sd\", \"B06_sum\", \"B06_iqr\", \"B06_iqr0595\", \"B07_p2\", \"B07_p5\", \"B07_p25\", \"B07_median\", \"B07_p75\", \"B07_p95\", \"B07_p98\", \"B07_mean\", \"B07_sd\", \"B07_sum\", \"B07_iqr\", \"B07_iqr0595\", \"B08_p2\", \"B08_p5\", \"B08_p25\", \"B08_median\", \"B08_p75\", \"B08_p95\", \"B08_p98\", \"B08_mean\", \"B08_sd\", \"B08_sum\", \"B08_iqr\", \"B08_iqr0595\", \"B8A_p2\", \"B8A_p5\", \"B8A_p25\", \"B8A_median\", \"B8A_p75\", \"B8A_p95\", \"B8A_p98\", \"B8A_mean\", \"B8A_sd\", \"B8A_sum\", \"B8A_iqr\", \"B8A_iqr0595\", \"B11_p2\", \"B11_p5\", \"B11_p25\", \"B11_median\", \"B11_p75\", \"B11_p95\", \"B11_p98\", \"B11_mean\", \"B11_sd\", \"B11_sum\", \"B11_iqr\", \"B11_iqr0595\", \"B12_p2\", \"B12_p5\", \"B12_p25\", \"B12_median\", \"B12_p75\", \"B12_p95\", \"B12_p98\", \"B12_mean\", \"B12_sd\", \"B12_sum\", \"B12_iqr\", \"B12_iqr0595\", \"ABDI1_p2\", \"ABDI1_p5\", \"ABDI1_p25\", \"ABDI1_median\", \"ABDI1_p75\", \"ABDI1_p95\", \"ABDI1_p98\", \"ABDI1_mean\", \"ABDI1_sd\", \"ABDI1_sum\", \"ABDI1_iqr\", \"ABDI1_iqr0595\", \"ABDI2_p2\", \"ABDI2_p5\", \"ABDI2_p25\", \"ABDI2_median\", \"ABDI2_p75\", \"ABDI2_p95\", \"ABDI2_p98\", \"ABDI2_mean\", \"ABDI2_sd\", \"ABDI2_sum\", \"ABDI2_iqr\", \"ABDI2_iqr0595\", \"AWEInsh_p2\", \"AWEInsh_p5\", \"AWEInsh_p25\", \"AWEInsh_median\", \"AWEInsh_p75\", \"AWEInsh_p95\", \"AWEInsh_p98\", \"AWEInsh_mean\", \"AWEInsh_sd\", \"AWEInsh_sum\", \"AWEInsh_iqr\", \"AWEInsh_iqr0595\", \"AVI_p2\", \"AVI_p5\", \"AVI_p25\", \"AVI_median\", \"AVI_p75\", \"AVI_p95\", \"AVI_p98\", \"AVI_mean\", \"AVI_sd\", \"AVI_sum\", \"AVI_iqr\", \"AVI_iqr0595\", \"BLFEI_p2\", \"BLFEI_p5\", \"BLFEI_p25\", \"BLFEI_median\", \"BLFEI_p75\", \"BLFEI_p95\", \"BLFEI_p98\", \"BLFEI_mean\", \"BLFEI_sd\", \"BLFEI_sum\", \"BLFEI_iqr\", \"BLFEI_iqr0595\", \"CIRE_p2\", \"CIRE_p5\", \"CIRE_p25\", \"CIRE_median\", \"CIRE_p75\", \"CIRE_p95\", \"CIRE_p98\", \"CIRE_mean\", \"CIRE_sd\", \"CIRE_sum\", \"CIRE_iqr\", \"CIRE_iqr0595\", \"EVI_p2\", \"EVI_p5\", \"EVI_p25\", \"EVI_median\", \"EVI_p75\", \"EVI_p95\", \"EVI_p98\", \"EVI_mean\", \"EVI_sd\", \"EVI_sum\", \"EVI_iqr\", \"EVI_iqr0595\", \"IRECI_p2\", \"IRECI_p5\", \"IRECI_p25\", \"IRECI_median\", \"IRECI_p75\", \"IRECI_p95\", \"IRECI_p98\", \"IRECI_mean\", \"IRECI_sd\", \"IRECI_sum\", \"IRECI_iqr\", \"IRECI_iqr0595\", \"MBWI_p2\", \"MBWI_p5\", \"MBWI_p25\", \"MBWI_median\", \"MBWI_p75\", \"MBWI_p95\", \"MBWI_p98\", \"MBWI_mean\", \"MBWI_sd\", \"MBWI_sum\", \"MBWI_iqr\", \"MBWI_iqr0595\", \"MNDWI_p2\", \"MNDWI_p5\", \"MNDWI_p25\", \"MNDWI_median\", \"MNDWI_p75\", \"MNDWI_p95\", \"MNDWI_p98\", \"MNDWI_mean\", \"MNDWI_sd\", \"MNDWI_sum\", \"MNDWI_iqr\", \"MNDWI_iqr0595\", \"MNDVI_p2\", \"MNDVI_p5\", \"MNDVI_p25\", \"MNDVI_median\", \"MNDVI_p75\", \"MNDVI_p95\", \"MNDVI_p98\", \"MNDVI_mean\", \"MNDVI_sd\", \"MNDVI_sum\", \"MNDVI_iqr\", \"MNDVI_iqr0595\", \"NDMI_p2\", \"NDMI_p5\", \"NDMI_p25\", \"NDMI_median\", \"NDMI_p75\", \"NDMI_p95\", \"NDMI_p98\", \"NDMI_mean\", \"NDMI_sd\", \"NDMI_sum\", \"NDMI_iqr\", \"NDMI_iqr0595\", \"NDVI_p2\", \"NDVI_p5\", \"NDVI_p25\", \"NDVI_median\", \"NDVI_p75\", \"NDVI_p95\", \"NDVI_p98\", \"NDVI_mean\", \"NDVI_sd\", \"NDVI_sum\", \"NDVI_iqr\", \"NDVI_iqr0595\", \"NDVIMNDWI_p2\", \"NDVIMNDWI_p5\", \"NDVIMNDWI_p25\", \"NDVIMNDWI_median\", \"NDVIMNDWI_p75\", \"NDVIMNDWI_p95\", \"NDVIMNDWI_p98\", \"NDVIMNDWI_mean\", \"NDVIMNDWI_sd\", \"NDVIMNDWI_sum\", \"NDVIMNDWI_iqr\", \"NDVIMNDWI_iqr0595\", \"NDWI_p2\", \"NDWI_p5\", \"NDWI_p25\", \"NDWI_median\", \"NDWI_p75\", \"NDWI_p95\", \"NDWI_p98\", \"NDWI_mean\", \"NDWI_sd\", \"NDWI_sum\", \"NDWI_iqr\", \"NDWI_iqr0595\", \"NMDI_p2\", \"NMDI_p5\", \"NMDI_p25\", \"NMDI_median\", \"NMDI_p75\", \"NMDI_p95\", \"NMDI_p98\", \"NMDI_mean\", \"NMDI_sd\", \"NMDI_sum\", \"NMDI_iqr\", \"NMDI_iqr0595\", \"NIRv_p2\", \"NIRv_p5\", \"NIRv_p25\", \"NIRv_median\", \"NIRv_p75\", \"NIRv_p95\", \"NIRv_p98\", \"NIRv_mean\", \"NIRv_sd\", \"NIRv_sum\", \"NIRv_iqr\", \"NIRv_iqr0595\", \"S2WI_p2\", \"S2WI_p5\", \"S2WI_p25\", \"S2WI_median\", \"S2WI_p75\", \"S2WI_p95\", \"S2WI_p98\", \"S2WI_mean\", \"S2WI_sd\", \"S2WI_sum\", \"S2WI_iqr\", \"S2WI_iqr0595\", \"S2REP_p2\", \"S2REP_p5\", \"S2REP_p25\", \"S2REP_median\", \"S2REP_p75\", \"S2REP_p95\", \"S2REP_p98\", \"S2REP_mean\", \"WRI_p2\", \"WRI_p5\", \"WRI_p25\", \"WRI_median\", \"WRI_p75\", \"WRI_p95\", \"WRI_p98\", \"WRI_mean\", \"WRI_sd\", \"WRI_sum\", \"WRI_iqr\", \"WRI_iqr0595\", \"VH_p2\", \"VH_p5\", \"VH_p25\", \"VH_median\", \"VH_p75\", \"VH_p95\", \"VH_p98\", \"VH_mean\", \"VH_sd\", \"VH_iqr\", \"VH_iqr0595\", \"VV_p2\", \"VV_p5\", \"VV_p25\", \"VV_median\", \"VV_p75\", \"VV_p95\", \"VV_p98\", \"VV_mean\", \"VV_sd\", \"VV_iqr\", \"VV_iqr0595\", \"VHVVD_p2\", \"VHVVD_p5\", \"VHVVD_p25\", \"VHVVD_median\", \"VHVVD_p75\", \"VHVVD_p95\", \"VHVVD_p98\", \"VHVVD_mean\", \"VHVVD_sd\", \"VHVVD_iqr\", \"VHVVD_iqr0595\", \"VHVVR_p2\", \"VHVVR_p5\", \"VHVVR_p25\", \"VHVVR_median\", \"VHVVR_p75\", \"VHVVR_p95\", \"VHVVR_p98\", \"VHVVR_mean\", \"VHVVR_sd\", \"VHVVR_sum\", \"VHVVR_iqr\", \"VHVVR_iqr0595\", \"DpRVIVV_p2\", \"DpRVIVV_p5\", \"DpRVIVV_p25\", \"DpRVIVV_median\", \"DpRVIVV_p75\", \"DpRVIVV_p95\", \"DpRVIVV_p98\", \"DpRVIVV_mean\", \"DpRVIVV_sd\", \"DpRVIVV_sum\", \"DpRVIVV_iqr\", \"DpRVIVV_iqr0595\"], \"data\": {\"from_node\": \"renamelabels4\"}}, \"process_id\": \"filter_bands\"}, \"filterbands2\": {\"arguments\": {\"bands\": [\"B02\"], \"data\": {\"from_node\": \"aggregatetemporalperiod1\"}}, \"process_id\": \"filter_bands\"}, \"loadcollection1\": {\"arguments\": {\"bands\": [\"B02\", \"B03\", \"B04\", \"B05\", \"B06\", \"B07\", \"B08\", \"B8A\", \"B11\", \"B12\"], \"featureflags\": {\"tilesize\": 16}, \"id\": \"SENTINEL2_L2A\", \"properties\": {\"eo:cloud_cover\": {\"process_graph\": {\"lte1\": {\"arguments\": {\"x\": {\"from_parameter\": \"value\"}, \"y\": 95}, \"process_id\": \"lte\", \"result\": true}}}}, \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": [\"2024-01-01\", \"2025-01-01\"]}, \"process_id\": \"load_collection\"}, \"loadcollection2\": {\"arguments\": {\"bands\": [\"SCL\"], \"featureflags\": {\"tilesize\": 16}, \"id\": \"SENTINEL2_L2A\", \"properties\": {\"eo:cloud_cover\": {\"process_graph\": {\"lte2\": {\"arguments\": {\"x\": {\"from_parameter\": \"value\"}, \"y\": 95}, \"process_id\": \"lte\", \"result\": true}}}}, \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": [\"2024-01-01\", \"2025-01-01\"]}, \"process_id\": \"load_collection\"}, \"loadcollection3\": {\"arguments\": {\"bands\": [\"VH\", \"VV\"], \"featureflags\": {\"tilesize\": 16}, \"id\": \"SENTINEL1_GRD\", \"properties\": {\"sar:polarizations\": {\"process_graph\": {\"eq2\": {\"arguments\": {\"x\": {\"from_parameter\": \"value\"}, \"y\": [\"VV\", \"VH\"]}, \"process_id\": \"eq\", \"result\": true}}}, \"sat:orbit_state\": {\"process_graph\": {\"eq1\": {\"arguments\": {\"x\": {\"from_parameter\": \"value\"}, \"y\": \"DESCENDING\"}, \"process_id\": \"eq\", \"result\": true}}}}, \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": [\"2024-01-01\", \"2025-01-01\"]}, \"process_id\": \"load_collection\"}, \"loadcollection4\": {\"arguments\": {\"bands\": [\"DEM\"], \"featureflags\": {\"tilesize\": 16}, \"id\": \"COPERNICUS_30\", \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": null}, \"process_id\": \"load_collection\"}, \"loadcollection5\": {\"arguments\": {\"bands\": [\"LST\"], \"featureflags\": {\"tilesize\": 4}, \"id\": \"SENTINEL3_SLSTR_L2_LST\", \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": [\"2024-01-01\", \"2025-01-01\"]}, \"process_id\": \"load_collection\"}, \"loadcollection6\": {\"arguments\": {\"bands\": [\"lai\"], \"featureflags\": {\"tilesize\": 4}, \"id\": \"CLMS_LAI_GLOBAL_300M_10DAILY_V2\", \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": [\"2024-01-01\", \"2025-01-01\"]}, \"process_id\": \"load_collection\"}, \"loadcollection7\": {\"arguments\": {\"bands\": [\"ssm\"], \"featureflags\": {\"tilesize\": 4}, \"id\": \"CLMS_SSM_EUROPE_1KM_DAILY_V1\", \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": [\"2024-01-01\", \"2025-01-01\"]}, \"process_id\": \"load_collection\"}, \"loadstac1\": {\"arguments\": {\"bands\": [\"precipitation-flux\", \"temperature-mean\"], \"featureflags\": {\"tilesize\": 4}, \"spatial_extent\": {\"crs\": 3035, \"east\": 4790000, \"north\": 2840000, \"south\": 2830000, \"west\": 4780000}, \"temporal_extent\": [\"2024-01-01\", \"2025-01-01\"], \"url\": \"https://stac.openeo.vito.be/collections/agera5_monthly_composite\"}, \"process_id\": \"load_stac\"}, \"mask1\": {\"arguments\": {\"data\": {\"from_node\": \"resamplespatial1\"}, \"mask\": {\"from_node\": \"renamelabels1\"}}, \"process_id\": \"mask\"}, \"mergecubes1\": {\"arguments\": {\"cube1\": {\"from_node\": \"renamelabels2\"}, \"cube2\": {\"from_node\": \"renamelabels3\"}}, \"process_id\": \"merge_cubes\"}, \"mergecubes2\": {\"arguments\": {\"cube1\": {\"from_node\": \"filterbands1\"}, \"cube2\": {\"from_node\": \"renamelabels5\"}}, \"process_id\": \"merge_cubes\"}, \"mergecubes3\": {\"arguments\": {\"cube1\": {\"from_node\": \"mergecubes2\"}, \"cube2\": {\"from_node\": \"resamplespatial4\"}}, \"process_id\": \"merge_cubes\"}, \"mergecubes4\": {\"arguments\": {\"cube1\": {\"from_node\": \"mergecubes3\"}, \"cube2\": {\"from_node\": \"resamplespatial5\"}}, \"process_id\": \"merge_cubes\"}, \"mergecubes5\": {\"arguments\": {\"cube1\": {\"from_node\": \"mergecubes4\"}, \"cube2\": {\"from_node\": \"resamplespatial6\"}}, \"process_id\": \"merge_cubes\"}, \"mergecubes6\": {\"arguments\": {\"cube1\": {\"from_node\": \"mergecubes5\"}, \"cube2\": {\"from_node\": \"resamplespatial7\"}}, \"process_id\": \"merge_cubes\"}, \"mergecubes7\": {\"arguments\": {\"cube1\": {\"from_node\": \"mergecubes6\"}, \"cube2\": {\"from_node\": \"renamelabels9\"}}, \"process_id\": \"merge_cubes\"}, \"reducedimension1\": {\"arguments\": {\"data\": {\"from_node\": \"filterbands2\"}, \"dimension\": \"t\", \"reducer\": {\"process_graph\": {\"count1\": {\"arguments\": {\"context\": {\"from_parameter\": \"context\"}, \"data\": {\"from_parameter\": \"data\"}}, \"process_id\": \"count\", \"result\": true}}}}, \"process_id\": \"reduce_dimension\"}, \"reducedimension2\": {\"arguments\": {\"data\": {\"from_node\": \"loadcollection4\"}, \"dimension\": \"t\", \"reducer\": {\"process_graph\": {\"last1\": {\"arguments\": {\"data\": {\"from_parameter\": \"data\"}, \"ignore_nodata\": true}, \"process_id\": \"last\", \"result\": true}}}}, \"process_id\": \"reduce_dimension\"}, \"renamelabels1\": {\"arguments\": {\"data\": {\"from_node\": \"toscldilationmask1\"}, \"dimension\": \"bands\", \"target\": [\"S2-CLOUD-MASK\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels2\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension1\"}, \"dimension\": \"bands\", \"target\": [\"B02\", \"B03\", \"B04\", \"B05\", \"B06\", \"B07\", \"B08\", \"B8A\", \"B11\", \"B12\", \"ABDI1\", \"ABDI2\", \"AWEInsh\", \"AVI\", \"BLFEI\", \"CIRE\", \"EVI\", \"IRECI\", \"MBWI\", \"MNDWI\", \"MNDVI\", \"NDMI\", \"NDVI\", \"NDVIMNDWI\", \"NDWI\", \"NMDI\", \"NIRv\", \"S2WI\", \"S2REP\", \"WRI\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels3\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension4\"}, \"dimension\": \"bands\", \"target\": [\"VH\", \"VV\", \"VHVVD\", \"VHVVR\", \"DpRVIVV\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels4\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension5\"}, \"dimension\": \"bands\", \"target\": [\"B02_p2\", \"B02_p5\", \"B02_p25\", \"B02_median\", \"B02_p75\", \"B02_p95\", \"B02_p98\", \"B02_mean\", \"B02_sd\", \"B02_sum\", \"B02_iqr\", \"B02_iqr0595\", \"B03_p2\", \"B03_p5\", \"B03_p25\", \"B03_median\", \"B03_p75\", \"B03_p95\", \"B03_p98\", \"B03_mean\", \"B03_sd\", \"B03_sum\", \"B03_iqr\", \"B03_iqr0595\", \"B04_p2\", \"B04_p5\", \"B04_p25\", \"B04_median\", \"B04_p75\", \"B04_p95\", \"B04_p98\", \"B04_mean\", \"B04_sd\", \"B04_sum\", \"B04_iqr\", \"B04_iqr0595\", \"B05_p2\", \"B05_p5\", \"B05_p25\", \"B05_median\", \"B05_p75\", \"B05_p95\", \"B05_p98\", \"B05_mean\", \"B05_sd\", \"B05_sum\", \"B05_iqr\", \"B05_iqr0595\", \"B06_p2\", \"B06_p5\", \"B06_p25\", \"B06_median\", \"B06_p75\", \"B06_p95\", \"B06_p98\", \"B06_mean\", \"B06_sd\", \"B06_sum\", \"B06_iqr\", \"B06_iqr0595\", \"B07_p2\", \"B07_p5\", \"B07_p25\", \"B07_median\", \"B07_p75\", \"B07_p95\", \"B07_p98\", \"B07_mean\", \"B07_sd\", \"B07_sum\", \"B07_iqr\", \"B07_iqr0595\", \"B08_p2\", \"B08_p5\", \"B08_p25\", \"B08_median\", \"B08_p75\", \"B08_p95\", \"B08_p98\", \"B08_mean\", \"B08_sd\", \"B08_sum\", \"B08_iqr\", \"B08_iqr0595\", \"B8A_p2\", \"B8A_p5\", \"B8A_p25\", \"B8A_median\", \"B8A_p75\", \"B8A_p95\", \"B8A_p98\", \"B8A_mean\", \"B8A_sd\", \"B8A_sum\", \"B8A_iqr\", \"B8A_iqr0595\", \"B11_p2\", \"B11_p5\", \"B11_p25\", \"B11_median\", \"B11_p75\", \"B11_p95\", \"B11_p98\", \"B11_mean\", \"B11_sd\", \"B11_sum\", \"B11_iqr\", \"B11_iqr0595\", \"B12_p2\", \"B12_p5\", \"B12_p25\", \"B12_median\", \"B12_p75\", \"B12_p95\", \"B12_p98\", \"B12_mean\", \"B12_sd\", \"B12_sum\", \"B12_iqr\", \"B12_iqr0595\", \"ABDI1_p2\", \"ABDI1_p5\", \"ABDI1_p25\", \"ABDI1_median\", \"ABDI1_p75\", \"ABDI1_p95\", \"ABDI1_p98\", \"ABDI1_mean\", \"ABDI1_sd\", \"ABDI1_sum\", \"ABDI1_iqr\", \"ABDI1_iqr0595\", \"ABDI2_p2\", \"ABDI2_p5\", \"ABDI2_p25\", \"ABDI2_median\", \"ABDI2_p75\", \"ABDI2_p95\", \"ABDI2_p98\", \"ABDI2_mean\", \"ABDI2_sd\", \"ABDI2_sum\", \"ABDI2_iqr\", \"ABDI2_iqr0595\", \"AWEInsh_p2\", \"AWEInsh_p5\", \"AWEInsh_p25\", \"AWEInsh_median\", \"AWEInsh_p75\", \"AWEInsh_p95\", \"AWEInsh_p98\", \"AWEInsh_mean\", \"AWEInsh_sd\", \"AWEInsh_sum\", \"AWEInsh_iqr\", \"AWEInsh_iqr0595\", \"AVI_p2\", \"AVI_p5\", \"AVI_p25\", \"AVI_median\", \"AVI_p75\", \"AVI_p95\", \"AVI_p98\", \"AVI_mean\", \"AVI_sd\", \"AVI_sum\", \"AVI_iqr\", \"AVI_iqr0595\", \"BLFEI_p2\", \"BLFEI_p5\", \"BLFEI_p25\", \"BLFEI_median\", \"BLFEI_p75\", \"BLFEI_p95\", \"BLFEI_p98\", \"BLFEI_mean\", \"BLFEI_sd\", \"BLFEI_sum\", \"BLFEI_iqr\", \"BLFEI_iqr0595\", \"CIRE_p2\", \"CIRE_p5\", \"CIRE_p25\", \"CIRE_median\", \"CIRE_p75\", \"CIRE_p95\", \"CIRE_p98\", \"CIRE_mean\", \"CIRE_sd\", \"CIRE_sum\", \"CIRE_iqr\", \"CIRE_iqr0595\", \"EVI_p2\", \"EVI_p5\", \"EVI_p25\", \"EVI_median\", \"EVI_p75\", \"EVI_p95\", \"EVI_p98\", \"EVI_mean\", \"EVI_sd\", \"EVI_sum\", \"EVI_iqr\", \"EVI_iqr0595\", \"IRECI_p2\", \"IRECI_p5\", \"IRECI_p25\", \"IRECI_median\", \"IRECI_p75\", \"IRECI_p95\", \"IRECI_p98\", \"IRECI_mean\", \"IRECI_sd\", \"IRECI_sum\", \"IRECI_iqr\", \"IRECI_iqr0595\", \"MBWI_p2\", \"MBWI_p5\", \"MBWI_p25\", \"MBWI_median\", \"MBWI_p75\", \"MBWI_p95\", \"MBWI_p98\", \"MBWI_mean\", \"MBWI_sd\", \"MBWI_sum\", \"MBWI_iqr\", \"MBWI_iqr0595\", \"MNDWI_p2\", \"MNDWI_p5\", \"MNDWI_p25\", \"MNDWI_median\", \"MNDWI_p75\", \"MNDWI_p95\", \"MNDWI_p98\", \"MNDWI_mean\", \"MNDWI_sd\", \"MNDWI_sum\", \"MNDWI_iqr\", \"MNDWI_iqr0595\", \"MNDVI_p2\", \"MNDVI_p5\", \"MNDVI_p25\", \"MNDVI_median\", \"MNDVI_p75\", \"MNDVI_p95\", \"MNDVI_p98\", \"MNDVI_mean\", \"MNDVI_sd\", \"MNDVI_sum\", \"MNDVI_iqr\", \"MNDVI_iqr0595\", \"NDMI_p2\", \"NDMI_p5\", \"NDMI_p25\", \"NDMI_median\", \"NDMI_p75\", \"NDMI_p95\", \"NDMI_p98\", \"NDMI_mean\", \"NDMI_sd\", \"NDMI_sum\", \"NDMI_iqr\", \"NDMI_iqr0595\", \"NDVI_p2\", \"NDVI_p5\", \"NDVI_p25\", \"NDVI_median\", \"NDVI_p75\", \"NDVI_p95\", \"NDVI_p98\", \"NDVI_mean\", \"NDVI_sd\", \"NDVI_sum\", \"NDVI_iqr\", \"NDVI_iqr0595\", \"NDVIMNDWI_p2\", \"NDVIMNDWI_p5\", \"NDVIMNDWI_p25\", \"NDVIMNDWI_median\", \"NDVIMNDWI_p75\", \"NDVIMNDWI_p95\", \"NDVIMNDWI_p98\", \"NDVIMNDWI_mean\", \"NDVIMNDWI_sd\", \"NDVIMNDWI_sum\", \"NDVIMNDWI_iqr\", \"NDVIMNDWI_iqr0595\", \"NDWI_p2\", \"NDWI_p5\", \"NDWI_p25\", \"NDWI_median\", \"NDWI_p75\", \"NDWI_p95\", \"NDWI_p98\", \"NDWI_mean\", \"NDWI_sd\", \"NDWI_sum\", \"NDWI_iqr\", \"NDWI_iqr0595\", \"NMDI_p2\", \"NMDI_p5\", \"NMDI_p25\", \"NMDI_median\", \"NMDI_p75\", \"NMDI_p95\", \"NMDI_p98\", \"NMDI_mean\", \"NMDI_sd\", \"NMDI_sum\", \"NMDI_iqr\", \"NMDI_iqr0595\", \"NIRv_p2\", \"NIRv_p5\", \"NIRv_p25\", \"NIRv_median\", \"NIRv_p75\", \"NIRv_p95\", \"NIRv_p98\", \"NIRv_mean\", \"NIRv_sd\", \"NIRv_sum\", \"NIRv_iqr\", \"NIRv_iqr0595\", \"S2WI_p2\", \"S2WI_p5\", \"S2WI_p25\", \"S2WI_median\", \"S2WI_p75\", \"S2WI_p95\", \"S2WI_p98\", \"S2WI_mean\", \"S2WI_sd\", \"S2WI_sum\", \"S2WI_iqr\", \"S2WI_iqr0595\", \"S2REP_p2\", \"S2REP_p5\", \"S2REP_p25\", \"S2REP_median\", \"S2REP_p75\", \"S2REP_p95\", \"S2REP_p98\", \"S2REP_mean\", \"S2REP_sd\", \"S2REP_sum\", \"S2REP_iqr\", \"S2REP_iqr0595\", \"WRI_p2\", \"WRI_p5\", \"WRI_p25\", \"WRI_median\", \"WRI_p75\", \"WRI_p95\", \"WRI_p98\", \"WRI_mean\", \"WRI_sd\", \"WRI_sum\", \"WRI_iqr\", \"WRI_iqr0595\", \"VH_p2\", \"VH_p5\", \"VH_p25\", \"VH_median\", \"VH_p75\", \"VH_p95\", \"VH_p98\", \"VH_mean\", \"VH_sd\", \"VH_sum\", \"VH_iqr\", \"VH_iqr0595\", \"VV_p2\", \"VV_p5\", \"VV_p25\", \"VV_median\", \"VV_p75\", \"VV_p95\", \"VV_p98\", \"VV_mean\", \"VV_sd\", \"VV_sum\", \"VV_iqr\", \"VV_iqr0595\", \"VHVVD_p2\", \"VHVVD_p5\", \"VHVVD_p25\", \"VHVVD_median\", \"VHVVD_p75\", \"VHVVD_p95\", \"VHVVD_p98\", \"VHVVD_mean\", \"VHVVD_sd\", \"VHVVD_sum\", \"VHVVD_iqr\", \"VHVVD_iqr0595\", \"VHVVR_p2\", \"VHVVR_p5\", \"VHVVR_p25\", \"VHVVR_median\", \"VHVVR_p75\", \"VHVVR_p95\", \"VHVVR_p98\", \"VHVVR_mean\", \"VHVVR_sd\", \"VHVVR_sum\", \"VHVVR_iqr\", \"VHVVR_iqr0595\", \"DpRVIVV_p2\", \"DpRVIVV_p5\", \"DpRVIVV_p25\", \"DpRVIVV_median\", \"DpRVIVV_p75\", \"DpRVIVV_p95\", \"DpRVIVV_p98\", \"DpRVIVV_mean\", \"DpRVIVV_sd\", \"DpRVIVV_sum\", \"DpRVIVV_iqr\", \"DpRVIVV_iqr0595\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels5\": {\"arguments\": {\"data\": {\"from_node\": \"reducedimension1\"}, \"dimension\": \"bands\", \"target\": [\"S2-NVBT\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels6\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension6\"}, \"dimension\": \"bands\", \"target\": [\"LST_mean\", \"LST_max\", \"LST_min\", \"LST_range\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels7\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension7\"}, \"dimension\": \"bands\", \"target\": [\"lai_mean\", \"lai_max\", \"lai_min\", \"lai_range\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels8\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension8\"}, \"dimension\": \"bands\", \"target\": [\"ssm_mean\", \"ssm_max\", \"ssm_min\", \"ssm_range\"]}, \"process_id\": \"rename_labels\"}, \"renamelabels9\": {\"arguments\": {\"data\": {\"from_node\": \"applydimension9\"}, \"dimension\": \"bands\", \"target\": [\"precipitation-flux_mean\", \"precipitation-flux_max\", \"precipitation-flux_min\", \"precipitation-flux_range\", \"temperature-mean_mean\", \"temperature-mean_max\", \"temperature-mean_min\", \"temperature-mean_range\"]}, \"process_id\": \"rename_labels\"}, \"resamplespatial1\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"loadcollection1\"}, \"method\": \"near\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"resamplespatial2\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"loadcollection2\"}, \"method\": \"near\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"resamplespatial3\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"sarbackscatter1\"}, \"method\": \"near\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"resamplespatial4\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"reducedimension2\"}, \"method\": \"bilinear\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"resamplespatial5\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"renamelabels6\"}, \"method\": \"near\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"resamplespatial6\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"renamelabels7\"}, \"method\": \"near\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"resamplespatial7\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"renamelabels8\"}, \"method\": \"near\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"resamplespatial8\": {\"arguments\": {\"align\": \"upper-left\", \"data\": {\"from_node\": \"loadstac1\"}, \"method\": \"near\", \"projection\": 3035, \"resolution\": 10.0}, \"process_id\": \"resample_spatial\"}, \"sarbackscatter1\": {\"arguments\": {\"coefficient\": \"sigma0-ellipsoid\", \"contributing_area\": false, \"data\": {\"from_node\": \"loadcollection3\"}, \"elevation_model\": \"COPERNICUS_30\", \"ellipsoid_incidence_angle\": false, \"local_incidence_angle\": false, \"mask\": false, \"noise_removal\": true, \"options\": {\"debug\": false, \"elev_geoid\": \"/opt/openeo-vito-aux-data/egm96.tif\", \"implementation_version\": \"2\", \"otb_memory\": 1024, \"tile_size\": 16}}, \"process_id\": \"sar_backscatter\"}, \"saveresult1\": {\"arguments\": {\"data\": {\"from_node\": \"mergecubes7\"}, \"format\": \"GTiff\", \"options\": {}}, \"process_id\": \"save_result\", \"result\": true}, \"toscldilationmask1\": {\"arguments\": {\"data\": {\"from_node\": \"resamplespatial2\"}, \"erosion_kernel_size\": 3, \"kernel1_size\": 17, \"kernel2_size\": 77, \"mask1_values\": [2, 4, 5, 6, 7], \"mask2_values\": [3, 8, 9, 10, 11], \"scl_band_name\": \"SCL\"}, \"process_id\": \"to_scl_dilation_mask\"}}}, \"progress\": 100, \"python-memory\": \"disable\", \"soft-errors\": 0.05, \"stac-version\": \"1.1\", \"status\": \"finished\", \"title\": \"eo_feature cube (10x10km)\", \"updated\": \"2026-07-01T10:41:23Z\", \"usage\": {\"cpu\": {\"unit\": \"cpu-seconds\", \"value\": 8034}, \"duration\": {\"unit\": \"seconds\", \"value\": 1681}, \"input_pixel\": {\"unit\": \"mega-pixel\", \"value\": 673.2793788909912}, \"max_executor_memory\": {\"unit\": \"gb\", \"value\": 6.074092864990234}, \"memory\": {\"unit\": \"mb-seconds\", \"value\": 123371520}, \"memory_requested\": {\"unit\": \"mb-seconds\", \"value\": 123371520}, \"network_received\": {\"unit\": \"b\", \"value\": 44285145021}, \"orfeo_backscatter_input_pixels\": {\"unit\": \"count\", \"value\": 117863424}, \"sar_backscatter_soft_errors\": {\"unit\": \"fraction\", \"value\": 0}}}}</script>\n",
+       "    </openeo-job>\n",
+       "    "
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "execution_count": 8
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## now upscale the the final 20x20km tiles",
+   "id": "3d9134ce13226561"
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": [
+    "# we take as example an 20x20km tile in EU LAEA grid around Vienna\n",
+    "AOI = {'west': 4780000, 'east': 4800000, 'south': 2820000, 'north': 2840000, 'crs': 3035}\n",
+    "# increasing driver memory\n",
+    "job_options.update({\n",
+    "    \"driver-memory\": \"10G\",\n",
+    "    \"driver-memoryOverhead\": \"4G\",\n",
+    "})\n",
+    "data4 = create_EOfeature_cube_WEED_V1(con, AOI, start, end, collection_options, processing_options)"
+   ],
+   "id": "b7fe80d4f70e9b87"
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "data4.execute_batch(r'C:\\Users\\buchhorm\\Downloads\\test_cube\\eo_feature_cube_beta2_20x20.tif', title='eo_feature cube (20x20km)', job_options=job_options)",
+   "id": "a2be83f50c1aa7d0"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "weed",
+   "language": "python",
+   "name": "weed"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.14.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/requirements.txt b/requirements.txt
index d88a11c..1f5f001 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -15,6 +15,7 @@ fastparquet>=2024.5.0
 pydrive2[fsspec]>=1.21.1
 hvac>=2.3.0
 boto3>=1.36.16
+requests>=2.32.0
 skl2onnx==1.19.1
 psycopg2-binary>=2.9.10
 folium>=0.17.0
diff --git a/scripts/global_120x120km_UTM_tiling-grid.py b/scripts/global_120x120km_UTM_tiling-grid.py
new file mode 100644
index 0000000..b692e37
--- /dev/null
+++ b/scripts/global_120x120km_UTM_tiling-grid.py
@@ -0,0 +1,120 @@
+"""
+this script generates a global 120x120km tiling grid in UTM.
+
+"""
+
+
+'''
+STEPS
+1. load the UTM zones gpkg
+2. load the global land masses gpkg
+3. loop over the 120 UTM zones
+    a. load the full 120x120 km grid depending on the hemisphere and change the epsg to the UTM zone
+    b. load a copy of the UTM zone polygon and warp to correct epsg
+    c. select the grid cells intersecting the UTM zone polygon and delete non-needed
+    d. load a copy of the land masses polygon and warp to correct epsg
+    e. select the grid cells intersecting the land masses and dlete non-needed ones
+    f. run over the remaining 120x120km tiles and add the naming as well as
+       add the openEO bbox dict using the bounds of the polygon (plus add the bounds in WGS84)
+    g. convert the geodataframe back to EPSG:4326 and save it to a new gpkg
+4. combine all UTM zones into one gpkg and clean up the metadata
+5. save the final global processing grid in the package ressources
+
+'''
+
+import geopandas as gpd
+import pandas as pd
+import math
+from eo_processing.utils.mgrs import UTM_2_grid20id
+import os
+
+# standard paths
+path_grid_n = os.path.normpath(r'C:\Users\buchhorm\Downloads\120x120km_grid\basic_120x120km_grid_nothern_no-crs_v2.gpkg')
+path_grid_s = os.path.normpath(r'C:\Users\buchhorm\Downloads\120x120km_grid\basic_120x120km_grid_southern_no-crs_v2.gpkg')
+path_land = os.path.normpath(r'C:\Users\buchhorm\Downloads\120x120km_grid\land_sea_mask_20kmbuffered_EPSG4326_v2.gpkg')
+path_utm = os.path.normpath(r'C:\Users\buchhorm\Downloads\120x120km_grid\UTM_zones_high-res_EPSG4326.gpkg')
+
+# load UTM zones
+gdf_utm = gpd.read_file(path_utm)
+
+# loop over all UTM zones
+lZones = gdf_utm.name.unique().tolist()
+lFiles = []
+
+for UTMzone in lZones:
+    print(f'processing zone: {UTMzone}')
+    # get the UTM zone polygon and the EPSG
+    if UTMzone[-1] == 'N':
+        epsg = 32600 + int(UTMzone[:2])
+    else:
+        epsg = 32700 + int(UTMzone[:2])
+
+    gdf_zone = gdf_utm[gdf_utm.name == UTMzone].copy()
+
+    path_out = os.path.normpath(
+            r'C:\Users\buchhorm\Downloads\120x120km_grid\results\UTM_zone_{0}.gpkg'.format(
+                epsg))
+    os.makedirs(os.path.dirname(path_out), exist_ok=True)
+
+    if not os.path.exists(path_out):
+        # get the land masses
+        gdf_land = gpd.read_file(path_land)
+        gdf_land = gdf_land.clip(gdf_zone)
+        gdf_land = gdf_land.dissolve()
+
+        # bring all to correct epsg
+        gdf_zone = gdf_zone.to_crs(epsg=epsg)
+        gdf_land = gdf_land.to_crs(epsg=epsg)
+
+        # short cut if the gdf_land is empty
+        if gdf_land.empty:
+            continue
+
+        # now we load the basic 120x120km grid and set the crs to the correct epsg
+        if UTMzone[-1] == 'N':
+            gdf_grid = gpd.read_file(path_grid_n).set_crs(epsg=epsg, allow_override=True)
+        else:
+            gdf_grid = gpd.read_file(path_grid_s).set_crs(epsg=epsg, allow_override=True)
+
+        # select grid cells which are intersecting with utm zone
+        gdf_grid = gdf_grid[gdf_grid.intersects(gdf_zone.union_all(method='coverage'))]
+
+        # intersecting
+        gdf_grid = gdf_grid[gdf_grid.intersects(gdf_land.union_all(method='coverage'))]
+
+        # add the bbox dict for openEO
+        gdf_grid['bbox_dict'] = gdf_grid.apply(
+            lambda row: {
+                'west': math.floor(row.geometry.bounds[0] / 100) * 100.,
+                'south': math.floor(row.geometry.bounds[1] / 100) * 100.,
+                'east': math.ceil(row.geometry.bounds[2] / 100) * 100.,
+                'north': math.ceil(row.geometry.bounds[3] / 100) * 100.,
+                'crs': epsg
+            }, axis=1
+        )
+
+        # save to disk
+
+
+        gdf_grid[['left', 'top', 'right', 'bottom', 'row_index','col_index',  'bbox_dict', 'geometry']].to_file(
+            path_out)
+    else:
+        # load
+        gdf_grid = gpd.read_file(path_out)
+        gdf_zone = gdf_zone.to_crs(epsg=epsg)
+        gdf_grid = gdf_grid.clip(gdf_zone)
+        gdf_grid.to_file(path_out)
+
+    lFiles.append(path_out)
+
+
+# load all geopackages which were produced and convert to EPSG:4326 and merge them into one GeoDataFrame
+result = gpd.GeoDataFrame(columns=['left', 'top', 'right', 'bottom', 'row_index','col_index', 'bbox_dict', 'geometry'], geometry='geometry', crs='EPSG:4326')
+
+for file in lFiles:
+    gdf_tmp = gpd.read_file(file)
+    gdf_tmp = gdf_tmp.to_crs(epsg=4326)
+    result = pd.concat([result, gdf_tmp], ignore_index=True)
+
+# save final result to disk
+result.to_file(os.path.normpath(r'C:\Users\buchhorm\Downloads\120x120km_grid\ECDC_global_120x120km_grid.gpkg'))
diff --git a/scripts/laea_tiling_grids_2_high_res_Sentinel2_tiles.py b/scripts/laea_tiling_grids_2_high_res_Sentinel2_tiles.py
index eb6500a..4444e26 100644
--- a/scripts/laea_tiling_grids_2_high_res_Sentinel2_tiles.py
+++ b/scripts/laea_tiling_grids_2_high_res_Sentinel2_tiles.py
@@ -28,17 +28,17 @@ def get_epsg(tile_id):
     return target_EPSG
 
 # filter to tiles in UTM zones needed for pan EU
-df2 = pd.read_csv(r'C:\Users\buchhorm\Downloads\new_grids\utm_codes_europe.csv')
-df2['utm'] = df2['ZONE'].astype(str) + df2['ROW_']
-lNeeded = df2['utm'].tolist()
+#df2 = pd.read_csv(r'C:\Users\buchhorm\Downloads\new_grids\utm_codes_europe.csv')
+#df2['utm'] = df2['ZONE'].astype(str) + df2['ROW_']
+#lNeeded = df2['utm'].tolist()
 
 
 ## Start read out everything we need with beautiful soup from Sentinel-2 KML
-xml_file = r'C:\Users\buchhorm\Downloads\new_grids\Sentinel2_tiles.kml'
-soup = bs.BeautifulSoup(open(xml_file), 'xml')
+xml_file = r'C:\Users\buchhorm\Downloads\120x120km_grid\S2_tiles.kml'
+soup = bs.BeautifulSoup(open(xml_file), 'html.parser')
 
 #find all VRTRasterBands in the soup
-tiles = soup.findAll('description')
+tiles = soup.find_all('description')
 
 data = []
 
@@ -57,8 +57,8 @@ def get_epsg(tile_id):
         cols = [ele.text.strip() for ele in cols]
         if cols[0] == 'TILE_ID': data1 = cols[1]
         if cols[0] == 'UTM_WKT': data2 = cols[1]
-    if data1[:3] in lNeeded:
-        data.append((data1, data2, get_epsg(data1)))
+
+    data.append((data1, data2, get_epsg(data1)))
 
 df = pd.DataFrame(data, columns=['tile_id', 'geometry', 'epsg'])
 data = None
@@ -80,10 +80,10 @@ def get_epsg(tile_id):
     # add extra points in 250m intervall
     gdf['geometry'] = gdf['geometry'].apply(lambda x: x.segmentize(250))
 
-    gdf2 = gdf.to_crs(epsg=3035)
+    gdf2 = gdf.to_crs(epsg=4326)
     list_results.append(gdf2)
 
 result = gpd.GeoDataFrame(pd.concat(list_results, ignore_index=True), crs=list_results[0].crs)
 
 # write out
-result.to_file(r'C:\Users\buchhorm\Downloads\new_grids\Sentinel2_tiling_grid_EU_high_res_EPSG3035.gpkg', driver='GPKG')
+result.to_file(r'C:\Users\buchhorm\Downloads\120x120km_grid\Sentinel2_tiling_grid_high_res_EPSG4326.gpkg', driver='GPKG')
diff --git a/src/eo_processing/_version.py b/src/eo_processing/_version.py
index 5680ebc..35b620f 100644
--- a/src/eo_processing/_version.py
+++ b/src/eo_processing/_version.py
@@ -1,3 +1,3 @@
 #!/usr/bin/env python3
 
-__version__ = '0.6.0'
+__version__ = '0.7.0'
diff --git a/src/eo_processing/config/settings.py b/src/eo_processing/config/settings.py
index e9a0312..12f11a1 100644
--- a/src/eo_processing/config/settings.py
+++ b/src/eo_processing/config/settings.py
@@ -1,5 +1,5 @@
 from __future__ import annotations
-from typing import List, Optional, Dict, Union, TYPE_CHECKING
+from typing import List, Optional, Dict, Union, TYPE_CHECKING, Any
 
 if TYPE_CHECKING:
     from eo_processing.config.data_formats import storage_option_format
@@ -14,12 +14,13 @@
 # ---------------------------------------------------
 # standard processing options S1/S2
 TARGET_CRS: int = 3035                   # can be all known EPSG codes
-TARGET_RESOLUTION: float = 10.
+TARGET_RESOLUTION: float|int = 10.
 S1_ORBITDIRECTION: str = 'DESCENDING'
 S2_BANDS: List[str] = ["B02", "B03", "B04", "B05", "B06", "B07", "B08", "B8A", "B11", "B12"]
 S2_MAX_CLOUD_COVER: int = 95
 MASKING_ALGO: str = 'mask_scl_dilation'
 APPLY_CLOUD_MASK: bool = True
+GET_NVBT: bool = False
 S2_TILEID_LIST: Optional[List[str]] = None
 SKIP_CHECK_S1: bool = False
 SKIP_CHECK_S2: bool = False
@@ -52,23 +53,23 @@
 RADAR_LIST: List[str] = ['VHVVD',
               'VHVVR',
               'DpRVIVV']
-S2_SCALING: List = [0, 10000, 0, 1.0]
+S2_SCALING: List[Union[int, float]] = [0, 10000, 0, 1.0]
 # ---------------------------------------------------
 # Planet Processing options
 PLANET_MASKING_ALGO: str = 'mask_udm_dilation'
 PLANET_BANDS: List[str] = ["B01", "B02", "B03", "B04", "B05", "B06", "B07", "B08"] # Same for UDM2 and Spectral bands
-PLANET_RESOLUTION: float = 3.0
+PLANET_RESOLUTION: float|int = 3.0
 PLANET_VI_LIST: List[str] = ['NDVI',
            'AVI',
            'CIRE',
            'NIRv',
            'NDWI'
            ]
-PLANET_SCALING: List = [0, 10000, 0, 1.0]
-
+PLANET_SCALING: List[Union[int, float]] = [0, 10000, 0, 1.0]
+HRVPP_COLLECTION: str = 'copernicus_r_utm-wgs84_10_m_hrvpp-vpp_p_2017-now_v01_direct'  #special case with 2 seasons iso 1 year
 # ---------------------------------------------------
 # Job options for OpenEO
-OPENEO_EXTRACT_JOB_OPTIONS: Dict[str, str] = {
+OPENEO_EXTRACT_JOB_OPTIONS: Dict[str, Union[str, int, float, List]] = {
     "driver-memory": "4G",
     "driver-memoryOverhead": "8G",
     "driver-cores": 2,
@@ -80,7 +81,7 @@
     "stac-version":"1.1"
 }
 
-OPENEO_EXTRACT_CREO_JOB_OPTIONS: Dict[str, str] = {
+OPENEO_EXTRACT_CREO_JOB_OPTIONS: Dict[str, Union[str, int, float, List]] = {
     "driver-memory": "4G",
     "driver-memoryOverhead": "2G",
     "driver-cores": 1,
@@ -91,7 +92,7 @@
     "max-executors": 200
 }
 
-OPENEO_EXTRACT_CDSE_JOB_OPTIONS: Dict[str, str] = {
+OPENEO_EXTRACT_CDSE_JOB_OPTIONS: Dict[str, Union[str, int, float, List]] = {
     "driver-memory": "8G",
     "driver-memoryOverhead": "5G",
     "driver-cores": 1,
@@ -103,7 +104,7 @@
     "logging-threshold": "info"
 }
 
-OPENEO_INFERENCE_CDSE_JOB_OPTIONS: Dict[str, str] = {
+OPENEO_INFERENCE_CDSE_JOB_OPTIONS: Dict[str, Union[str, int, float, List]] = {
     "driver-memory": "1000m",
     "driver-memoryOverhead": "1000m",
     "driver-cores": 1,
@@ -118,7 +119,7 @@
     ]
 }
 
-OPENEO_POINTEXTRACTION_CDSE_JOB_OPTIONS: Dict[str, str] = {
+OPENEO_POINTEXTRACTION_CDSE_JOB_OPTIONS: Dict[str, Union[str, int, float, List]] = {
     "driver-memory": "4G",
     "driver-memoryOverhead": "2G",
     "driver-cores": 1,
@@ -130,7 +131,7 @@
     "logging-threshold": "info"
 }
 
-OPENEO_CUBEEXTRACTION_CDSE_JOB_OPTIONS: Dict[str, str] = {
+OPENEO_CUBEEXTRACTION_CDSE_JOB_OPTIONS: Dict[str, Union[str, int, float, List]] = {
     "driver-memory": "4G",
     "driver-memoryOverhead": "4G",
     "driver-cores": 1,
@@ -168,7 +169,7 @@
     'S1_collection': "SENTINEL1_GRD"
 }
 
-def _get_default_job_options() -> Dict[str, str]:
+def _get_default_job_options() -> Dict[str, Union[str, int, float, List]]:
     """
     Retrieves the default job options for OpenEO extract operations.
 
@@ -181,7 +182,7 @@ def _get_default_job_options() -> Dict[str, str]:
     """
     return OPENEO_EXTRACT_JOB_OPTIONS.copy()
 
-def get_job_options(provider: str = None, task: str = 'raw_extraction') -> Dict[str, str]:
+def get_job_options(provider: str = None, task: str = 'raw_extraction') -> Dict[str, Union[str, int, float, List]]:
     """
     Retrieve job options based on the specified provider and task.
 
@@ -249,7 +250,8 @@ def get_collection_options(provider: str) -> Dict[str, str]:
     else:
         raise ValueError(f'Provider `{provider}` not known.')
 
-def get_standard_processing_options(provider: str, task: str = 'raw_extraction') -> dict:
+def get_standard_processing_options(provider: str, task: str = 'raw_extraction') \
+        -> Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]]:
     """
     Generate standard processing options based on the provider and specified task.
 
@@ -288,6 +290,7 @@ def get_standard_processing_options(provider: str, task: str = 'raw_extraction')
             "skip_check_S1": SKIP_CHECK_S1,
             "skip_check_S2": SKIP_CHECK_S2,
             "apply_cloud_mask": APPLY_CLOUD_MASK,
+            "get_NVBT": False,  # NVBT is only added for feature cubes without time domain
             "openeo_chunk_size": CHUNK_SIZE,
         }
     elif (task == 'feature_generation') or (task == 'vi_generation'):
@@ -307,6 +310,7 @@ def get_standard_processing_options(provider: str, task: str = 'raw_extraction')
             "skip_check_S1": SKIP_CHECK_S1,
             "skip_check_S2": SKIP_CHECK_S2,
             "apply_cloud_mask": APPLY_CLOUD_MASK,
+            "get_NVBT": GET_NVBT,
             "optical_vi_list" : VI_LIST,
             "radar_vi_list" : RADAR_LIST,
             "S2_scaling" : S2_SCALING,
@@ -314,6 +318,8 @@ def get_standard_processing_options(provider: str, task: str = 'raw_extraction')
             "append" : True,
             "openeo_chunk_size": CHUNK_SIZE,
         }
+        if task == 'vi_generation':
+            proc_opt['get_NVBT'] = False # NVBT is only added for feature cubes without time domain
     else:
         raise ValueError(f'Task `{task}` not known.')
     return proc_opt
@@ -325,62 +331,50 @@ def get_advanced_options(provider: str, s1_orbitdirection: Optional[str] = S1_OR
                          S1_temporal_reducer: str = S1_TEMPORAL_REDUCER, slc_masking: Optional[str] = MASKING_ALGO,
                          S2_bands: List[str] = S2_BANDS, s2_tileid_list: Optional[List[str]] = S2_TILEID_LIST,
                          skip_check_S1: bool = SKIP_CHECK_S1, skip_check_S2: bool = SKIP_CHECK_S2,
-                         apply_cloud_mask: bool = APPLY_CLOUD_MASK, S2_max_cloud_cover: int = S2_MAX_CLOUD_COVER,
+                         apply_cloud_mask: bool = APPLY_CLOUD_MASK, get_NVBT: bool = GET_NVBT,
+                         S2_max_cloud_cover: int = S2_MAX_CLOUD_COVER,
                          optical_vi_list: List[str] = VI_LIST, radar_vi_list: List[str] = RADAR_LIST,
                          S2_scaling: List[int | float] = S2_SCALING, S1_db_rescale: bool = True,
-                         append: bool = True) -> Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]:
+                         append: bool = True) \
+        -> Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]]:
     """
-    Generate a dictionary of advanced options for processing satellite imagery.
-
-    This function validates input parameters and prepares a dictionary of options
-    required for processing satellite imagery data. Validation is applied for
-    various parameters to ensure that the provided values conform to the expected
-    formats or constraints. The function checks for valid values for key options
-    like satellite orbit direction, target coordinate reference system (CRS),
-    resolution, and others before constructing the dictionary.
-
-    :param provider: The provider of satellite data.
-    :param s1_orbitdirection: Direction of Sentinel-1 pass, can be 'ASCENDING',
-                              'DESCENDING' or None.
-    :param target_crs: An integer representing the target coordinate reference
-                       system (CRS).
-    :param resolution: The spatial resolution of the output in integer or float
-                       format.
-    :param ts_interpolation: Boolean indicating whether to apply linear time-series
-                             interpolation.
-    :param ts_interval: Interval for time series aggregation (temporal binning). Accepted values
-                        are 'day', 'week', 'dekad', 'month', 'season', 'year', or
-                        None.
-    :param S2_temporal_reducer: Method for reducing temporal data for Sentinel-2.
-                                Valid options include 'median', 'mean', 'max',
-                                'min', 'first', 'last', 'product', 'sd', 'sum',
-                                or 'variance'.
-    :param S1_temporal_reducer: Method for reducing temporal data for Sentinel-1.
-                                Valid options include 'median', 'mean', 'max',
-                                'min', 'first', 'last', 'product', 'sd', 'sum',
-                                or 'variance'.
-    :param slc_masking: Masking approach to be applied. Valid options are
-                        'mask_scl_dilation', 'satio', or None.
-    :param S2_bands: List of selected Sentinel-2 reflectance bands.
-    :param s2_tileid_list: Optional list of Sentinel-2 tiles for processing. Can
-                           be None if tiles are not specified.
-    :param skip_check_S1: Boolean indicating whether to skip validation checks
-                          for Sentinel-1 data.
-    :param skip_check_S2: Boolean indicating whether to skip validation checks
-                          for Sentinel-2 data.
-    :param apply_cloud_mask: Boolean indicating whether to apply cloud masking or to add it as own band.
-    :param S2_max_cloud_cover: Maximum allowable cloud cover percentage for
-                               Sentinel-2 data. Acceptable values are integers
-                               between 0 and 100.
-    :param optical_vi_list: List of selected vegetation indices for optical data.
-    :param radar_vi_list: List of selected vegetation indices for radar data.
-    :param S2_scaling: List of scaling factors to be applied to Sentinel-2 data.
-    :param S1_db_rescale: Boolean controlling whether Sentinel-1 data must be
-                          rescaled in decibels.
-    :param append: Boolean indicating whether to append the VI's to the reflectance cube or to replace them.
-    :param openeo_chunk_size: Chunk size for OpenEO processing.
-
-    :return: A dictionary containing all validated options as key-value pairs.
+    Generates a comprehensive dictionary of advanced processing options for satellite data workflows.
+    This function validates the provided parameters and ensures that the inputs comply with the
+    accepted formats and values. It returns a dictionary containing key-value pairs suitable for
+    configuring advanced processing tasks.
+
+    :param provider: (str) The provider for the data processing task.
+    :param s1_orbitdirection: (Optional[str]) The direction of Sentinel-1 orbit. Acceptable values
+        are 'ASCENDING', 'DESCENDING', or None.
+    :param target_crs: (Optional[int]) The target coordinate reference system (CRS) as an integer value.
+    :param resolution: (int | float) The spatial resolution of the data.
+    :param ts_interpolation: (bool) Whether to enable time-series interpolation.
+    :param ts_interval: (Optional[str]) The time-series interval. Acceptable values are 'day',
+        'week', 'dekad', 'month', 'season', 'year', or None.
+    :param S2_temporal_reducer: (str) Temporal reducer function for Sentinel-2 data. Supported
+        values include 'median', 'mean', 'max', 'min', 'first', 'last', 'product', 'sd', 'sum',
+        and 'variance'.
+    :param openeo_chunk_size: (int) The OpenEO chunk size for processing data.
+    :param S1_temporal_reducer: (str) Temporal reducer function for Sentinel-1 data. Supported
+        values include 'median', 'mean', 'max', 'min', 'first', 'last', 'product', 'sd', 'sum',
+        and 'variance'.
+    :param slc_masking: (Optional[str]) Masking algorithm for Sentinel-1 SLC data. Acceptable
+        values are 'mask_scl_dilation', 'satio', or None.
+    :param S2_bands: (List[str]) List of Sentinel-2 reflectance bands to include.
+    :param s2_tileid_list: (Optional[List[str]]) List of specific Sentinel-2 tile IDs to process, or None.
+    :param skip_check_S1: (bool) Toggles whether to skip quality checks for Sentinel-1 data.
+    :param skip_check_S2: (bool) Toggles whether to skip quality checks for Sentinel-2 data.
+    :param apply_cloud_mask: (bool) Whether to apply cloud masking to the data.
+    :param get_NVBT: (bool) Whether to generate the input data quality indicator (NVBT) for the data.
+    :param S2_max_cloud_cover: (int) Maximum allowed cloud cover percentage for Sentinel-2
+        data. Must be between 0 and 100.
+    :param optical_vi_list: (List[str]) List of optical vegetation indices to include in the workflow.
+    :param radar_vi_list: (List[str]) List of radar vegetation indices to include in the workflow.
+    :param S2_scaling: (List[int | float]) Scaling factors for Sentinel-2 data processing.
+    :param S1_db_rescale: (bool) Whether to apply dB rescaling to Sentinel-1 data.
+    :param append: (bool) Whether to append additional configuration options.
+    :return: Dictionary containing the validated processing options. Each key corresponds to a
+        configurable parameter, and the values reflect the input parameter values or defaults.
     """
 
     if s1_orbitdirection not in ['ASCENDING', 'DESCENDING', None]:
@@ -448,6 +442,9 @@ def get_advanced_options(provider: str, s1_orbitdirection: Optional[str] = S1_OR
     if type(apply_cloud_mask) != bool:
         raise ValueError(f'parameter for apply_cloud_mask must be an boolean.')
 
+    if type(get_NVBT) != bool:
+        raise ValueError(f'parameter for get_NVBT must be an boolean.')
+
     proc_opt = {
         "provider": provider,
         "s1_orbitdirection": s1_orbitdirection,
@@ -464,6 +461,7 @@ def get_advanced_options(provider: str, s1_orbitdirection: Optional[str] = S1_OR
         "skip_check_S1": skip_check_S1,
         "skip_check_S2": skip_check_S2,
         "apply_cloud_mask": apply_cloud_mask,
+        "get_NVBT": get_NVBT,
         "optical_vi_list": optical_vi_list,
         "radar_vi_list": radar_vi_list,
         "S2_scaling": S2_scaling,
@@ -504,9 +502,9 @@ def generate_storage_options(workspace_export: bool = False,
 
     #just some checks to avoid missing parameters
     if workspace_export and not S3_prefix:
-        raise print("You want to export the openEO results to S3, please specify the S3_prefix parameter.")
+        raise ValueError("You want to export the openEO results to S3, please specify the S3_prefix parameter.")
 
     if workspace_export and not storage:
-        raise print("A storage object has to be defined to specify the export_workspace name "
+        raise ValueError("A storage object has to be defined to specify the export_workspace name "
                     "and/or allow local_file_copy.")
     return storage_options
diff --git a/src/eo_processing/openeo/preprocessing.py b/src/eo_processing/openeo/preprocessing.py
index 8195331..f7160d7 100644
--- a/src/eo_processing/openeo/preprocessing.py
+++ b/src/eo_processing/openeo/preprocessing.py
@@ -8,7 +8,8 @@
                                                  catalogue_check_CDSE_S1, catalogue_check_CDSE_S2)
 from eo_processing.config.settings import S2_BANDS, PLANET_BANDS, CHUNK_SIZE
 
-from typing import Optional, Dict, Union, List, TYPE_CHECKING
+from typing import Optional, Dict, Union, List, TYPE_CHECKING, Any, Tuple
+
 if TYPE_CHECKING:
     from eo_processing.config.data_formats import openEO_bbox_format
 
@@ -16,7 +17,7 @@ def ts_datacube_extraction(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S2_collection: str ='SENTINEL2_L2A',
         S1_collection: Optional[str] ='SENTINEL1_GRD',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]]) -> DataCube:
     """ Warper to extract a full data cube of preprocessed data
 
     :param connection: active openEO connection object
@@ -29,11 +30,15 @@ def ts_datacube_extraction(
             resolution, ts_interval, time_interpolation, SLC_masking_algo, s1_orbitdirection, S2_bands)
     :return: DataCube
     """
+    # Note: for cubes with a time dimension, no S1_NVBT or S2_NVBT band can be attached
+    get_NVBT:bool = processing_options.get("get_NVBT", False)
+    if get_NVBT:
+        processing_options["get_NVBT"] = False
+
     # get the Sentinel-2 datacube as starting point
     bands = extract_S2_datacube(connection, bbox, start, end,
-                                S2_collection=S2_collection,
-                                **processing_options)
-
+                                          S2_collection=S2_collection,
+                                          **processing_options)
     # add the Sentinel-1 data
     if S1_collection is not None:
         bands = bands.merge_cubes(extract_S1_datacube(connection, bbox, start, end,
@@ -49,7 +54,8 @@ def ts_datacube_extraction(
 def extract_S1_datacube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S1_collection: str = 'SENTINEL1_GRD',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]]) \
+        -> Union[DataCube, Tuple[DataCube, Optional[DataCube]]]:
     """ extract the Sentinel-1 data for requested time period and preprocess the data
 
     :param connection: active openEO connection object
@@ -71,7 +77,6 @@ def extract_S1_datacube(
     if processing_options.get('skip_check_S1', False):
         catalogue_check = False
 
-    isCreo = "creo" in processing_options.get("provider", "").lower()
     orbit_direction: Optional[str] = processing_options.get('s1_orbitdirection', None)
     target_crs: Optional[str] = processing_options.get("target_crs", None)
     target_res: float = processing_options.get("resolution", 10.)
@@ -79,7 +84,9 @@ def extract_S1_datacube(
     ts_reducer: str = processing_options.get("S1_temporal_reducer", "mean")
     ts_interpolation: bool = processing_options.get("time_interpolation", False)
     chunk_size: int = processing_options.get("openeo_chunk_size", CHUNK_SIZE)
+    get_NVBT: bool = processing_options.get("get_NVBT", False)
 
+    # set the correct DEM for SAR backscatter correction based on platform
     if ("creo" in processing_options.get("provider", "").lower()) or \
             (processing_options.get("provider", "").lower() == "terrascope") or \
             (processing_options.get("provider", "").lower() == "development") or \
@@ -102,7 +109,7 @@ def extract_S1_datacube(
         properties = {}
 
     # fix no-VH-data issue
-    properties.update({"polarisation": lambda pol: pol == "VV&VH"})
+    properties.update({"sar:polarizations": lambda pol: pol == ["VV", "VH"]})
 
     # Load collection
     bands = connection.load_collection(S1_collection,
@@ -118,10 +125,10 @@ def extract_S1_datacube(
         bands = bands.sar_backscatter(
             coefficient='sigma0-ellipsoid',
             local_incidence_angle=False,
-            # DO NOT USE MAPZEN
+            # DO NOT USE MAPZEN, removed "otb_memory": 1024 from options on advice of JD,
             elevation_model='COPERNICUS_30' if flag_DEM else None,
             options={"implementation_version": "2",
-                     "tile_size": chunk_size, "otb_memory": 1024, "debug": False,
+                     "tile_size": chunk_size, "debug": False,
                      "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"}
         )
         check_flag = True
@@ -138,11 +145,19 @@ def extract_S1_datacube(
     if ts_interval is not None:
         bands = bands.aggregate_temporal_period(period=ts_interval, reducer=ts_reducer)
 
+    # here we have to add the calculation of the NVBT (Number of Valid Binned Timesteps)
+    # Note: we want to create the NVBT here before any possible linear interpolation is done
+    #       therefore, the integration has to be this ugly and not only in the final warper functions
+    if get_NVBT:
+        nvbt_band = bands.filter_bands(bands.metadata.band_names[0]).count_time().rename_labels("bands",
+                                                                                                ["S1-NVBT".lower()])
+        nvbt_band = nvbt_band.apply(lambda x: if_(x.is_nodata(), 0, x))
+
     # Linearly interpolate missing values if wished
     if ts_interpolation:
         bands = bands.apply_dimension(dimension="t", process="array_interpolate_linear")
 
-    # Scale to Uint16 range
+    # Scale to Uint16 range from dB to natural values
     if check_flag:
         # for CREO, rescaling also replaces nodata introduced by orfeo
         # with a low value
@@ -165,12 +180,17 @@ def extract_S1_datacube(
     # Force a linear scale removing values not expected
     bands = bands.linear_scale_range(1, 65534, 1, 65534)
 
-    return bands
+    # the return is tricky since we have to be backwards compatible and still get NVBT calculation working
+    if get_NVBT:
+        return bands, nvbt_band
+    else:
+        return bands
 
 def extract_S2_datacube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S2_collection: str='SENTINEL2_L2A',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> Union[DataCube, Tuple[DataCube, Optional[DataCube]]]:
     """ extract the Sentinel-2 data for requested time period and preprocess the data
 
     :param connection: active openEO connection object
@@ -179,7 +199,7 @@ def extract_S2_datacube(
     :param end: str, End date for requested input data (yyyy-mm-dd)
     :param S2_collection: (str, optional): Collection name for S2 data
     :param processing_options: (dict, optional), processing options for preprocessing routine (provider, target_crs,
-            resolution, ts_interval, time_interpolation, SLC_masking_algo, S2_bands)
+            resolution, ts_interval, time_interpolation, SLC_masking_algo, S2_bands, apply_cloud_mask, getNOBSperc)
     :return: DataCube
     """
     # evaluate additional processing_options
@@ -203,6 +223,7 @@ def extract_S2_datacube(
     max_cloud_max: int = processing_options.get("S2_max_cloud_cover", 95)
     chunk_size: int = processing_options.get("openeo_chunk_size", CHUNK_SIZE)
     s2_tileid_list: Optional[List[str]] = processing_options.get("s2_tileid_list", None)
+    get_NVBT: bool = processing_options.get("get_NVBT", False)
 
     # check if the masking parameter is valid
     if masking not in ['satio', 'mask_scl_dilation', None]:
@@ -271,9 +292,10 @@ def extract_S2_datacube(
         ).rename_labels("bands", ["S2-CLOUD-MASK"])
 
         if apply_mask:
+            # apply the cloud mask to the reference data
             bands = bands.mask(scl_dilated_mask) # here I do trust the automatic resampling of the mask
         else:
-            bands = bands.merge_cubes(scl_dilated_mask)
+            bands = bands.merge_cubes(scl_dilated_mask) #cubes are automatically resampled if needed
     elif masking == 'satio':
         # Apply satio-based mask
         mask = scl_mask_erode_dilate(
@@ -287,20 +309,31 @@ def extract_S2_datacube(
         if apply_mask:
             bands = bands.mask(mask) # masks are automatically resampled/warped
         else:
-            bands = bands.merge_cubes(mask)
+            bands = bands.merge_cubes(mask) #cubes are automatically resampled if needed
 
     # time aggregation if wished
     if ts_interval is not None:
         bands = bands.aggregate_temporal_period(period=ts_interval,  reducer=ts_reducer)
 
+    # here we have to add the calculation of the NVBT (Number of Valid Binned Timesteps)
+    # Note: we want to create the NVBT here before any possible linear interpolation is done
+    #       therefore, the integration has to be this ugly and not only in the final warper functions
+    if get_NVBT:
+        nvbt_band = bands.filter_bands(S2_bands[0]).count_time().rename_labels("bands", ["S2-NVBT".lower()])
+        nvbt_band = nvbt_band.apply(lambda x: if_(x.is_nodata(), 0, x))
+
     # Linearly interpolate missing values if wished
     if ts_interpolation:
         bands = bands.apply_dimension(dimension="t",
                                       process="array_interpolate_linear")
     # forcing 16bit --> UInt16
     bands = bands.linear_scale_range(0, 65534, 0, 65534)
-
-    return bands
+    
+    # the return is tricky since we have to be backwards compatible and still get NVBT calculation working
+    if get_NVBT:
+        return bands, nvbt_band
+    else:
+        return bands
 
 def extract_planet_datacube( 
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
diff --git a/src/eo_processing/openeo/processing.py b/src/eo_processing/openeo/processing.py
index 48da2f6..05a970e 100644
--- a/src/eo_processing/openeo/processing.py
+++ b/src/eo_processing/openeo/processing.py
@@ -1,6 +1,7 @@
 from __future__ import annotations
 import itertools
 import openeo
+import numpy as np
 from openeo.rest.datacube import DataCube
 from openeo.extra.spectral_indices import append_indices, compute_indices
 from openeo.processes import array_create, ProcessBuilder, array_concat, subtract
@@ -11,14 +12,15 @@
 from eo_processing.config.settings import VI_LIST, RADAR_LIST, S2_SCALING, \
     PLANET_VI_LIST, PLANET_SCALING, CHUNK_SIZE
 
-from typing import Optional, Dict, Union, List, Literal, TYPE_CHECKING
+from typing import Optional, Dict, Union, List, TYPE_CHECKING
 if TYPE_CHECKING:
     from eo_processing.config.data_formats import openEO_bbox_format
 
 def optical_indices(
         input_cube: DataCube,
         collection: str ='SENTINEL2_L2A',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """creates vegetation indices times series cube from given datacube of optical EO data.
        Currently Sentinel-2 and PlanetScope are supported
 
@@ -29,12 +31,12 @@ def optical_indices(
     """
     # evaluate additional processing_options
     if collection == 'SENTINEL2_L2A':
-        vi_list = processing_options.get("optical_vi_list", VI_LIST)
+        vi_list: List = processing_options.get("optical_vi_list", VI_LIST)
         input_scaling = processing_options.get("S2_scaling", S2_SCALING)
         append = processing_options.get("append", True)
         platform = 'Sentinel-2A'
     elif collection == 'PlanetScope':
-        vi_list = processing_options.get("optical_vi_list", PLANET_VI_LIST)
+        vi_list: List = processing_options.get("optical_vi_list", PLANET_VI_LIST)
         input_scaling = processing_options.get("planet_scaling", PLANET_SCALING)
         append = processing_options.get("append", True)
         platform = 'PlanetScope'
@@ -52,12 +54,12 @@ def optical_indices(
 
     # TODO: convert the datacube back to int16 - using the output scaling functionality tested in one
     #  of the example notebooks
-
     return vi_cube
 
 def radar_indices(
         input_cube: DataCube,
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """creates radar indices times series cube from given datacube of radar EO data
 
     :param input_cube: openEO DataCube
@@ -65,10 +67,9 @@ def radar_indices(
     :return: VI datacube merged of input_cube and vi results
     """
     # evaluate additional processing_options
-    vi_list = processing_options.get("radar_vi_list", RADAR_LIST)
+    vi_list: List = processing_options.get("radar_vi_list", RADAR_LIST)
     db_rescaling = processing_options.get("S1_db_rescale", True)
     append = processing_options.get("append", True)
-    chunk_size = processing_options.get("openeo_chunk_size", CHUNK_SIZE)
     platform = "sentinel1"
 
     # convert input DataCube into float (db)
@@ -80,20 +81,21 @@ def radar_indices(
                  (20. * x[1].log(base=10)) - 83.])
         )
 
-
     # calculate VI's
     if append:
         vi_cube = append_indices(datacube=input_cube, indices=vi_list, platform=platform)
     else:
         vi_cube = compute_indices(datacube=input_cube, indices=vi_list, platform=platform, append=False)
 
-
+    # TODO: convert the datacube back to int16 - using the output scaling functionality tested in one
+    #  of the example notebooks
     return vi_cube
 
 def generate_S1_indices(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S1_collection: str ='SENTINEL1_GRD',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed data
 
     :param connection: active openEO connection object
@@ -105,6 +107,11 @@ def generate_S1_indices(
             resolution, ts_interval, time_interpolation, s1_orbitdirection, radar_vi_list, S1_db_rescale, append)
     :return: DataCube
     """
+    # Note: for cubes with a time dimension, no s1-nvbt band can be attached
+    get_NVBT: bool = processing_options.get("get_NVBT", False)
+    if get_NVBT:
+        processing_options["get_NVBT"] = False
+
     # get the S1 input data pre-processed
     input_cube = extract_S1_datacube(connection, bbox, start, end, S1_collection=S1_collection, **processing_options)
 
@@ -116,7 +123,8 @@ def generate_S1_indices(
 def generate_S2_indices(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S2_collection: str ='SENTINEL2_L2A',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed data
 
     :param connection: active openEO connection object
@@ -128,9 +136,14 @@ def generate_S2_indices(
             resolution, ts_interval, time_interpolation, SLC_masking_algo, optical_vi_list, S2_scaling, append, S2_bands)
     :return: DataCube
     """
-    # get the S2 input data pre-processed
-    input_cube = extract_S2_datacube(connection, bbox, start, end, S2_collection=S2_collection,
-                                     **processing_options)
+    # Note: for cubes with a time dimension, no s2-nvbt band can be attached
+    get_NVBT: bool = processing_options.get("get_NVBT", False)
+    if get_NVBT:
+        processing_options["get_NVBT"] = False
+
+    # get the Sentinel-2 datacube as starting point
+    input_cube = extract_S2_datacube(connection, bbox, start, end, S2_collection=S2_collection, **processing_options)
+
     # call the VI generator
     result_cube = optical_indices(input_cube, collection=S2_collection, **processing_options)
 
@@ -138,8 +151,9 @@ def generate_S2_indices(
 
 def generate_indices_master_cube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
-        S2_collection: str ='SENTINEL2_L2A', S1_collection: str ='SENTINEL1_GRD',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        S2_collection: str ='SENTINEL2_L2A', S1_collection: Optional[str] ='SENTINEL1_GRD',
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed data
 
     :param connection: active openEO connection object
@@ -153,10 +167,11 @@ def generate_indices_master_cube(
             S2_scaling, append, S2_bands, radar_vi_list, S1_db_rescale)
     :return: DataCube
     """
-    # get the S2 indices
+    # get S2 indices cube - no NVBT band needed
     indices_cube = generate_S2_indices(connection, bbox, start, end, S2_collection=S2_collection,
                                        **processing_options)
-    # merge the S1 indices
+
+    # merge the S1 indices (the called warper makes sure no NVBT band is generated)
     if S1_collection is not None:
         indices_cube = indices_cube.merge_cubes(generate_S1_indices(connection, bbox, start, end,
                                                                     S1_collection=S1_collection,
@@ -166,7 +181,8 @@ def generate_indices_master_cube(
 def generate_indices_planet_cube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         planet_collection: str = 'PlanetScope',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed PlanetScope data
 
     :param connection: active openEO connection object
@@ -225,26 +241,28 @@ def calculate_features_cube(input_data: DataCube, chunk_size: int = CHUNK_SIZE)
     features_cube = input_data.apply_dimension(dimension='t',
                                                process=_compute_features,
                                                target_dimension='bands',
-                                               context={"parallel": True,
-                                                        "TileSize": chunk_size})
+                                               context={"TileSize": chunk_size})
     # adapt the band names
     new_band_names = [
-        band + "_" + stat
+        band.lower() + "_" + stat.lower()
         for band in input_data.metadata.band_names
         for stat in ["p2", "p5", "p25", "median", "p75", "p95", "p98", "mean", "sd", "sum", "iqr", "iqr0595"]
     ]
-    #rename 'S2-CLOUD-MASK_sum'
-    new_band_names = ['valid_obs' if x == 'S2-CLOUD-MASK_sum' else x for x in new_band_names]
 
     features_cube = features_cube.rename_labels('bands', new_band_names)
 
     # remove some bands which make no sense :)
     # mainly from S2REP --> sd, sum, iqr
+    #bands_keep = [band for band in features_cube.metadata.band_names if
+    #              band not in ['S2REP_sd', 'S2REP_sum', 'S2REP_iqr', 'S2REP_iqr0595' , 'VV_sum', 'VH_sum', 'VHVVD_sum',
+    #                           'S2-CLOUD-MASK_p2', 'S2-CLOUD-MASK_p5', 'S2-CLOUD-MASK_p25', 'S2-CLOUD-MASK_median',
+    #                           'S2-CLOUD-MASK_p75','S2-CLOUD-MASK_p95', 'S2-CLOUD-MASK_p98', 'S2-CLOUD-MASK_mean',
+    #                           'S2-CLOUD-MASK_sd','S2-CLOUD-MASK_iqr','S2-CLOUD-MASK_iqr0595', 'S2-CLOUD-MASK_sum']]
     bands_keep = [band for band in features_cube.metadata.band_names if
-                  band not in ['S2REP_sd', 'S2REP_sum', 'S2REP_iqr', 'S2REP_iqr0595' , 'VV_sum', 'VH_sum', 'VHVVD_sum',
-                               'S2-CLOUD-MASK_p2', 'S2-CLOUD-MASK_p5', 'S2-CLOUD-MASK_p25', 'S2-CLOUD-MASK_median',
-                               'S2-CLOUD-MASK_p75','S2-CLOUD-MASK_p95', 'S2-CLOUD-MASK_p98', 'S2-CLOUD-MASK_mean',
-                               'S2-CLOUD-MASK_sd','S2-CLOUD-MASK_iqr','S2-CLOUD-MASK_iqr0595']]
+                  band not in ['s2rep_sd', 's2rep_sum', 's2rep_iqr', 's2rep_iqr0595' , 'vv_sum', 'vh_sum', 'vhvvd_sum',
+                               's2-could-mask_p2', 's2-could-mask_p5', 's2-could-mask_p25', 's2-could-mask_median',
+                               's2-could-mask_p75','s2-could-mask_p95', 's2-could-mask_p98', 's2-could-mask_mean',
+                               's2-could-mask_sd','s2-could-mask_iqr','s2-could-mask_iqr0595', 's2-could-mask_sum']]
 
     features_cube = features_cube.filter_bands(bands=bands_keep)
 
@@ -253,7 +271,8 @@ def calculate_features_cube(input_data: DataCube, chunk_size: int = CHUNK_SIZE)
 def generate_S1_feature_cube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S1_collection: str ='SENTINEL1_GRD',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed data
 
     :param connection: active openEO connection object
@@ -267,18 +286,31 @@ def generate_S1_feature_cube(
     """
     chunk_size: int = processing_options.get("openeo_chunk_size", CHUNK_SIZE)
 
-    # get the reflectance and VI time series cube
-    input_data = generate_S1_indices(connection, bbox, start, end, S1_collection=S1_collection,
-                                     **processing_options)
+    get_NVBT: bool = processing_options.get("get_NVBT", False)
+    # feature cubes have no time dimension, so we can add the s1-nvbt band to the cube
+    if get_NVBT:
+        # get the sigma-naught and VI time series cube PLUS the S1-NVBT band
+        input_cube, nvbt_band = extract_S1_datacube(connection, bbox, start, end, S1_collection=S1_collection,
+                                                    **processing_options)
+        # call the VI generator
+        indices_cube = radar_indices(input_cube, **processing_options)
+    else:
+        indices_cube = generate_S1_indices(connection, bbox, start, end, S1_collection=S1_collection,
+                                           **processing_options)
     # get features
-    features_cube = calculate_features_cube(input_data, chunk_size=chunk_size)
+    features_cube = calculate_features_cube(indices_cube, chunk_size=chunk_size)
+
+    # add the S1-NVBT band to cube if needed
+    if get_NVBT:
+        features_cube = features_cube.merge_cubes(nvbt_band)
 
     return features_cube
 
 def generate_S2_feature_cube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S2_collection: str ='SENTINEL2_L2A',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed data
 
     :param connection: active openEO connection object
@@ -291,19 +323,34 @@ def generate_S2_feature_cube(
     :return: DataCube with only features
     """
     chunk_size: int = processing_options.get("openeo_chunk_size", CHUNK_SIZE)
-    # get the reflectance and VI time series cube
-    input_data = generate_S2_indices(connection, bbox, start, end, S2_collection=S2_collection,
-                                     **processing_options)
+
+    get_NVBT: bool = processing_options.get("get_NVBT", False)
+    # feature cubes have no time dimension, so we can add the s2-nvbt band to the cube
+    if get_NVBT:
+        # get the reflectance and VI time series cube PLUS S2-NVBT band
+        input_cube, nvbt_band = extract_S2_datacube(connection, bbox, start, end, S2_collection=S2_collection,
+                                                    **processing_options)
+        # call the VI generator
+        indices_cube = optical_indices(input_cube, collection=S2_collection, **processing_options)
+    else:
+        # get the reflectance and VI time series cube
+        indices_cube = generate_S2_indices(connection, bbox, start, end, S2_collection=S2_collection,
+                                           **processing_options)
+
     # get features
-    features_cube = calculate_features_cube(input_data, chunk_size=chunk_size)
+    features_cube = calculate_features_cube(indices_cube, chunk_size=chunk_size)
 
-    return features_cube
+    # add the S2-NVBT band to the cube if needed
+    if get_NVBT:
+        features_cube = features_cube.merge_cubes(nvbt_band)
 
+    return features_cube
 
 def generate_planet_feature_cube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         planet_collection: str ='PlanetScope',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed Planet data
 
     :param connection: active openEO connection object
@@ -329,7 +376,8 @@ def generate_planet_feature_cube(
 def generate_master_feature_cube(
         connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
         S2_collection: str ='SENTINEL2_L2A', S1_collection: str ='SENTINEL1_GRD',
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: Dict[str, Union[str, int, float, bool, List[str], List[Union[int, float]], None]])\
+        -> DataCube:
     """ Warper to extract a full data cube of preprocessed data
 
     :param connection: active openEO connection object
@@ -343,14 +391,14 @@ def generate_master_feature_cube(
             S2_scaling, append, S2_bands, radar_vi_list, S1_db_rescale)
     :return: DataCube with only features
     """
-    chunk_size: int = processing_options.get("openeo_chunk_size", CHUNK_SIZE)
-    # get the reflectance and VI time series cube
-    input_data = generate_indices_master_cube(connection, bbox, start, end, S2_collection=S2_collection,
-                                              S1_collection=S1_collection, **processing_options)
-    # get features
-    features_cube = calculate_features_cube(input_data, chunk_size=chunk_size)
-
-    return features_cube
+    # optimized pipeline were we run the feature generation per sensor and only merge in the end
+    feature_cube = generate_S2_feature_cube(connection, bbox, start, end, S2_collection=S2_collection,
+                                            **processing_options)
+    if S1_collection is not None:
+        feature_cube = feature_cube.merge_cubes(generate_S1_feature_cube(connection, bbox, start, end,
+                                                                          S1_collection=S1_collection,
+                                                                          **processing_options))
+    return feature_cube
 
 def create_collections_list_from_bands(input_bands : List[str]):
     """
@@ -394,23 +442,23 @@ def create_collections_list_from_bands(input_bands : List[str]):
     return collections_list
 
 def generate_nonEO_feature_cube(
-        connection: openeo.Connection, bbox: Optional[openEO_bbox_format], start: str, end: str,
-        collections_list: List[str],
+        connection: openeo.Connection, bbox: openEO_bbox_format | None, start: str, end: str,
+        collections_list: list[str],
         base_cube : DataCube,
-        **processing_options: Dict[str, Union[str, bool, int | float, List[str], List[int | float]]]) -> DataCube:
+        **processing_options: dict[str, str | bool | (int | float) | list[str] | list[int | float]]) -> DataCube:
 
     """ Warper to generate the data cube of all nonEO data based on a collections  list of the form [(collection, [band1, band2, ...])]"""
-    temporal_extent = [start, end]
-    temporal_extent = None
 
     chunk_size: int = processing_options.get("openeo_chunk_size", CHUNK_SIZE)
 
-    for collection, bands, reproj, year in collections_list:
+    for collection, bands, reproj, year, stac_url in collections_list:
         #first need to distinguish between STAC and collection
         #we assume that they will allways be an url type of link in contrary with a collections which should just be a name
-        if temporal_extent:
-            temporal_extent = [f"{year}-01-01T00:00:00Z", f"{year}-12-31T23:59:59Z"]
-        STAC_url = get_stac_collection_url(collection)
+        if not np.isnan(year):
+            temporal_extent = [f"{int(year)}-01-01T00:00:00Z", f"{int(year)}-12-31T23:59:59Z"]
+        else:
+            temporal_extent = None
+        STAC_url = get_stac_collection_url(collection, stac_url)
         isSTAC = STAC_url is not None
 
         #secondly we know there are some specific case of reprojection EG DEM should be bilinear iso near
@@ -431,6 +479,9 @@ def generate_nonEO_feature_cube(
                                                       temporal_extent=temporal_extent
                                                       )
             nonEO_feature_cube.result_node().update_arguments(featureflags={'tilesize': chunk_size})
+            # TODO add all the collections that are allowed to be empty
+            if collection in ["DEM_aspec_30m"]:
+                nonEO_feature_cube.result_node().update_arguments(featureflags={'allow_empty_cube': True})
 
         else:
             #if openeo the -v1 should be split off of the collection
@@ -448,7 +499,7 @@ def generate_nonEO_feature_cube(
                 # reduce the temporal domain since copernicus_30 collection is "special" and feature only are one time stamp
                 nonEO_feature_cube = nonEO_feature_cube.reduce_dimension(dimension='t', reducer=lambda x: x.last(ignore_nodata=True))
 
-        new_bands = [f"{collection}-{band}" for band in bands]
+        new_bands = [f"{collection.lower()}-{band.lower()}" for band in bands]
 
 
         # resample the cube to 10m and EPSG of corresponding 20x20km grid tile
@@ -471,4 +522,3 @@ def generate_nonEO_feature_cube(
         base_cube = base_cube.merge_cubes(nonEO_feature_cube)
 
     return base_cube
-
diff --git a/src/eo_processing/openeo/udf_capture.py b/src/eo_processing/openeo/udf_capture.py
new file mode 100644
index 0000000..b61cb1b
--- /dev/null
+++ b/src/eo_processing/openeo/udf_capture.py
@@ -0,0 +1,134 @@
+"""Build context for UDF input captures stored in CDSE object storage."""
+
+import hashlib
+import re
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+from urllib.parse import unquote, urlparse
+
+import boto3
+import openeo
+import requests
+
+from eo_processing.utils.helper import getUDFpath
+
+_CAPTURE_URL_PATTERN = re.compile(r"presigned download:\s*(https?://\S+)")
+
+
+def _build_s3_context(
+    connection: openeo.Connection,
+    region: str = "waw3-1",
+    role_session_name: str = "openeo-udf",
+    duration_hours: int = 12,
+) -> dict[str, str]:
+    """Build temporary object-storage credentials from an openEO OIDC token."""
+    if duration_hours <= 0:
+        raise ValueError("duration_hours must be positive")
+
+    auth = connection.auth
+    try:
+        web_identity_token = auth.bearer.split("/", maxsplit=2)[2] if auth else None
+    except (AttributeError, IndexError) as error:
+        raise ValueError("Connection must use an OIDC bearer token") from error
+    if not web_identity_token:
+        raise ValueError("Connection must use an OIDC bearer token")
+
+    sts_url = f"https://sts.{region}.openeo.v1.dataspace.copernicus.eu"
+    s3_url = sts_url.replace("sts", "s3", 1)
+    role_arn = f"arn:openeo:iam:::role/openeo-artifacts-{region}"
+
+    response: dict[str, Any] = boto3.Session().client(
+        "sts", endpoint_url=sts_url
+    ).assume_role_with_web_identity(
+        RoleArn=role_arn,
+        RoleSessionName=role_session_name,
+        WebIdentityToken=web_identity_token,
+        DurationSeconds=duration_hours * 3600,
+    )
+    credentials = response["Credentials"]
+    subject = response["SubjectFromWebIdentityToken"]
+    subject_hash = hashlib.sha1(subject.encode()).hexdigest()
+    prefix = f"{subject_hash}/{datetime.now(timezone.utc):%Y/%m/%d}/"
+
+    return {
+        "bucket": f"openeo-artifacts-{region}",
+        "prefix": prefix,
+        "endpoint": s3_url,
+        "token": credentials["SessionToken"],
+        "access_key_id": credentials["AccessKeyId"],
+        "secret_access_key": credentials["SecretAccessKey"],
+    }
+
+
+def get_capture_udf(
+    connection: openeo.Connection,
+    *,
+    output_format: str = "netcdf",
+    region: str = "waw3-1",
+    role_session_name: str = "openeo-udf",
+    duration_hours: int = 12,
+) -> openeo.UDF:
+    """Create an input-capture UDF with temporary object-storage credentials as context."""
+    output_format = output_format.lower()
+    if output_format not in {"netcdf", "gtiff"}:
+        raise ValueError("output_format must be 'netcdf' or 'gtiff'")
+
+    return openeo.UDF.from_file(
+        getUDFpath("udf_save_input.py"),
+        context={
+            **_build_s3_context(
+            connection,
+            region=region,
+            role_session_name=role_session_name,
+            duration_hours=duration_hours,
+            ),
+            "output_format": output_format,
+        },
+        runtime="Python",
+        version="3.11",
+    )
+
+
+def download_captured_udf_inputs(
+    connection: openeo.Connection,
+    job: openeo.BatchJob | str,
+    folder: str | Path,
+    *,
+    limit: int | None = None,
+) -> list[Path]:
+    """Download UDF inputs whose presigned URLs were emitted in batch-job logs.
+
+    ``job`` can be an openEO batch job or its ID. URLs are read from the
+    ``presigned download:`` messages emitted by ``udf_save_input.py``.
+    """
+    if limit is not None and limit < 0:
+        raise ValueError("limit must be non-negative")
+
+    job = connection.job(job) if isinstance(job, str) else job
+    urls: list[str] = []
+    for entry in job.logs(level="INFO"):
+        message = entry.get("message", "")
+        match = _CAPTURE_URL_PATTERN.search(message)
+        if match and match.group(1) not in urls:
+            urls.append(match.group(1))
+
+    if limit is not None:
+        urls = urls[:limit]
+
+    output_folder = Path(folder)
+    output_folder.mkdir(parents=True, exist_ok=True)
+    downloads: list[Path] = []
+    for url in urls:
+        filename = Path(unquote(urlparse(url).path)).name
+        if not filename:
+            raise ValueError(f"Capture URL has no filename: {url}")
+        destination = output_folder / filename
+        response = requests.get(url, stream=True, timeout=60)
+        response.raise_for_status()
+        with destination.open("wb") as file:
+            for chunk in response.iter_content(chunk_size=1024 * 1024):
+                file.write(chunk)
+        downloads.append(destination)
+
+    return downloads
\ No newline at end of file
diff --git a/src/eo_processing/resources/ECDC_global_120x120km_grid_v1.gpkg b/src/eo_processing/resources/ECDC_global_120x120km_grid_v1.gpkg
new file mode 100644
index 0000000..45f7762
Binary files /dev/null and b/src/eo_processing/resources/ECDC_global_120x120km_grid_v1.gpkg differ
diff --git a/src/eo_processing/resources/udf_save_input.py b/src/eo_processing/resources/udf_save_input.py
new file mode 100644
index 0000000..f6952ac
--- /dev/null
+++ b/src/eo_processing/resources/udf_save_input.py
@@ -0,0 +1,109 @@
+"""Save an openEO UDF input chunk to temporary object storage."""
+
+import logging
+from datetime import datetime
+from uuid import uuid4
+
+import boto3
+import numpy as np
+import xarray as xr
+from openeo.udf import inspect
+from rasterio.io import MemoryFile
+
+logger = logging.getLogger(__name__)
+
+
+def _s3_client(context: dict):
+    return boto3.client(
+        "s3",
+        aws_access_key_id=context.get("access_key_id"),
+        aws_secret_access_key=context.get("secret_access_key"),
+        aws_session_token=context.get("token"),
+        endpoint_url=context.get("endpoint"),
+    )
+
+
+def _build_object_key(cube: xr.DataArray, context: dict, extension: str) -> str:
+    title = context.get("title") or context.get("name") or "input"
+    stamp = datetime.now().strftime("%Y%m%dT%H%M%S")
+    short_id = uuid4().hex[:6]
+
+    coord_tag: str | None = None
+    if "x" in cube.coords and "y" in cube.coords:
+        try:
+            coord_tag = f"x{int(cube.x.values[0])}_y{int(cube.y.values[0])}"
+        except (TypeError, ValueError, IndexError):
+            pass
+
+    parts = [title]
+    if coord_tag:
+        parts.append(coord_tag)
+    parts.extend([stamp, short_id])
+
+    prefix = context.get("prefix", "").strip("/")
+    filename = "_".join(parts) + extension
+    return f"{prefix}/{filename}" if prefix else filename
+
+
+def _serialize_capture(cube: xr.DataArray, output_format: str) -> tuple[bytes, str, str]:
+    if output_format == "netcdf":
+        dataset = (
+            cube.to_dataset(dim="bands")
+            if "bands" in cube.dims
+            else cube.to_dataset(name=cube.name or "data")
+        )
+        return bytes(dataset.to_netcdf()), ".nc", "application/netcdf"
+
+    if output_format == "gtiff":
+        if "t" in cube.dims:
+            return _serialize_capture(cube, "netcdf")
+        if "y" not in cube.dims or "x" not in cube.dims:
+            raise ValueError("GeoTIFF capture requires y and x dimensions")
+
+        data = np.asarray(cube.values)
+        if data.ndim == 2:
+            data = data[np.newaxis, :, :]
+        elif data.ndim != 3:
+            raise ValueError("GeoTIFF capture requires a 2D or 3D spatial input cube")
+
+        with MemoryFile() as memory_file:
+            with memory_file.open(
+                driver="GTiff",
+                height=data.shape[-2],
+                width=data.shape[-1],
+                count=data.shape[0],
+                dtype=data.dtype,
+            ) as dataset:
+                dataset.write(data)
+            return memory_file.read(), ".tif", "image/tiff"
+
+    raise ValueError("output_format must be 'netcdf' or 'gtiff'")
+
+
+def apply_datacube(cube: xr.DataArray, context: dict) -> xr.DataArray:
+    """Upload UDF input, then return it unchanged."""
+    bucket = context.get("bucket")
+    if not bucket:
+        raise ValueError("Context must contain bucket")
+
+    desired_dims = [dimension for dimension in ["t", "bands", "y", "x"] if dimension in cube.dims]
+    capture_cube = cube.transpose(*desired_dims).load()
+    output_format = context.get("output_format", "netcdf").lower()
+    payload, extension, content_type = _serialize_capture(capture_cube, output_format)
+    key = _build_object_key(capture_cube, context, extension)
+    client = _s3_client(context)
+    client.put_object(
+        Bucket=bucket,
+        Key=key,
+        Body=payload,
+        ContentType=content_type,
+    )
+
+    presigned_url = client.generate_presigned_url(
+        "get_object",
+        Params={"Bucket": bucket, "Key": key},
+        ExpiresIn=int(context.get("presign_expires", 12 * 3600)),
+    )
+    inspect(message=f"uploaded to s3://{bucket}/{key}; presigned download: {presigned_url}")
+    logger.info("uploaded to s3://%s/%s; presigned download: %s", bucket, key, presigned_url)
+    return cube
\ No newline at end of file
diff --git a/src/eo_processing/utils/alphaearth_utils.py b/src/eo_processing/utils/alphaearth_utils.py
new file mode 100644
index 0000000..cb10ca8
--- /dev/null
+++ b/src/eo_processing/utils/alphaearth_utils.py
@@ -0,0 +1,490 @@
+"""Module to download alphaEarth embeddings for a given AOI and upload them to S3.
+
+Some snippets extracted from Marcel's code.
+
+This module provides functions to:
+1. Identify intersecting grids from an AOI and a global grid.
+2. Download the corresponding alphaEarth embeddings from S3 or HTTP.
+3. Convert the downloaded VRT files to Cloud Optimized GeoTIFF (COG)
+4. Upload the processed files to S3 using a specified storage utility.
+
+Example usage:
+
+    # get the intersecting grids and filenames
+    df = get_embedding_filenames(
+        "/vitodata/nca/weed/change/AOI/AOI_cze-change_UTM20k_grid.shp",
+        "/data/mepvm/alphaearth/aef_source-coop_2017-2025_index.gpkg",
+        '/vitodata/nca/weed/grid/global_terrestrial_UTM20k_grid_v2.gpkg',  # not needed if input is already in this grid
+        years=[2022, 2023],
+    )
+    # download files to local directory
+    downloaded_files = download_embeddings(
+        df["path"].tolist(), "/vitodata/nca/test/Manu/alphaearth_embeddings/"
+    )
+    # edit the vrt and then convert to cog
+    vrt_paths = [Path(f).with_suffix(".vrt") for f in downloaded_files]
+    cog_paths = []
+    for path_vrt in vrt_paths:
+        path_vrt: Path = Path(path_vrt)
+        patch_vrt_relative_path(path_vrt)
+        path_tif = translate_to_cog(path_vrt)
+        cog_paths.append(path_tif)
+
+    # Upload to S3
+    files_df = build_files_dataframe(cog_paths)
+    storage = WEED_storage(...)   # Initialize with appropriate parameters)
+    upload_files(files_df, storage, S3_ROOT)
+    print('All done.')
+
+"""
+
+import logging
+import re
+import subprocess
+from pathlib import Path
+from typing import List, Optional, Tuple
+
+import geopandas as gpd
+import pandas as pd
+from eo_processing.utils.storage import WEED_storage
+
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s"
+)
+logger = logging.getLogger(__name__)
+
+try:
+    import boto3
+    from botocore import UNSIGNED
+    from botocore.client import Config
+    from botocore.exceptions import ClientError
+
+    boto3_available = True
+except ImportError:
+    logger.warning(
+        "boto3 not available, falling back to HTTP protocol for downloading."
+    )
+    boto3_available = False
+
+
+# download settings
+S3_BASE_URL = "s3://us-west-2.opendata.source.coop/"
+ENDPOINT_URL = "https://data.source.coop"
+# COG settings
+GDAL_COG_OPTIONS = [
+    "-of COG",
+    "-co INTERLEAVE=BAND",
+    "-co COMPRESS=ZSTD",
+    "-co LEVEL=15",
+    "-co NUM_THREADS=ALL_CPUS",
+    "-co PREDICTOR=YES",
+    "-co OVERVIEW_RESAMPLING=NEAREST",
+    "-co BIGTIFF=YES",
+    "-co OVERVIEW_COUNT=6",
+]
+
+
+class S3Downloader:
+    def __init__(self):
+        self.s3_client = boto3.client(
+            "s3",
+            endpoint_url=ENDPOINT_URL,
+            config=Config(signature_version=UNSIGNED),
+        )
+
+    def s3_object_exists(self, bucket, key):
+        """
+        Check if an S3 object exists using unsigned requests.
+
+        Args:
+            bucket (str): S3 bucket name.
+            key (str): S3 object key.
+            endpoint_url (str): Custom S3 endpoint URL.
+
+        Returns:
+            bool: True if object exists, False otherwise.
+        """
+        try:
+            logger.debug(f"Checking existence of s3://{bucket}/{key}")
+            self.s3_client.head_object(Bucket=bucket, Key=key)
+            logger.info(f"Object exists: s3://{bucket}/{key}")
+            return True
+        except ClientError as e:
+            if e.response["Error"]["Code"] == "404":
+                logger.warning(f"Object does not exist: s3://{bucket}/{key}")
+                return False
+            else:
+                logger.error(f"Error checking object existence: {e}")
+                raise
+
+    def get_bucket_and_key(self, s3_url: str) -> Tuple[str, str]:
+        """
+        Parse an S3 URL into its bucket name and object key.
+
+        Args:
+            s3_url (str): The full S3 URL to parse.
+        """
+        split_str = s3_url.replace(S3_BASE_URL, "").split("/", 1)
+        return split_str[0], split_str[1]
+
+    def download_s3_file(self, s3_url, output_dir):
+        """
+        Download a single file from S3 using unsigned requests.
+
+        Args:
+            bucket (str): S3 bucket name.
+            key (str): S3 object key.
+            endpoint_url (str): Custom S3 endpoint URL.
+            output_dir (str or Path): Local directory to save the object.
+        """
+        bucket, key = self.get_bucket_and_key(s3_url)
+        key1 = key.replace(".tiff", ".vrt")
+        if not self.s3_object_exists(bucket, key):
+            logger.error(f"Object does not exist: s3://{bucket}/{key}")
+            return False, None
+        if not self.s3_object_exists(bucket, key1):
+            logger.warning(f"Object does not exist: s3://{bucket}/{key1}")
+
+        try:
+            output_path = Path(output_dir) / Path(key)
+            output_path.parent.mkdir(parents=True, exist_ok=True)
+            self.s3_client.download_file(bucket, key, str(output_path))
+            logger.info(f"Download complete: {output_path}")
+            output_path1 = Path(output_dir) / Path(key1)
+            self.s3_client.download_file(bucket, key1, str(output_path1))
+            logger.info(f"Download complete: {output_path1}")
+            return True, str(output_path)
+        except Exception as e:
+            logger.error(f"Failed to download s3://{bucket}/{key}: {e}")
+            return False, None
+
+
+def http_download(
+    filenames: List[str], output_dir: Path, overwrite: bool = False
+) -> List[str]:
+    """
+    Download files using HTTP protocol.
+
+    Args:
+        filenames (List[str]): List of file URLs to download.
+        output_dir (Path): Directory to save downloaded files.
+        overwrite (bool): If True, overwrite existing files.
+
+    Returns:
+        List[str]: List of paths to downloaded files.
+    """
+    import requests
+
+    new_paths = []
+    for fl in filenames:
+        fl_path = Path(fl.replace(S3_BASE_URL, ""))
+        final_dir = output_dir / fl_path.parent
+        final_dir.mkdir(parents=True, exist_ok=True)
+        url = fl.replace(S3_BASE_URL, "https://data.source.coop/")
+        out_path = final_dir / fl_path.name
+        if out_path.exists() and not overwrite:
+            logger.info(f"File {out_path} exists, skipping download.")
+            new_paths.append(str(out_path))
+            continue
+        logger.info(f"Downloading {url} to {final_dir}")
+        with requests.get(url, stream=True) as r:
+            r.raise_for_status()
+            with open(out_path, "wb") as f:
+                for chunk in r.iter_content(chunk_size=1024 * 1024):
+                    if chunk:
+                        f.write(chunk)
+        new_paths.append(str(out_path))
+    return new_paths
+
+
+def _ensure_crs(df: gpd.GeoDataFrame, crs: str = "EPSG:4326") -> gpd.GeoDataFrame:
+    """
+    Ensure the GeoDataFrame has the specified CRS.
+
+    Args:
+        df (gpd.GeoDataFrame): Input GeoDataFrame.
+        crs (str): Target CRS.
+
+    Returns:
+        gpd.GeoDataFrame: GeoDataFrame in the target CRS.
+    """
+    if df.crs is None or df.crs != crs:
+        return df.to_crs(crs)
+    return df
+
+
+def get_intersecting_grids(
+    input_gdf: gpd.GeoDataFrame, grid_file: str
+) -> gpd.GeoDataFrame:
+    """
+    Intersect the input_gdf with the grid_file and return the intersecting grids.
+
+    Args:
+        input_gdf (gpd.GeoDataFrame): Input geometries.
+        grid_file (str): Path to grid file.
+
+    Returns:
+        gpd.GeoDataFrame: Intersecting grid geometries.
+    """
+    grid_gdf = gpd.read_file(grid_file)
+    input_union = input_gdf.union_all()
+    possible_matches_index = list(grid_gdf.sindex.intersection(input_union.bounds))
+    possible_matches = grid_gdf.iloc[possible_matches_index]
+    intersecting = possible_matches[possible_matches.intersects(input_union)]
+    return intersecting
+
+
+def get_embedding_filenames(
+    input_shape_filename: str,
+    alphaearth_metadata_file: str,
+    format_grid_file: Optional[str] = None,
+    years: Optional[List[int]] = None,
+) -> gpd.GeoDataFrame:
+    """
+    Get the intersecting grids from the input shape file and return the corresponding alphaearth embeddings.
+
+    Args:
+        input_shape_filename (str): Path to the input shape file. Can be .shp, .gpkg, .geojson, or .parquet.
+        alphaearth_metadata_file (str): Path to the alphaearth metadata file.
+        format_grid_file (Optional[str]): Path to the global grid file. If provided, filter grids.
+        years (Optional[List[int]]): List of years to filter the embeddings.
+
+    Returns:
+        gpd.GeoDataFrame: Intersecting grids and their corresponding alphaearth embeddings paths.
+    """
+    input_file = Path(input_shape_filename)
+    if not input_file.exists():
+        logger.error(f"Input shape file {input_shape_filename} does not exist.")
+        raise FileNotFoundError(
+            f"Input shape file {input_shape_filename} does not exist."
+        )
+
+    if input_file.suffix in [".shp", ".gpkg", ".geojson"]:
+        input_gdf = gpd.read_file(input_file)
+    elif input_file.suffix == ".parquet":
+        input_gdf = gpd.read_parquet(input_file)
+    else:
+        logger.error(
+            f"Input shape file {input_shape_filename} has unsupported file type {input_file.suffix}. "
+            "Supported types are .shp, .gpkg, .geojson, .parquet"
+        )
+        raise ValueError(
+            f"Input shape file {input_shape_filename} has unsupported file type {input_file.suffix}. "
+            "Supported types are .shp, .gpkg, .geojson, .parquet"
+        )
+    input_gdf = _ensure_crs(input_gdf)
+
+    if format_grid_file is not None:
+        if not Path(format_grid_file).exists():
+            logger.error(f"Global grid file {format_grid_file} does not exist.")
+            raise FileNotFoundError(
+                f"Global grid file {format_grid_file} does not exist."
+            )
+        grids_20km = get_intersecting_grids(input_gdf, format_grid_file)
+    else:
+        grids_20km = input_gdf
+
+    if not Path(alphaearth_metadata_file).exists():
+        logger.error(
+            f"AlphaEarth metadata file {alphaearth_metadata_file} does not exist."
+        )
+        raise FileNotFoundError(
+            f"AlphaEarth metadata file {alphaearth_metadata_file} does not exist."
+        )
+    alphaearth_grids = get_intersecting_grids(grids_20km, alphaearth_metadata_file)
+    if years:
+        alphaearth_grids = alphaearth_grids[alphaearth_grids["year"].isin(years)]
+    else:
+        logger.info("No years specified, returning all intersecting grids.")
+    return alphaearth_grids
+
+
+def download_embeddings(
+    filenames: List[str], output_path: str, overwrite: bool = False
+) -> List[str]:
+    """
+    Download the embeddings for the intersecting grids from sourcecoop or HTTP and save them to the output directory.
+
+    Args:
+        filenames (List[str]): List of S3 paths to the embeddings.
+        output_path (str): Path to the output directory where the embeddings will be downloaded.
+        overwrite (bool): If True, download and overwrite files even if they exist.
+
+    Returns:
+        List[str]: List of paths to downloaded files.
+    """
+    output_dir = Path(output_path)
+    output_dir.mkdir(parents=True, exist_ok=True)
+    logger.info(f"Downloading {len(filenames)} files to {output_dir}")
+    new_paths = []
+    successful_downloads = 0
+    if boto3_available:
+        logger.info("Using S3 for downloading files.")
+        client = S3Downloader()
+        for fl in filenames:
+            success, new_path = client.download_s3_file(fl, output_dir)
+            if success:
+                new_paths.append(new_path)
+                successful_downloads += 1
+        logger.info(
+            f"Downloaded {len(new_paths)} files to {output_dir} out of {len(filenames)}"
+        )
+    else:
+        logger.info("Using HTTP protocol for downloading files.")
+        new_paths = http_download(filenames, output_dir, overwrite=overwrite)
+        logger.info(f"Downloaded {len(new_paths)} files to {output_dir}")
+    return new_paths
+
+
+def patch_vrt_relative_path(path_vrt: Path) -> None:
+    """
+    Modifies the VRT file to set the 'relativeToVRT' attribute for the source dataset to 1.
+
+    This function reads the content of the specified VRT file, locates the SourceDataset
+    element whose 'relativeToVRT' attribute is set to 0 and whose filename matches the
+    generated filename, updates its 'relativeToVRT' attribute to 1, and writes the modified
+    content back to the same file.
+
+    :param path_vrt: A Path object representing the path to the VRT file to be modified.
+    """
+    filename = path_vrt.stem + ".tiff"
+    vrt_content = path_vrt.read_text(encoding="utf-8")
+    vrt_content = re.sub(
+        r'<SourceDataset relativeToVRT="0">[^<]*'
+        + re.escape(filename)
+        + r"</SourceDataset>",
+        f'<SourceDataset relativeToVRT="1">{filename}</SourceDataset>',
+        vrt_content,
+    )
+    path_vrt.write_text(vrt_content, encoding="utf-8")
+
+
+def translate_to_cog(path_vrt: Path, version):
+    """Translates a VRT (Virtual Dataset) file to a Cloud Optimized GeoTIFF (COG) format using GDAL.
+
+        This function converts a given VRT file into a COG-compatible GeoTIFF file. If the output
+        file already exists, the function will skip the translation process and return the existing
+        file path.
+
+        Args:
+            path_vrt (Path): The path to the input VRT file.
+            version (str): Version string to append to the output filename.
+
+
+    urn:    The path to the generated Cloud Optimized GeoTIFF file.    :return: The path to the generated Cloud Optimized GeoTIFF file.
+    """
+    path_out = path_vrt.parent / f"{path_vrt.stem}_{version}.tif"
+
+    if path_out.exists():
+        print(f"File {path_out} already exists, skipping.")
+        return path_out
+
+    gdal_cmd = " ".join(
+        ["gdal_translate"] + GDAL_COG_OPTIONS + [str(path_vrt), str(path_out)]
+    )
+    try:
+        subprocess.check_call(gdal_cmd, shell=True)
+    except subprocess.CalledProcessError as e:
+        raise OSError(f"Could not translate file: {e}") from e
+    return path_out
+
+
+def build_files_dataframe(files: list[Path]) -> pd.DataFrame:
+    """
+    Builds a DataFrame from a list of file paths, extracting relevant metadata from their parent directories.
+
+    Args:
+        files (list[Path]): List of file paths to include in the DataFrame.
+
+    Returns:
+        pd.DataFrame: A DataFrame containing file paths and extracted metadata, including 'version', 'year', 'zone', and 's3_prefix'.
+    """
+    files_df = pd.DataFrame({"file_path": files})
+    # Extract parent parts
+    parent_parts = (
+        files_df["file_path"]
+        .apply(lambda x: Path(x).parent.parts[-5:])
+        .apply(pd.Series)
+    )
+    # Join extracted parts as new columns
+    files_df = files_df.join(
+        parent_parts.rename(
+            columns={0: "rest", 1: "version", 2: "_unused", 3: "year", 4: "zone"}
+        )
+    )
+    files_df = files_df.drop(columns=["rest", "_unused"])
+    files_df["s3_prefix"] = files_df[["version", "year", "zone"]].apply(
+        lambda x: "/".join(x), axis=1
+    )
+    return files_df
+
+
+def upload_files(files_df: pd.DataFrame, storage: WEED_storage, s3_root: str) -> None:
+    """
+    Uploads files to an S3-compatible storage using the specified storage utility. Each file's destination
+    is determined from a DataFrame containing file paths and their respective S3 prefixes. This function
+    also supports options such as progress tracking, ETag validation, and existence checks for each upload.
+
+    :param files_df: A DataFrame where each row contains details of a file to upload. Must include columns
+        for 'file_path' specifying the local path of the file and 's3_prefix' defining the relative destination
+        path in the S3-compatible storage.
+    :param storage: An instance of WEED_storage, which provides methods for uploading files to
+        S3-compatible storage backends.
+    :param s3_root: The root directory in the target S3 storage where files will be uploaded. The
+        final S3 destination of each file is formed by concatenating this root with the 's3_prefix'.
+    """
+    for file_row in files_df.itertuples():
+        s3_destination = f"{s3_root}/{file_row.s3_prefix}"
+        logger.info(f"Uploading {file_row.file_path} to {s3_destination}")
+        storage.upload_file_to_s3(
+            file_row.file_path,
+            s3_destination,
+            progress_bar=True,
+            etag_check=True,
+            exist_check=True,
+        )
+
+
+# def filter_files_on_s3(storage: WEED_storage, s3_root: str, df: pd.DataFrame) -> pd.DataFrame:
+#     """Get all files in the S3 bucket in a directory."""
+#     list_all = storage.get_s3_content(s3_root)
+#     all_files = [f["Key"] for f in list_all if f["Key"].endswith(".tif")]
+#     result = [
+#         {"year": f.split("/")[1], "zone": f.split("/")[2], "filename": f.split("/")[3].split("_")[0]}
+#         for f in all_files
+#     ]
+#     df_exist= pd.DataFrame(result)
+    
+#     # drop existing files on S3
+#     # Create a boolean mask for rows to drop
+#     def should_drop(row):
+#         for rw in df_exist.itertuples(index=False):
+#             if int(row['year']) == int(rw.year) and rw.filename in row['path']:
+#                 return True
+#         return False
+#     mask = df.apply(should_drop, axis=1)
+#     df_filtered = df[~mask].reset_index(drop=True)
+#     return df_filtered
+
+
+def filter_files_on_s3(storage: WEED_storage, s3_root: str, df: pd.DataFrame) -> pd.DataFrame:
+    """Get all files in the S3 bucket in a directory and filter out existing ones."""
+    list_all = storage.get_s3_content(s3_root)
+    all_files = [f["Key"] for f in list_all if f["Key"].endswith(".tif")]
+    # Build a list of dicts as before
+    result = [
+        {"year": f.split("/")[-3], "zone": f.split("/")[-2], "filename": f.split("/")[-1].split("_")[0]}
+        for f in all_files
+    ]
+
+    def should_drop(row):
+        for rw in result:
+            if int(row['year']) == int(rw['year']) and rw['filename'] in row['path']:
+                return True
+        return False
+
+    mask = df.apply(should_drop, axis=1)
+    df_filtered = df[~mask].reset_index(drop=True)
+    return df_filtered
diff --git a/src/eo_processing/utils/catalogue_check.py b/src/eo_processing/utils/catalogue_check.py
index 0f0962e..2561fd9 100644
--- a/src/eo_processing/utils/catalogue_check.py
+++ b/src/eo_processing/utils/catalogue_check.py
@@ -2,30 +2,39 @@
 import requests
 import json
 import pandas as pd
-from eo_processing.utils.geoprocessing import reproj_bbox_to_ll
+from eo_processing.utils.geoprocessing import reproj_bbox_to_ll, bbox_of_PointsFeatureCollection
 import geojson
 from typing import TYPE_CHECKING
 import pystac_client
+import time
 
 if TYPE_CHECKING:
     from eo_processing.config.data_formats import openEO_bbox_format
 
-def catalogue_check_S1(orbit_direction: str, start: str, end: str, bbox: openEO_bbox_format) -> str | None:
+def catalogue_check_S1(orbit_direction: str, start: str, end: str, bbox: openEO_bbox_format,
+                       messages: bool=True, stop_processing: bool=True) -> str | None:
     """
-    Checks the availability of Sentinel-1 images based on the specified orbit direction, date range,
-    and bounding box. Validates the amount of data available against a predefined minimum threshold.
-
-    :param orbit_direction: The direction of the orbit, either 'ASCENDING' or 'DESCENDING'. If not
-        specified, the function will check data for both orbit directions. Must comply with the
-        specified format.
-    :param start: The start date of the desired time range in ISO 8601 date format (YYYY-MM-DD) or 'YYYY-MM-DDThh:mm:ss.SSZ'..
-    :param end: The end date of the desired time range in ISO 8601 date format (YYYY-MM-DD) or 'YYYY-MM-DDThh:mm:ss.SSZ'..
-    :param bbox: The bounding box of the area of interest in openEO_bbox_format. It will be reprojected
-        to a latitude and longitude format for API queries.
-    :return: Returns the specified orbit direction if sufficient Sentinel-1 images for the given
-        direction are available. Returns `None` if the checks for both orbit directions combined are
-        sufficient or if orbit direction was not specified. Raises an error if the amount of data
-        does not meet the threshold.
+    Checks the availability of Sentinel-1 imagery within a specified spatiotemporal extent and orbit
+    direction constraints in the given catalog.
+
+    This function determines if the number of Sentinel-1 images available in a specified bounding
+    box and temporal range meets an expected threshold. It supports restricting results based on
+    an orbit direction and provides summary messages or raises exceptions if conditions are not met.
+
+    :param orbit_direction: (str) The orbit direction for filtering imagery. Must be 'ASCENDING'
+                            or 'DESCENDING'. If None, both directions are checked.
+    :param start: (str) The start date of the query in ISO 8601 format. Time is appended as 'T00:00:00.00Z'
+                  if not provided.
+    :param end: (str) The end date of the query in ISO 8601 format. Time is appended as 'T00:00:00.00Z'
+                if not provided.
+    :param bbox: (openEO_bbox_format) A bounding box specifying the geographic extent of the query
+                 in the format supported by OpenEO.
+    :param messages: (bool) If True, print messages summarizing the results. Default is True.
+    :param stop_processing: (bool) If True, raises a ValueError when the imagery availability criteria
+                            are not met. Default is True.
+
+    :return: The specific orbit direction ('ASCENDING' or 'DESCENDING') if enough images are found
+             for that orbit direction, otherwise None.
     """
     #standard settigns for amount of expected files per day
     #quickfix on dates that are in date format
@@ -52,31 +61,41 @@ def catalogue_check_S1(orbit_direction: str, start: str, end: str, bbox: openEO_
         json_data = json.loads(results.text)
 
         if len(json_data["value"]) < MIN_VALUE_S1*percentage*temp_extent_days:
-            print(f'Not enough S1 images with orbit {orbit_direction}. \n' + \
-                  f'Found {len(json_data["value"])} images.')
-        else: return orbit_direction
+            if messages:
+                print(f'Not enough S1 images with orbit {orbit_direction}. \n' + \
+                      f'Found {len(json_data["value"])} images.')
+        else:
+            if messages:
+                print(f'Found {len(json_data["value"])} images with orbit direction {orbit_direction}.')
+            return orbit_direction
     #use both orbits
     #check with both directions.
     nbr_files = count_amount_of_files('S1', latlon_box, start, end)
     if nbr_files < MIN_VALUE_S1*percentage*temp_extent_days:
-        raise ValueError(f'not enough S1 without orbit direction selection. \n'+ \
-                         f'Found {nbr_files} images.')
+        if stop_processing:
+            raise ValueError(f'not enough S1 without orbit direction selection. \n'+ \
+                             f'Found {nbr_files} images.')
+    if messages:
+        print(f'Found {nbr_files} images with orbit direction BOTH.')
 
     return None
 
-def catalogue_check_S2(start: str, end: str, bbox: openEO_bbox_format) -> None:
+def catalogue_check_S2(start: str, end: str, bbox: openEO_bbox_format,
+                       messages: bool=True, stop_processing: bool=True) -> None:
     """
-    Check the availability of Sentinel-2 (S2) satellite images for a given time period
-    and bounding box. The function calculates the expected minimum number of images
-    and raises a ValueError if the actual count is insufficient.
-
-    :param start: The start date of the time period, in the format 'YYYY-MM-DD' or 'YYYY-MM-DDThh:mm:ss.SSZ'.
-    :param end: The end date of the time period, in the format 'YYYY-MM-DD'or 'YYYY-MM-DDThh:mm:ss.SSZ'..
-    :param bbox: The bounding box defining the spatial extent, must be in openEO
-        bounding box format.
-    :return: None
-    :raises ValueError: If the number of available Sentinel-2 images is less than the
-        required minimum threshold.
+    Checks the availability of Sentinel-2 (S2) satellite images within a given time range and bounding box.
+    The function determines if the number of available images meets the minimum threshold based on the temporal
+    extent and year-specific conditions. If the threshold is not met, it raises an error or optionally prints
+    the count of found images.
+
+    :param start: (str) The start date of the search range in ISO 8601 format.
+    :param end: (str) The end date of the search range in ISO 8601 format.
+    :param bbox: (openEO_bbox_format) The bounding box in a geographical coordinate system.
+    :param messages: (bool) Optional flag to print a message with the number of found images. Default is True.
+    :param stop_processing: (bool) Optional flag to raise an exception if the number of images is below the threshold.
+                            Default is True.
+
+    :raises ValueError: If the number of Sentinel-2 images does not meet the minimum threshold and stop_processing is True.
     """
     MIN_VALUE_S2 = 1./5.
     percentage = 0.8
@@ -95,7 +114,10 @@ def catalogue_check_S2(start: str, end: str, bbox: openEO_bbox_format) -> None:
 
     nbr_files = count_amount_of_files('S2', latlon_box, start, end)
     if nbr_files < MIN_VALUE_S2*percentage*temp_extent_days:
-        raise ValueError(f'not enough S2 images. Found {nbr_files} images.')
+        if stop_processing:
+            raise ValueError(f'not enough S2 images. Found {nbr_files} images.')
+    if messages:
+        print(f'Found {nbr_files} S2 images.')
 
 mece_sequence = [[[9], [15], [21], [27], [34], [40], [49], [54], [57], [62], [69], [73], [82]],
                  [[86], [89], [93], [99], [102], [110], [113], [117], [122], [126], [130], [135], [138]],
@@ -132,24 +154,30 @@ def count_amount_of_files(sentinel: str, latlon_box: geojson.Feature, start: str
     json_data = json.loads(results.text)
     return len(json_data["value"])
 
-def catalogue_check_CDSE_S1(orbit_direction: str, start: str, end: str, bbox: openEO_bbox_format) -> str | None:
+def catalogue_check_CDSE_S1(orbit_direction: str, start: str, end: str, bbox: openEO_bbox_format,
+                            messages: bool=True, stop_processing: bool=True) -> str | None:
     """
-    Executes a query to the Copernicus Data Space Ecosystem (CDSE) Sentinel-1 catalogue
-    to verify the availability of Sentinel-1 imagery over a specified temporal extent
-    and spatial bounding box. The function evaluates whether sufficient Sentinel-1
-    images exist based on certain thresholds and optionally filters by orbit direction.
-
-    :param orbit_direction: Direction of the orbit for filtering results. Can be
-        'ASCENDING', 'DESCENDING', or None for both. If provided, it must be one of these values.
-    :param start: Start date of the query temporal extent in ISO 8601 format
-        (YYYY-MM-DD). Time will default to "T00:00:00.00Z" if not specified.
-    :param end: End date of the query temporal extent in ISO 8601 format
-        (YYYY-MM-DD). Time will default to "T00:00:00.00Z" if not specified.
-    :param bbox: Spatial bounding box for the query in openEO_bbox_format. Used to
-        define the region of interest.
-
-    :return: The orbit direction if sufficient Sentinel-1 images are available for
-        the specified orbit, else None.
+    Checks the availability of Sentinel-1 satellite images for a given temporal and spatial extent
+    and optionally filters them by orbit direction. If the specified criteria are not met, the
+    function can optionally raise errors or display messages. VErsion to use with CDSE and pySTAC.
+
+    :param orbit_direction: str. The orbit direction to filter on. Acceptable values are
+                            'ASCENDING' or 'DESCENDING'. If None, both directions are considered.
+    :param start: str. Start date for the temporal extent in ISO 8601 format (e.g., 'YYYY-MM-DD').
+    :param end: str. End date for the temporal extent in ISO 8601 format (e.g., 'YYYY-MM-DD').
+    :param bbox: openEO_bbox_format. Bounding box defining the spatial extent of the search region
+                 in openEO format.
+    :param messages: bool (default=True). Whether to print messages about the results of the search.
+    :param stop_processing: bool (default=True). Whether to raise an error if the number of images
+                            found does not meet the required criteria.
+
+    :return: str | None. The orbit direction that satisfies the criteria if applicable. Returns
+             None if no specific orbit direction was found to meet the requirements or if no orbit
+             direction was specified.
+
+    :raises ValueError: If `orbit_direction` is not one of the acceptable values ('ASCENDING' or
+                        'DESCENDING'), or if not enough Sentinel-1 images are found to meet the
+                        required criteria when `stop_processing` is True.
     """
     #quickfix on dates that are in date format
     if not 'Z' in start:
@@ -184,64 +212,79 @@ def catalogue_check_CDSE_S1(orbit_direction: str, start: str, end: str, bbox: op
             datetime=f"{start}/{end}",
             fields=["id", "properties.datetime"],
             query={"sat:orbit_state": {"eq": f"{orbit_direction.lower()}"},
-                   #"sar:polarizations": {"eq": "VV&VH"},
+                   "sar:polarizations": {"eq": ["VV", "VH"]},
                    },
         )
 
         # get the dates of all found matches
-        results = []
-        for item in search.items_as_dicts():
-            results.append(item['properties']['datetime'])
+        results_single = []
+        query_retry(search, results_single)
 
         # count the number of unique dates on which we have observations (resolved tile overlap)
-        df = pd.DataFrame(results, columns=['date'])
+        df = pd.DataFrame(results_single, columns=['date'])
         df['date'] = pd.to_datetime(df['date'])
         df['date'] = df['date'].apply(lambda x: x.date())
         nbr_files = df['date'].nunique()
 
         if nbr_files < MIN_VALUE_S1*percentage*temp_extent_days:
-            print(f'Not enough S1 images with orbit {orbit_direction}. \n' + \
-                  f'Found {nbr_files} images.')
-        else: return orbit_direction
-    #use both orbits -> check with both directions.
+            if messages:
+                print(f'Not enough S1 images with orbit {orbit_direction}. \n' + \
+                      f'Found {nbr_files} images.')
+            # jump back to check with BOTH orbits
+            pass
+        else:
+            if messages:
+                print(f'Found {nbr_files} images with orbit direction {orbit_direction}.')
+            return orbit_direction
 
+    #use both orbits -> check with both directions.
     search = client.search(
         collections=['sentinel-1-grd'],
         bbox=list(latlon_box.bounds),
         datetime=f"{start}/{end}",
         fields=["id", "properties.datetime"],
-        #query={"sar:polarizations": {"eq": "VV&VH"} },
+        query={"sar:polarizations": {"eq": ["VV", "VH"]} },
     )
 
     # get the dates of all found matches
-    results = []
-    for item in search.items_as_dicts():
-        results.append(item['properties']['datetime'])
+    results_both = []
+    query_retry(search, results_both)
 
     # count the number of unique dates on which we have observations (resolved tile overlap)
-    df = pd.DataFrame(results, columns=['date'])
+    df = pd.DataFrame(results_both, columns=['date'])
     df['date'] = pd.to_datetime(df['date'])
     df['date'] = df['date'].apply(lambda x: x.date())
     nbr_files = df['date'].nunique()
 
     if nbr_files < MIN_VALUE_S1*percentage*temp_extent_days:
-        raise ValueError(f'not enough S1 without orbit direction selection. \n'+ \
-                         f'Found {nbr_files} images.')
+        if stop_processing:
+            raise ValueError(f'not enough S1 without orbit direction selection. \n'+ \
+                             f'Found {nbr_files} images.')
+    if messages:
+        print(f'Found {nbr_files} images with orbit direction BOTH.')
 
     return None
 
-def catalogue_check_CDSE_S2(start: str, end: str, bbox: openEO_bbox_format) -> None:
+def catalogue_check_CDSE_S2(start: str, end: str, bbox: openEO_bbox_format,
+                            messages: bool=True, stop_processing: bool=True) -> None:
     """
-    Checks the availability of Sentinel-2 images from the Copernicus Data Space Ecosystem STAC
-    API within a specified temporal and spatial extent. Validates whether the minimum required
-    observation density is met based on temporal extent duration and predefined thresholds.
-
-    :param start: The start date of the temporal extent in ISO 8601 format (e.g., "YYYY-MM-DD").
-    :param end: The end date of the temporal extent in ISO 8601 format (e.g., "YYYY-MM-DD").
-    :param bbox: A bounding box defining the spatial extent in openEO_bbox_format.
-
-    :raises ValueError: If the number of Sentinel-2 images found does not meet the minimum
-        required observation density for the specified bounding box and temporal extent.
+    Checks the availability of Sentinel-2 images for a specified temporal and spatial extent
+    using the Copernicus Data Space Ecosystem STAC API.
+
+    This function evaluates whether the available number of Sentinel-2 (S2) images falls
+    below a minimum threshold for an expected observation frequency based on the specified
+    temporal extent and spatial bounding box. The function can optionally stop further processing
+    if the images are insufficient or print a message about the number of images found.
+
+    :param start: (str) The start date of the temporal extent in "YYYY-MM-DD" format.
+    :param end: (str) The end date of the temporal extent in "YYYY-MM-DD" format.
+    :param bbox: (openEO_bbox_format) The spatial bounding box in an openEO-compatible format.
+    :param messages: (bool) A flag to indicate whether to print the number of images found. Defaults to True.
+    :param stop_processing: (bool) A flag to indicate whether to raise an error and halt processing if
+        the number of images is insufficient. Defaults to True.
+
+    :raises ValueError: If the number of available S2 images is less than the required threshold and
+        `stop_processing` is set to True.
     """
     #quickfix on dates that are in date format
     if not 'Z' in start:
@@ -278,8 +321,7 @@ def catalogue_check_CDSE_S2(start: str, end: str, bbox: openEO_bbox_format) -> N
 
     # get the dates of all found matches
     results = []
-    for item in search.items_as_dicts():
-        results.append(item['properties']['datetime'])
+    query_retry(search, results)
 
     # count the number of unique dates on which we have observations (resolved tile overlap)
     df = pd.DataFrame(results, columns=['date'])
@@ -289,4 +331,60 @@ def catalogue_check_CDSE_S2(start: str, end: str, bbox: openEO_bbox_format) -> N
 
     # run the test
     if nbr_files < MIN_VALUE_S2*percentage*temp_extent_days:
-        raise ValueError(f'not enough S2 images. Found {nbr_files} images.')
+        if stop_processing:
+            raise ValueError(f'not enough S2 images. Found {nbr_files} images.')
+    if messages:
+        print(f'Found {nbr_files} S2 images.')
+
+def catalogue_check_CDSE_S1_FeatureCollection(points_geometry: geojson.FeatureCollection, start_orbit: str,
+                                              start: str, end: str) -> str | None:
+    """
+    Checks the availability of satellite data within a defined geometry and time range.
+
+    This function takes a geography feature collection and a time range, then determines
+    satellite data availability by performing an orbit check. It calculates a bounding
+    box from the given feature collection to perform the check.
+
+    :param points_geometry: (geojson.FeatureCollection) The geometry as a feature
+        collection used to define the spatial extent.
+    :param start_orbit: (str) The starting orbit identifier for the data query.
+    :param start: (str) The start of the time range for the data query in ISO 8601 format.
+    :param end: (str) The end of the time range for the data query in ISO 8601 format.
+
+    :return: Returns a string containing the result of the orbit check if data is available.
+        Returns None if no data is found or the check fails.
+    """
+    # need openEO BBOX for orbit check
+    bbox = bbox_of_PointsFeatureCollection(points_geometry)
+    # now we run the orbit check and give result back
+    return catalogue_check_CDSE_S1(start_orbit, start, end, bbox, messages=False, stop_processing=False)
+
+
+def query_retry(search: pystac_client.ItemSearch, results: list, base_waiting_time: int = 20,
+                max_attempts: int = 3) -> list:
+    """
+    Retries a query multiple times with exponential backoff in case of failure.
+
+    This function performs a query using the provided pystac_client.ItemSearch object,
+    attempting to collect datetime properties from each item's dictionary representation.
+    It will retry the query up to a maximum configured number of attempts, applying an
+    exponential backoff between retries. If the maximum number of attempts is reached
+    and the query still fails, it will raise the exception encountered.
+
+    :param search: A pystac_client.ItemSearch object used to perform the item query.
+    :param results: A list where the datetimes from the queried items will be appended.
+    :param base_waiting_time: Initial waiting time in seconds for exponential backoff.
+        Default is 20 seconds.
+    :param max_attempts: Maximum number of retry attempts. Default is 3.
+    :return: A list containing the datetime properties of items retrieved from the query.
+    """
+    for attempt in range(max_attempts):
+        try:
+            for item in search.items_as_dicts():
+                results.append(item['properties']['datetime'])
+        except Exception as e:
+            if attempt < (max_attempts - 1):
+                time.sleep(base_waiting_time * (attempt+1))  # 20s, 40s, 60s...
+            else:
+                raise e
+    return results
\ No newline at end of file
diff --git a/src/eo_processing/utils/helper.py b/src/eo_processing/utils/helper.py
index 7d00904..e731c63 100644
--- a/src/eo_processing/utils/helper.py
+++ b/src/eo_processing/utils/helper.py
@@ -13,7 +13,7 @@
 from datetime import datetime
 import json
 from ast import literal_eval
-from typing import Union, Dict, List, TYPE_CHECKING
+from typing import Union, Dict, List, TYPE_CHECKING, Optional
 try:
     import importlib.resources as importlib_resources
 except:
@@ -21,39 +21,80 @@
 
 if TYPE_CHECKING:
     from eo_processing.config.data_formats import openEO_bbox_format
+    from eo_processing.utils.storage import WEED_storage
 
-def init_connection(provider: str) -> openeo.Connection :
+def init_connection(provider: str, storage: Optional[WEED_storage]=None) -> openeo.Connection :
     """
-    Initializes a connection to the specified OpenEO backend provider and
-    authenticates the connection using OpenID Connect. Supports connections
-    to Terrascope, Development, CDSE, CDSE-Staging, and a standard OpenEO
-    entry point.
-
-    :param provider: The name of the OpenEO backend provider. Supported values
-                     are 'terrascope', 'development', 'cdse', 'cdse-staging',
-                     or other for default OpenEO connection.
-    :return: An authenticated OpenEO connection to the specified provider.
-
-    :raises ValueError: If the provider specified does not match the supported
-                        categories and a backend-specific connection setup is
-                        unavailable.
+
+    Initializes a connection to an OpenEO backend based on the specified provider. Supports
+    two modes of authentication: OpenID Connect and client credentials when a storage object
+    is provided. Each provider corresponds to a specific backend URL.
+
+    :param provider: (str) The name of the OpenEO backend provider. Supported values include:
+        - 'terrascope': Connects to the VITO backend.
+        - 'development': Connects to the VITO development backend.
+        - 'cdse': Connects to the Copernicus Data Space Ecosystem backend.
+        - 'cdse-staging': Connects to the staging environment of the Copernicus Data Space
+          Ecosystem backend.
+        - 'cdse-staging-waw4-1': Connects to the staging WAW4-1 instance.
+        If an unsupported provider is specified and no storage is provided, a connection is
+        established with the default "https://openeo.cloud" entry point.
+
+    :param storage: (Optional[WEED_storage]) An optional storage object containing
+        service account credentials necessary for client credentials authentication. When
+        provided, attempts to authenticate using the storage's `CLIENT_ID` and `CLIENT_SECRET`.
+        Supported providers with this authentication mode include:
+        - 'cdse'
+        - 'cdse-staging'
+        - 'cdse-staging-waw4-1'
+
+    :return: An instance of `openeo.Connection` representing the connection to the selected
+        backend.
     """
-    if provider == 'terrascope':
-        connection = openeo.connect("https://openeo.vito.be").authenticate_oidc()
-    elif provider == 'development':
-        connection = openeo.connect("https://openeo-dev.vito.be").authenticate_oidc()
-    elif provider == 'cdse':
-        connection = openeo.connect(url="openeo.dataspace.copernicus.eu").authenticate_oidc()
-    elif provider == 'cdse-staging':
-        connection = openeo.connect(url='openeo-staging.dataspace.copernicus.eu').authenticate_oidc()
-    elif provider == 'cdse-staging-waw4-1':
-        connection = openeo.connect(url='https://openeo.stag.waw4-1.openeo-int.v1.dataspace.copernicus.eu').authenticate_oidc()
+    if storage is None:
+        if provider == 'terrascope':
+            url = 'https://openeo.vito.be'
+        elif provider == 'development':
+            url = 'https://openeo-dev.vito.be'
+        elif provider == 'cdse':
+            url = 'https://openeo.dataspace.copernicus.eu'
+        elif provider == 'cdse-staging':
+            url = 'https://openeo-staging.dataspace.copernicus.eu'
+        elif provider == 'cdse-staging-waw4-1':
+            url = 'https://openeo.stag.waw4-1.openeo-int.v1.dataspace.copernicus.eu'
+        else:
+            print('currently no specific connections to backends like creodias and sentinelhub are setup.')
+            print('use standard entry point')
+            url = 'https://openeo.cloud'
+        connection = openeo.connect(url).authenticate_oidc()
     else:
-        print('currently no specific connections to backends like creodias and sentinelhub are setup.')
-        print('use standard entry point')
-        connection = openeo.connect("https://openeo.cloud").authenticate_oidc()
+        if provider == 'cdse':
+            url = 'https://openeo.dataspace.copernicus.eu'
+        elif provider == 'cdse-staging':
+            url = 'https://openeo-staging.dataspace.copernicus.eu'
+        elif provider == 'cdse-staging-waw4-1':
+            url = 'https://openeo.stag.waw4-1.openeo-int.v1.dataspace.copernicus.eu'
+        else:
+            raise ValueError('currently no other backends are setup for WEED service account. Choose from cdse, cdse-staging, cdse-staging-waw4-1.')
+        connection = openeo.connect(url=url).authenticate_oidc_client_credentials(
+            client_id=storage.service_account['CLIENT_ID'],
+            client_secret=storage.service_account['CLIENT_SECRET'])
     return connection
 
+def purge_jobs(conn: openeo.Connection) -> None:
+    """
+    Purges all jobs from the given openEO connection.
+
+    :param conn: The openEO connection object.
+    """
+    jobs = conn.list_jobs(limit=1000)
+
+    for job_metadata in jobs:
+        if job_metadata.get("status", None) in ["queued", "running", "queued_for_start"]:
+            job = conn.job(job_metadata["id"])
+            print(f"Cancelling job {job.job_id} with status {job.status()}")
+            job.stop()
+    print("All jobs purged if needed.")
 
 def location_visu(aoi_object: openEO_bbox_format | gpd.GeoDataFrame, zoom: bool = False, region: str = 'EU',
                   label: bool = True) -> None:
diff --git a/src/eo_processing/utils/jobmanager.py b/src/eo_processing/utils/jobmanager.py
index bbfa96a..086c10b 100644
--- a/src/eo_processing/utils/jobmanager.py
+++ b/src/eo_processing/utils/jobmanager.py
@@ -1,6 +1,7 @@
 from __future__ import annotations
 import os
 import json
+import geojson
 import logging
 import geopandas as gpd
 from threading import Thread, active_count
@@ -27,7 +28,8 @@
 import openeo
 import warnings
 from eo_processing.utils.helper import string_to_dict
-from eo_processing.utils.geoprocessing import create_feature_extraction_processing_grid, get_point_number
+from eo_processing.utils.geoprocessing import (create_feature_extraction_processing_grid, get_point_number,
+                                               bbox_of_PointsFeatureCollection, reproj_bbox_to_ll)
 from eo_processing.utils.mgrs import gridID_2_epsg
 
 if TYPE_CHECKING:
@@ -119,25 +121,19 @@ def download_job_too_long(self, job: openeo.BatchJob, row: pd.Series) -> bool:
             return True
         else: return False
 
-    def check_finished(self, job: openeo.BatchJob) -> bool:
+    def check_finished(self, job: openeo.BatchJob, row: pd.Series) -> bool:
         """
-        Check if the metadata file for a given job already exists in the filesystem,
-        indicating whether the job has been completed.
-
-        This function extracts the job's metadata and determines the file path for
-        the associated metadata file. It then checks if this file path exists, which
-        would suggest that the job has been processed and the metadata has been saved.
-
-        :param job: The job object whose completion status needs to be verified. It
-                    must provide a 'describe' method that returns a dictionary
-                    containing job metadata, including the job's title.
-        :return: A boolean value where `True` indicates that the job metadata file
-                 exists, and thus the job is finished. `False` signifies that the
-                 metadata file is not found, indicating that the job might not be
-                 complete.
+        Determines if a batch job is finished by checking the existence of its metadata.
+
+        :param job: The batch job for which the status needs to be checked.
+        :param row: A pandas Series containing job-related information, including the
+            file_prefix used to identify the metadata file.
+        :return: True if the job's metadata file exists, indicating the job is finished;
+            False otherwise.
         """
-        job_metadata = job.describe()
-        title = os.path.splitext(job_metadata['title'])[0]
+        #job_metadata = job.describe()
+        #title = os.path.splitext(job_metadata['title'])[0]
+        title = row["file_prefix"]
         metadata_path = self.get_job_metadata_path(job.job_id, title)
         return os.path.exists(metadata_path)
 
@@ -223,7 +219,8 @@ def on_job_error(self, job: openeo.BatchJob, row: pd.Series) -> Union[str, bool]
         """
         error_logs = job.logs(level="error")
         job_metadata = job.describe_job()
-        title = os.path.splitext(job_metadata['title'])[0]
+        #title = os.path.splitext(job_metadata['title'])[0]
+        title = row["file_prefix"]
         error_log_path = self.get_error_log_path(job.job_id,title)
         job_graph_path = self.get_job_graph_path(job.job_id,title)
 
@@ -257,7 +254,10 @@ def on_job_done(self, job: openeo.BatchJob, row: pd.Series) -> None:
         job_metadata = job.describe()
 
         job_dir = self.get_job_dir(job.job_id)
-        title = os.path.splitext(job_metadata['title'])[0]
+        #title = os.path.splitext(job_metadata['title'])[0]
+
+        title = row["file_prefix"]
+
         file_ext = job_metadata['process']['process_graph']['saveresult1']['arguments']['format'].lower()
         metadata_path = self.get_job_metadata_path(job.job_id,title)
         job_graph_path = self.get_job_graph_path(job.job_id,title)
@@ -280,16 +280,15 @@ def on_job_done(self, job: openeo.BatchJob, row: pd.Series) -> None:
             else :
                 s3_client = self.storage_options["WEED_storage"].get_s3_client()
                 bucket_name= self.storage_options["WEED_storage"].get_s3_bucket_name()
-                s3_client.download_file(bucket_name, os.path.join(S3_prefix,f"timeseries.{file_ext}"),
+                s3_client.download_file(bucket_name, os.path.join(S3_prefix,f"{title}.{file_ext}"),
                                         job_dir / f"{title}.{file_ext}")
 
-
         if not self.storage_options.get('workspace_export', False):
             #fix prefix problem for non netcdf or GTiff files
             if file_ext in ['netcdf','gtiff']:
                 results.download_files(job_dir, include_stac_metadata=False)
             else :
-                results.download_file(job_dir / f"{title}.{file_ext}", name=f"timeseries.{file_ext}")
+                results.download_file(job_dir / f"{title}.{file_ext}")
 
 
         with open(metadata_path, "w", encoding='utf8') as f:
@@ -370,7 +369,7 @@ def _track_statuses(self, job_db: JobDatabaseInterface, stats: Optional[Dict] =
                     new_status = "downloading"
 
                 if previous_status == "downloading":
-                    if not self.check_finished(the_job):
+                    if not self.check_finished(the_job, active.loc[i]):
                         new_status = "downloading"
 
                 if previous_status != "error" and new_status == "error":
@@ -500,6 +499,8 @@ def _launch_job(self, start_job, df, i, backend_name, stats: Optional[Dict] = No
                         # start job if not yet done by callback
                         try:
                             job_con = job.connection
+                            # Proactively refresh bearer token (because task in thread will not be able to do that)
+                            self._refresh_bearer_token(connection=job_con)
                             task = _JobStartTask(
                                 root_url=job_con.root_url,
                                 bearer_token=job_con.auth.bearer if isinstance(job_con.auth, BearerAuth) else None,
@@ -781,6 +782,7 @@ def create_job_dataframe(gdf: Union[gpd.GeoDataFrame, List], year: int, file_nam
                          discriminator: Optional[str] = None, target_crs: Optional[int] = None,
                          version: Optional[str] = None,
                          model_ID: Optional[str] = None,
+                         nonEO_file: Optional[str] = None,
                          storage_options: Optional[storage_option_format] = None,
                          organization_id : Optional[int] = None, path_global_grid: Optional[str] = None,
                          feature_bbox: Optional[Tuple[float, float, float, float]] = None) -> gpd.GeoDataFrame:
@@ -816,11 +818,11 @@ def create_job_dataframe(gdf: Union[gpd.GeoDataFrame, List], year: int, file_nam
     if isinstance(gdf, gpd.GeoDataFrame):
         # we are preparing a inference or post-processing actions
         columns = ['name', 'tileID', 'target_epsg', 'bbox', 'file_prefix', 'start_date', 'end_date','export_workspace',
-                   's3_prefix', 'organization_id', 's2_tileid_list']
+                   's3_prefix', 'organization_id', 's2_tileid_list','nonEO_file']
         dtypes = {'name': 'string', 'tileID': 'string', 'target_epsg': 'UInt16',
                   'file_prefix': 'string', 'start_date': 'string', 'end_date': 'string', 's3_prefix': 'string',
                   'geometry': 'geometry', 'bbox': 'string', 'organization_id':'UInt16','s2_tileid_list':'string',
-                  'export_workspace':'string'}
+                  'export_workspace':'string','nonEO_file' : 'string'}
 
         job_df = gdf.copy()
 
@@ -861,6 +863,8 @@ def create_job_dataframe(gdf: Union[gpd.GeoDataFrame, List], year: int, file_nam
             job_df['s3_prefix'] = None
             job_df['export_workspace'] = None
 
+        # set no EO list  Should be later replaced by an extraction method straight out of the model metadata.
+        job_df['nonEO_file'] = nonEO_file
         # a fix since the "name" column has to be unique
         job_df['tileID'] = job_df[tile_col].copy()
         if discriminator:
@@ -959,8 +963,14 @@ def create_job_dataframe(gdf: Union[gpd.GeoDataFrame, List], year: int, file_nam
         # merge in the needed Polygons and convert to GeoDataFrame
         job_df = pd.merge(df, gdf_grid[['tile_name', 'geometry']], left_on='name', right_on='tile_name',
                           how='left')
-        # remove row which have no  polygon assigned due to fact that this grid is not in openEO processing extent
-        job_df = job_df.dropna(subset=["geometry"])
+        # we have to fix rows which did not get a valid geometry
+        missing_geometry_row = job_df[job_df['geometry'].isna()].index
+        #print(missing_geometry_row)
+        for row in missing_geometry_row:
+            job_df.at[row, 'geometry'] = reproj_bbox_to_ll(bbox_of_PointsFeatureCollection(geojson.loads(job_df.loc[row, 'FeatureCollection'])))
+            job_df.at[row, 'tile_name'] = job_df.loc[row, 'name']
+        #job_df = job_df.dropna(subset=["geometry"])
+
         # convert to GeoPandas GeoDataFrame
         job_df = gpd.GeoDataFrame(job_df, geometry='geometry')
         job_df.reset_index(inplace=True)
@@ -970,8 +980,17 @@ def create_job_dataframe(gdf: Union[gpd.GeoDataFrame, List], year: int, file_nam
         job_df['end_date'] = (
                     pd.to_datetime(job_df['end_date'], format='%Y-%m-%d') - pd.Timedelta(seconds=1)).dt.strftime(
             '%Y-%m-%dT%H:%M:%SZ')
-        job_df['export_workspace'] = None
-        job_df['s3_prefix'] = None
+        # set the s3_prefix which is needed for the path to S3 storage relative to bucket if we export
+        if storage_options:
+            job_df['s3_prefix'] = storage_options.get('S3_prefix', None)
+            if storage_options.get('WEED_storage', None):
+                job_df['export_workspace'] = storage_options['WEED_storage'].get_export_workspace()
+            else:
+                job_df['export_workspace'] = None
+        else:
+            job_df['s3_prefix'] = None
+            job_df['export_workspace'] = None
+
         job_df['organization_id'] = organization_id
         job_df['s2_tileid_list'] = None
 
diff --git a/src/eo_processing/utils/messaging.py b/src/eo_processing/utils/messaging.py
index 7391179..76574c0 100644
--- a/src/eo_processing/utils/messaging.py
+++ b/src/eo_processing/utils/messaging.py
@@ -6,8 +6,7 @@
 # Constants
 SMTP_SERVER = 'mail.vgt.vito.be'
 SENDER_NAME = 'WEED openEO processing cluster'
-SENDER_EMAIL = 'esa.weed.project@vito.be'
-
+SENDER_EMAIL = 'esa.weed.project@vgt.vito.be'
 
 def format_email_address(name_email_pair: Tuple[str, str]) -> str:
     """
diff --git a/src/eo_processing/utils/stac_helper.py b/src/eo_processing/utils/stac_helper.py
index 638e46d..e88e2f3 100644
--- a/src/eo_processing/utils/stac_helper.py
+++ b/src/eo_processing/utils/stac_helper.py
@@ -1,22 +1,51 @@
 import pystac_client
 
 
-def get_stac_collection_url(collection_id):
-    """Fetches the url of the STAC collection with the given collection_id. And returns None if not found."""
-    client = pystac_client.Client.open("https://catalogue.weed.apex.esa.int/")
+def get_stac_collection_url(collection_id: str, catalog_url: str = "https://catalogue.weed.apex.esa.int/") -> str:
+    """
+    Fetches the URL of a STAC (SpatioTemporal Asset Catalog) collection based on the provided 
+    collection ID and catalog URL.
+
+    This function utilizes the pystac_client library to interact with a STAC catalog and extract 
+    the URL of a specific collection by its ID. If the collection cannot be found, the function 
+    returns None.
+
+    :param collection_id (str): The unique identifier of the STAC collection to retrieve.
+    :param catalog_url (str): The URL of the STAC catalog to query. Defaults to 
+                              'https://catalogue.weed.apex.esa.int/'.
+
+    :return: The URL (as a string) of the requested STAC collection if found, or None if the 
+             collection does not exist in the catalog.
+    """
+    client = pystac_client.Client.open(catalog_url)
 
     try: return client.get_collection(collection_id).self_href
     except:
         return None
 
+def query_modelID_asset_url(model_id: str,
+                    catalog_url: str ="https://catalogue.weed.apex.esa.int/", 
+                    collection_id: str ="model-STAC-v2") -> str:
+    """
+    Queries the URL of a specific asset for a given modelID from a STAC catalog.
+
+    This function connects to the specified STAC catalog URL and searches for metadata
+    associated with the given modelID and collectionID using CQL2 filters. It returns
+    the URL of the asset identified as `model_valid_geometry`.
+
+    :param model_id: (str) The unique identifier of the model to search for.
+    :param catalog_url: (str) [Optional] The URL of the STAC catalog to query.
+                        Defaults to "https://catalogue.weed.apex.esa.int/".
+    :param collection_id: (str) [Optional] The ID of the collection in the STAC catalog
+                          to search within. Defaults to "model-STAC-v2".
 
-def query_asset_url(model_id):
-    """Use model-id to get the parquet asset link"""
-    client = pystac_client.Client.open("https://catalogue.weed.apex.esa.int/")
+    :return: (str) The URL of the asset associated with the searched model ID.
+    """
+    client = pystac_client.Client.open(catalog_url)
 
     search = client.search(
         limit=20,
-        collections=["model-STAC-v2"],
+        collections=[collection_id],
         filter={"op": "=", "args": [{"property": "properties.modelID"}, model_id]},
         filter_lang="cql2-json",
     )
diff --git a/src/eo_processing/utils/storage.py b/src/eo_processing/utils/storage.py
index 65977c6..c319101 100644
--- a/src/eo_processing/utils/storage.py
+++ b/src/eo_processing/utils/storage.py
@@ -2,6 +2,7 @@
 
 import os
 import boto3
+import pandas as pd
 from botocore.exceptions import ClientError
 from getpass import getpass
 import geopandas as gpd
@@ -760,6 +761,9 @@ def __init__(self, sql_credentials: Optional[sql_credentials_format] = None):
         #at the moment we initialize with hadoop false. Not sure if it's need to have?
         self.hadoop = False
 
+    def get_info(self):
+        return self.sql_credentials['host'], self.sql_credentials['port'], self.sql_credentials['dbname'], self.sql_credentials['schema'], self.sql_credentials['password']
+
     def create_connection(self) -> psycopg.Connection:
         """
         Establishes a connection to a PostgreSQL database using the provided credentials. 
@@ -811,6 +815,7 @@ def GenericQueryWithResult(self, sql_statement: str) -> List[tuple]:
             print('** get data from request')
             # create cursor
             cur = conn.cursor()
+            cur.itersize = 10000
             cur.execute(sql_statement)
             # get data
             vResult = cur.fetchall()
@@ -975,7 +980,78 @@ def QueryItems(self, table: str, lcolumns: List[str]) -> List[tuple]:
 
         return lresults
 
-    def StatusUpdateTiles(self, table: str, tileid: int, lcolumns: List[str], lmsg: List[str]) -> bool:
+    def AddColumns(self, table: str, column_names: lst(str)) -> None:
+        """
+        Adds a new column to a specified table in the database. The method dynamically constructs
+        an SQL ALTER TABLE statement to add the column with the specified name, ensuring
+        compatibility with the existing table structure. If the column already exists, the query
+        does not raise an error.
+
+        Args:
+            table (str): The name of the table to which the column should be added.
+            column_names (str): The names of the new columns.
+
+        Returns:
+            None
+        """
+
+        sql_statement = f"""ALTER TABLE {table}
+            {',\n'.join([f'ADD COLUMN IF NOT EXISTS "{col.lower()}" numeric' for col in column_names])};"""
+
+        self.GenericQueryWithOUTResult(sql_statement)
+
+    def UploadTrainingPointData(self, table: str, df: pd.DataFrame, column_names: List[str]) -> None:
+        """
+        Uploads data to the specified database table by adding missing columns, handling existing
+        data updates, and inserting new data points in bulk or individually.
+
+        This method performs the following steps:
+        1. Checks and ensures all necessary columns in the table.
+        2. Identifies whether existing data points need to be updated or if new points need to be
+           inserted.
+        3. Performs a bulk data insert for new data points if any.
+        4. Updates rows individually for existing data points.
+
+        Parameters:
+            table: str
+                The name of the database table where the data should be uploaded.
+            df: pd.DataFrame
+                A pandas DataFrame containing the data to be uploaded.
+            column_names: List[str]
+                A list of column names that need to be added to the table if they do not exist.
+
+        Raises:
+            None
+
+        Returns:
+            None
+        """
+
+        #First check if all columns are in the table
+        self.AddColumns(table, column_names)
+
+        #First check which points are new and which are not
+        sql_statement = f"""SELECT mgrsid10, year
+                            FROM {table}"""
+
+        available_keys = self.GenericQueryWithResult(sql_statement)
+
+        #split according to PK available are not
+        bulk_df = df[~df.set_index(['MGRSid10', 'year']).index.isin(available_keys)]
+        line_df = df[df.set_index(['MGRSid10', 'year']).index.isin(available_keys)]
+
+        if len(bulk_df) != 0:
+            #upload bulk
+            data = ReadFaker(bulk_df)
+            self.BulkInsert(table, data, tuple([column.lower() for column in df.columns]))
+
+        for index, row in line_df.iterrows():
+            #upload line
+            self.StatusUpdateTiles(table, (row['MGRSid10'], row['year']),
+                                           tuple([column.lower() for column in column_names]),
+                                           row[column_names].to_list())
+
+    def StatusUpdateTiles(self, table: str, PK: tuple(str, int), lcolumns: List[str], lmsg: List[str]) -> bool:
         """
         Updates specific columns in a particular database table for a given tile ID with new values.
 
@@ -986,7 +1062,7 @@ def StatusUpdateTiles(self, table: str, tileid: int, lcolumns: List[str], lmsg:
         database connection cleanup.
 
         :param table: The name of the database table to be updated.
-        :param tileid: The identifier of the tile for which data is to be updated.
+        :param PK: The identifier  for which data is to be updated.
         :param lcolumns: A list of column names that need to be updated.
         :param lmsg: A list of new values corresponding to the specified columns.
         :return: True if the update operation completes successfully, otherwise False.
@@ -1002,8 +1078,8 @@ def StatusUpdateTiles(self, table: str, tileid: int, lcolumns: List[str], lmsg:
             # prepare UPDATE statement
             print('** update the tile status...')
             for i in range(0, len(lcolumns)):
-                sql_statement = "UPDATE %s SET %s = %%s WHERE tile_id = %%s;" % (table, lcolumns[i])
-                cur.execute(sql_statement, (lmsg[i], tileid))
+                sql_statement = 'UPDATE %s SET "%s" = %%s WHERE (mgrsid10, year) = %%s;' % (table, lcolumns[i])
+                cur.execute(sql_statement, (lmsg[i], PK))
 
             # commit transactions
             conn.commit()
@@ -1280,7 +1356,7 @@ def upload_collection_to_catalog(self, collection: pystac.Collection, edit_flag:
         #get the auth
         auth_token = self.get_bearer_auth()
         #get catalog_url
-        catalog_url = self.get_catalog_url()
+        catalog_url = self.get_catalog_url().rstrip('/')
 
         # load the collection from the created collection.  
         coll = collection.to_dict()
@@ -1296,7 +1372,7 @@ def upload_collection_to_catalog(self, collection: pystac.Collection, edit_flag:
             # upload a new collection
             collection_url = f"{catalog_url}/collections/"
             resp = post(collection_url, auth=auth_token, json=coll)
-        if resp.status_code == 201:
+        if resp.status_code == 200 or resp.status_code == 201:
             coll_id = resp.json()["id"]
             if edit_flag:
                 print(f"Collection edited: {coll_id}")
@@ -1326,7 +1402,7 @@ def upload_items_to_collection(self, collection: pystac.Collection,
         #get the auth
         auth_token = self.get_bearer_auth()
         #get catalog_url
-        catalog_url = self.get_catalog_url()
+        catalog_url = self.get_catalog_url().rstrip('/')
 
         # check if there are items that need to be uploaded only if update is False
         if len(items_to_upload) == 0:
@@ -1588,7 +1664,7 @@ def __init__(self, username: str = 'buchhornm',
         S3 bucket and ML Flow uri. It also initializes necessary credentials and configurations for using
         Google Drive and S3 storage services.
 
-        :param username: A username string used for accessing credentials.
+        :param username: A username string used for accessing credentials. NOTE use "VAULT_TOKEN" to use token saved in environment variable.
         :param gdrive_entry_point: The entry point ID of the Google Drive folder.
         :param s3_bucket: The name of the S3 bucket to be used.
         :param stac_env: The environment name for the STAC catalog.
@@ -1609,6 +1685,7 @@ def __init__(self, username: str = 'buchhornm',
         self._set_gdrive_credentials(gdrive_entry_point=gdrive_entry_point)
         self._set_stac_credentials(stac_env=stac_env)
         self._set_mlflow_credentials()
+        self._set_service_account()
 
     def _get_credentials(self):
         """warper to get the credentials."""
@@ -1665,6 +1742,17 @@ def _set_s3_credentials(self, bucket: str) -> None:
             self.s3_client.close()
             self._init_boto3()
 
+    def _set_service_account(self) -> None:
+        """
+        Sets the service account based on provided credentials.
+
+        This method retrieves the service account information from the
+        credentials dictionary and assigns it to the service_account attribute.
+
+        :return: None
+        """
+        self.service_account = string_to_dict(self.credentials['weed-service-account'])
+
     def _set_sql_credentials(self) -> None:
         """
         Sets SQL credentials for the database connection.
@@ -1766,30 +1854,57 @@ def _set_stac_credentials(self, stac_env: str) -> None:
 
 def get_credentials(user :str ) -> Dict[str, str]:
     """
-    Retrieves WEED access credentials from Terrascope VAULT using LDAP authentication.
+    Gets the credentials of a specified user from the Terrascope VAULT.
+
+    This function prompts the user to enter their password and then
+    authenticates with the Terrascope VAULT service using the LDAP method.
+    Once authenticated, it attempts to retrieve the secret for the TAP apps
+    under the WEED path from the Vault. If unsuccessful, an exception is raised.
+
+    Parameters:
+    :param user: (str) The username of the account to authenticate against the VAULT. NOTE use "VAULT_TOKEN" to use token saved in environment variable.
 
-    This method prompts the user to enter their password for Terrascope VAULT, authenticates
-    with the VAULT using LDAP, and fetches credentials from the WEED KV storage path.
+    Returns:
+    :returns: Dictionary containing the retrieved secret credentials.
 
-    :return: credentials as a dictionary
+    Raises:
+    :raises Exception: If the credentials cannot be retrieved (e.g., not connected
+                       to the VITO VPN or authentication failure).
     """
-    password_prompt = 'Please enter your password for the Terrascope VAULT: '
-    service_account_password = getpass(prompt=password_prompt)
+    # first a check if username is "VAULT_TOKEN"
+    if user == "VAULT_TOKEN":
+        # we run the auth via token from environment variable
+        # check if TOKEN is set
+        vault_token = os.environ.get('VAULT_TOKEN')
+        if vault_token is None:
+            raise Exception('VAULT_TOKEN environment variable is not set. Please set it and try again. Or use a different username.')
+    else:
+        password_prompt = 'Please enter your password for the Terrascope VAULT: '
+        service_account_password = getpass(prompt=password_prompt)
 
     try:
         client = hvac.Client(url='https://vault.vgt.vito.be')
-        client.auth.ldap.login(
-            username=user,
-            password=service_account_password,
-            mount_point='ldap'
-        )
+        if user == "VAULT_TOKEN":
+            client.token = vault_token
+            if not client.is_authenticated():
+                raise Exception('Your token is expired. Please re-authenticate.')
+        else:
+            client.auth.ldap.login(
+                username=user,
+                password=service_account_password,
+                mount_point='ldap'
+            )
+
+            if not client.is_authenticated():
+                raise Exception('Your credentials are invalid. Please re-authenticate.')
+
         secret_version_response = client.secrets.kv.v2.read_secret_version(mount_point='kv',
                                                                            path='TAP/apps/WEED',
                                                                            raise_on_deleted_version=True)
         client.logout()
     except:
         raise Exception('Could not retrieve WEED credentials from Terrascope VAULT. '
-                        'Are you connected to the VITO VPN?')
+                        'Are you connected to the VITO VPN? Check your password or renew your token!')
     return secret_version_response['data']['data']
 
 def read_credential_file(file_path: str = '~/.sonata_credentials') -> Dict[str, str]:
diff --git a/tests/resources/cube_extraction/extract_S1_basic.json b/tests/resources/cube_extraction/extract_S1_basic.json
index 73c6eff..36511c7 100644
--- a/tests/resources/cube_extraction/extract_S1_basic.json
+++ b/tests/resources/cube_extraction/extract_S1_basic.json
@@ -12,7 +12,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -20,7 +20,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -56,7 +59,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
diff --git a/tests/resources/cube_extraction/extract_S1_custom_crs.json b/tests/resources/cube_extraction/extract_S1_custom_crs.json
index b5e8f7d..8cd3a4a 100644
--- a/tests/resources/cube_extraction/extract_S1_custom_crs.json
+++ b/tests/resources/cube_extraction/extract_S1_custom_crs.json
@@ -12,7 +12,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -20,7 +20,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -56,7 +59,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
diff --git a/tests/resources/cube_extraction/extract_S1_integration.json b/tests/resources/cube_extraction/extract_S1_integration.json
index 286d570..58b67db 100644
--- a/tests/resources/cube_extraction/extract_S1_integration.json
+++ b/tests/resources/cube_extraction/extract_S1_integration.json
@@ -16,7 +16,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -24,7 +24,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
diff --git a/tests/resources/cube_extraction/extract_S1_temporal_aggregation.json b/tests/resources/cube_extraction/extract_S1_temporal_aggregation.json
index aa0ab2d..59a572c 100644
--- a/tests/resources/cube_extraction/extract_S1_temporal_aggregation.json
+++ b/tests/resources/cube_extraction/extract_S1_temporal_aggregation.json
@@ -12,7 +12,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -20,7 +20,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -56,7 +59,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
diff --git a/tests/resources/cube_extraction/ts_datacube_extraction_S1_interpolation.json b/tests/resources/cube_extraction/ts_datacube_extraction_S1_interpolation.json
index 7212dc1..29448ea 100644
--- a/tests/resources/cube_extraction/ts_datacube_extraction_S1_interpolation.json
+++ b/tests/resources/cube_extraction/ts_datacube_extraction_S1_interpolation.json
@@ -141,7 +141,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -149,7 +149,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -185,7 +188,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
diff --git a/tests/resources/cube_extraction/ts_datacube_extraction_S2_with_masking.json b/tests/resources/cube_extraction/ts_datacube_extraction_S2_with_masking.json
index cad2077..eacf802 100644
--- a/tests/resources/cube_extraction/ts_datacube_extraction_S2_with_masking.json
+++ b/tests/resources/cube_extraction/ts_datacube_extraction_S2_with_masking.json
@@ -197,7 +197,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -205,7 +205,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -241,7 +244,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
diff --git a/tests/resources/cube_extraction/ts_datacube_extraction_combined.json b/tests/resources/cube_extraction/ts_datacube_extraction_combined.json
index bbfae6a..d0e2143 100644
--- a/tests/resources/cube_extraction/ts_datacube_extraction_combined.json
+++ b/tests/resources/cube_extraction/ts_datacube_extraction_combined.json
@@ -97,7 +97,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -105,7 +105,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -141,7 +144,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
diff --git a/tests/resources/cube_extraction/ts_datacube_extraction_combined_custom_crs.json b/tests/resources/cube_extraction/ts_datacube_extraction_combined_custom_crs.json
index c19956b..81a443b 100644
--- a/tests/resources/cube_extraction/ts_datacube_extraction_combined_custom_crs.json
+++ b/tests/resources/cube_extraction/ts_datacube_extraction_combined_custom_crs.json
@@ -97,7 +97,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -105,7 +105,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -141,7 +144,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
diff --git a/tests/resources/cube_extraction/ts_datacube_extraction_combined_integration.json b/tests/resources/cube_extraction/ts_datacube_extraction_combined_integration.json
index 852acef..6bf449c 100644
--- a/tests/resources/cube_extraction/ts_datacube_extraction_combined_integration.json
+++ b/tests/resources/cube_extraction/ts_datacube_extraction_combined_integration.json
@@ -101,7 +101,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -109,7 +109,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
diff --git a/tests/resources/cube_generation/generate_S1_feature_cube.json b/tests/resources/cube_generation/generate_S1_feature_cube.json
index 3704b40..930a43a 100644
--- a/tests/resources/cube_generation/generate_S1_feature_cube.json
+++ b/tests/resources/cube_generation/generate_S1_feature_cube.json
@@ -12,7 +12,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -20,7 +20,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -56,7 +59,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
@@ -516,7 +518,6 @@
       "process_id": "apply_dimension",
       "arguments": {
         "context": {
-          "parallel": true,
           "TileSize": 128
         },
         "data": {
@@ -671,66 +672,66 @@
         },
         "dimension": "bands",
         "target": [
-          "VH_p2",
-          "VH_p5",
-          "VH_p25",
-          "VH_median",
-          "VH_p75",
-          "VH_p95",
-          "VH_p98",
-          "VH_mean",
-          "VH_sd",
-          "VH_sum",
-          "VH_iqr",
-          "VH_iqr0595",
-          "VV_p2",
-          "VV_p5",
-          "VV_p25",
-          "VV_median",
-          "VV_p75",
-          "VV_p95",
-          "VV_p98",
-          "VV_mean",
-          "VV_sd",
-          "VV_sum",
-          "VV_iqr",
-          "VV_iqr0595",
-          "VHVVD_p2",
-          "VHVVD_p5",
-          "VHVVD_p25",
-          "VHVVD_median",
-          "VHVVD_p75",
-          "VHVVD_p95",
-          "VHVVD_p98",
-          "VHVVD_mean",
-          "VHVVD_sd",
-          "VHVVD_sum",
-          "VHVVD_iqr",
-          "VHVVD_iqr0595",
-          "VHVVR_p2",
-          "VHVVR_p5",
-          "VHVVR_p25",
-          "VHVVR_median",
-          "VHVVR_p75",
-          "VHVVR_p95",
-          "VHVVR_p98",
-          "VHVVR_mean",
-          "VHVVR_sd",
-          "VHVVR_sum",
-          "VHVVR_iqr",
-          "VHVVR_iqr0595",
-          "DpRVIVV_p2",
-          "DpRVIVV_p5",
-          "DpRVIVV_p25",
-          "DpRVIVV_median",
-          "DpRVIVV_p75",
-          "DpRVIVV_p95",
-          "DpRVIVV_p98",
-          "DpRVIVV_mean",
-          "DpRVIVV_sd",
-          "DpRVIVV_sum",
-          "DpRVIVV_iqr",
-          "DpRVIVV_iqr0595"
+          "vh_p2",
+          "vh_p5",
+          "vh_p25",
+          "vh_median",
+          "vh_p75",
+          "vh_p95",
+          "vh_p98",
+          "vh_mean",
+          "vh_sd",
+          "vh_sum",
+          "vh_iqr",
+          "vh_iqr0595",
+          "vv_p2",
+          "vv_p5",
+          "vv_p25",
+          "vv_median",
+          "vv_p75",
+          "vv_p95",
+          "vv_p98",
+          "vv_mean",
+          "vv_sd",
+          "vv_sum",
+          "vv_iqr",
+          "vv_iqr0595",
+          "vhvvd_p2",
+          "vhvvd_p5",
+          "vhvvd_p25",
+          "vhvvd_median",
+          "vhvvd_p75",
+          "vhvvd_p95",
+          "vhvvd_p98",
+          "vhvvd_mean",
+          "vhvvd_sd",
+          "vhvvd_sum",
+          "vhvvd_iqr",
+          "vhvvd_iqr0595",
+          "vhvvr_p2",
+          "vhvvr_p5",
+          "vhvvr_p25",
+          "vhvvr_median",
+          "vhvvr_p75",
+          "vhvvr_p95",
+          "vhvvr_p98",
+          "vhvvr_mean",
+          "vhvvr_sd",
+          "vhvvr_sum",
+          "vhvvr_iqr",
+          "vhvvr_iqr0595",
+          "dprvivv_p2",
+          "dprvivv_p5",
+          "dprvivv_p25",
+          "dprvivv_median",
+          "dprvivv_p75",
+          "dprvivv_p95",
+          "dprvivv_p98",
+          "dprvivv_mean",
+          "dprvivv_sd",
+          "dprvivv_sum",
+          "dprvivv_iqr",
+          "dprvivv_iqr0595"
         ]
       }
     },
@@ -738,63 +739,63 @@
       "process_id": "filter_bands",
       "arguments": {
         "bands": [
-          "VH_p2",
-          "VH_p5",
-          "VH_p25",
-          "VH_median",
-          "VH_p75",
-          "VH_p95",
-          "VH_p98",
-          "VH_mean",
-          "VH_sd",
-          "VH_iqr",
-          "VH_iqr0595",
-          "VV_p2",
-          "VV_p5",
-          "VV_p25",
-          "VV_median",
-          "VV_p75",
-          "VV_p95",
-          "VV_p98",
-          "VV_mean",
-          "VV_sd",
-          "VV_iqr",
-          "VV_iqr0595",
-          "VHVVD_p2",
-          "VHVVD_p5",
-          "VHVVD_p25",
-          "VHVVD_median",
-          "VHVVD_p75",
-          "VHVVD_p95",
-          "VHVVD_p98",
-          "VHVVD_mean",
-          "VHVVD_sd",
-          "VHVVD_iqr",
-          "VHVVD_iqr0595",
-          "VHVVR_p2",
-          "VHVVR_p5",
-          "VHVVR_p25",
-          "VHVVR_median",
-          "VHVVR_p75",
-          "VHVVR_p95",
-          "VHVVR_p98",
-          "VHVVR_mean",
-          "VHVVR_sd",
-          "VHVVR_sum",
-          "VHVVR_iqr",
-          "VHVVR_iqr0595",
-          "DpRVIVV_p2",
-          "DpRVIVV_p5",
-          "DpRVIVV_p25",
-          "DpRVIVV_median",
-          "DpRVIVV_p75",
-          "DpRVIVV_p95",
-          "DpRVIVV_p98",
-          "DpRVIVV_mean",
-          "DpRVIVV_sd",
-          "DpRVIVV_sum",
-          "DpRVIVV_iqr",
-          "DpRVIVV_iqr0595"
+          "vh_p2",
+          "vh_p5",
+          "vh_p25",
+          "vh_median",
+          "vh_p75",
+          "vh_p95",
+          "vh_p98",
+          "vh_mean",
+          "vh_sd",
+          "vh_iqr",
+          "vh_iqr0595",
+          "vv_p2",
+          "vv_p5",
+          "vv_p25",
+          "vv_median",
+          "vv_p75",
+          "vv_p95",
+          "vv_p98",
+          "vv_mean",
+          "vv_sd",
+          "vv_iqr",
+          "vv_iqr0595",
+          "vhvvd_p2",
+          "vhvvd_p5",
+          "vhvvd_p25",
+          "vhvvd_median",
+          "vhvvd_p75",
+          "vhvvd_p95",
+          "vhvvd_p98",
+          "vhvvd_mean",
+          "vhvvd_sd",
+          "vhvvd_iqr",
+          "vhvvd_iqr0595",
+          "vhvvr_p2",
+          "vhvvr_p5",
+          "vhvvr_p25",
+          "vhvvr_median",
+          "vhvvr_p75",
+          "vhvvr_p95",
+          "vhvvr_p98",
+          "vhvvr_mean",
+          "vhvvr_sd",
+          "vhvvr_sum",
+          "vhvvr_iqr",
+          "vhvvr_iqr0595",
+          "dprvivv_p2",
+          "dprvivv_p5",
+          "dprvivv_p25",
+          "dprvivv_median",
+          "dprvivv_p75",
+          "dprvivv_p95",
+          "dprvivv_p98",
+          "dprvivv_mean",
+          "dprvivv_sd",
+          "dprvivv_sum",
+          "dprvivv_iqr",
+          "dprvivv_iqr0595"
         ],
         "data": {
           "from_node": "renamelabels2"
diff --git a/tests/resources/cube_generation/generate_S1_feature_cube_integration.json b/tests/resources/cube_generation/generate_S1_feature_cube_integration.json
index d6014e7..1536b1d 100644
--- a/tests/resources/cube_generation/generate_S1_feature_cube_integration.json
+++ b/tests/resources/cube_generation/generate_S1_feature_cube_integration.json
@@ -16,7 +16,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -24,7 +24,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
diff --git a/tests/resources/cube_generation/generate_S2_feature_cube.json b/tests/resources/cube_generation/generate_S2_feature_cube.json
index 345ad04..84d8709 100644
--- a/tests/resources/cube_generation/generate_S2_feature_cube.json
+++ b/tests/resources/cube_generation/generate_S2_feature_cube.json
@@ -1269,7 +1269,6 @@
       "process_id": "apply_dimension",
       "arguments": {
         "context": {
-          "parallel": true,
           "TileSize": 128
         },
         "data": {
@@ -1424,366 +1423,366 @@
         },
         "dimension": "bands",
         "target": [
-          "B02_p2",
-          "B02_p5",
-          "B02_p25",
-          "B02_median",
-          "B02_p75",
-          "B02_p95",
-          "B02_p98",
-          "B02_mean",
-          "B02_sd",
-          "B02_sum",
-          "B02_iqr",
-          "B02_iqr0595",
-          "B03_p2",
-          "B03_p5",
-          "B03_p25",
-          "B03_median",
-          "B03_p75",
-          "B03_p95",
-          "B03_p98",
-          "B03_mean",
-          "B03_sd",
-          "B03_sum",
-          "B03_iqr",
-          "B03_iqr0595",
-          "B04_p2",
-          "B04_p5",
-          "B04_p25",
-          "B04_median",
-          "B04_p75",
-          "B04_p95",
-          "B04_p98",
-          "B04_mean",
-          "B04_sd",
-          "B04_sum",
-          "B04_iqr",
-          "B04_iqr0595",
-          "B05_p2",
-          "B05_p5",
-          "B05_p25",
-          "B05_median",
-          "B05_p75",
-          "B05_p95",
-          "B05_p98",
-          "B05_mean",
-          "B05_sd",
-          "B05_sum",
-          "B05_iqr",
-          "B05_iqr0595",
-          "B06_p2",
-          "B06_p5",
-          "B06_p25",
-          "B06_median",
-          "B06_p75",
-          "B06_p95",
-          "B06_p98",
-          "B06_mean",
-          "B06_sd",
-          "B06_sum",
-          "B06_iqr",
-          "B06_iqr0595",
-          "B07_p2",
-          "B07_p5",
-          "B07_p25",
-          "B07_median",
-          "B07_p75",
-          "B07_p95",
-          "B07_p98",
-          "B07_mean",
-          "B07_sd",
-          "B07_sum",
-          "B07_iqr",
-          "B07_iqr0595",
-          "B08_p2",
-          "B08_p5",
-          "B08_p25",
-          "B08_median",
-          "B08_p75",
-          "B08_p95",
-          "B08_p98",
-          "B08_mean",
-          "B08_sd",
-          "B08_sum",
-          "B08_iqr",
-          "B08_iqr0595",
-          "B8A_p2",
-          "B8A_p5",
-          "B8A_p25",
-          "B8A_median",
-          "B8A_p75",
-          "B8A_p95",
-          "B8A_p98",
-          "B8A_mean",
-          "B8A_sd",
-          "B8A_sum",
-          "B8A_iqr",
-          "B8A_iqr0595",
-          "B11_p2",
-          "B11_p5",
-          "B11_p25",
-          "B11_median",
-          "B11_p75",
-          "B11_p95",
-          "B11_p98",
-          "B11_mean",
-          "B11_sd",
-          "B11_sum",
-          "B11_iqr",
-          "B11_iqr0595",
-          "B12_p2",
-          "B12_p5",
-          "B12_p25",
-          "B12_median",
-          "B12_p75",
-          "B12_p95",
-          "B12_p98",
-          "B12_mean",
-          "B12_sd",
-          "B12_sum",
-          "B12_iqr",
-          "B12_iqr0595",
-          "ABDI1_p2",
-          "ABDI1_p5",
-          "ABDI1_p25",
-          "ABDI1_median",
-          "ABDI1_p75",
-          "ABDI1_p95",
-          "ABDI1_p98",
-          "ABDI1_mean",
-          "ABDI1_sd",
-          "ABDI1_sum",
-          "ABDI1_iqr",
-          "ABDI1_iqr0595",
-          "ABDI2_p2",
-          "ABDI2_p5",
-          "ABDI2_p25",
-          "ABDI2_median",
-          "ABDI2_p75",
-          "ABDI2_p95",
-          "ABDI2_p98",
-          "ABDI2_mean",
-          "ABDI2_sd",
-          "ABDI2_sum",
-          "ABDI2_iqr",
-          "ABDI2_iqr0595",
-          "AWEInsh_p2",
-          "AWEInsh_p5",
-          "AWEInsh_p25",
-          "AWEInsh_median",
-          "AWEInsh_p75",
-          "AWEInsh_p95",
-          "AWEInsh_p98",
-          "AWEInsh_mean",
-          "AWEInsh_sd",
-          "AWEInsh_sum",
-          "AWEInsh_iqr",
-          "AWEInsh_iqr0595",
-          "AVI_p2",
-          "AVI_p5",
-          "AVI_p25",
-          "AVI_median",
-          "AVI_p75",
-          "AVI_p95",
-          "AVI_p98",
-          "AVI_mean",
-          "AVI_sd",
-          "AVI_sum",
-          "AVI_iqr",
-          "AVI_iqr0595",
-          "BLFEI_p2",
-          "BLFEI_p5",
-          "BLFEI_p25",
-          "BLFEI_median",
-          "BLFEI_p75",
-          "BLFEI_p95",
-          "BLFEI_p98",
-          "BLFEI_mean",
-          "BLFEI_sd",
-          "BLFEI_sum",
-          "BLFEI_iqr",
-          "BLFEI_iqr0595",
-          "CIRE_p2",
-          "CIRE_p5",
-          "CIRE_p25",
-          "CIRE_median",
-          "CIRE_p75",
-          "CIRE_p95",
-          "CIRE_p98",
-          "CIRE_mean",
-          "CIRE_sd",
-          "CIRE_sum",
-          "CIRE_iqr",
-          "CIRE_iqr0595",
-          "EVI_p2",
-          "EVI_p5",
-          "EVI_p25",
-          "EVI_median",
-          "EVI_p75",
-          "EVI_p95",
-          "EVI_p98",
-          "EVI_mean",
-          "EVI_sd",
-          "EVI_sum",
-          "EVI_iqr",
-          "EVI_iqr0595",
-          "IRECI_p2",
-          "IRECI_p5",
-          "IRECI_p25",
-          "IRECI_median",
-          "IRECI_p75",
-          "IRECI_p95",
-          "IRECI_p98",
-          "IRECI_mean",
-          "IRECI_sd",
-          "IRECI_sum",
-          "IRECI_iqr",
-          "IRECI_iqr0595",
-          "MBWI_p2",
-          "MBWI_p5",
-          "MBWI_p25",
-          "MBWI_median",
-          "MBWI_p75",
-          "MBWI_p95",
-          "MBWI_p98",
-          "MBWI_mean",
-          "MBWI_sd",
-          "MBWI_sum",
-          "MBWI_iqr",
-          "MBWI_iqr0595",
-          "MNDWI_p2",
-          "MNDWI_p5",
-          "MNDWI_p25",
-          "MNDWI_median",
-          "MNDWI_p75",
-          "MNDWI_p95",
-          "MNDWI_p98",
-          "MNDWI_mean",
-          "MNDWI_sd",
-          "MNDWI_sum",
-          "MNDWI_iqr",
-          "MNDWI_iqr0595",
-          "MNDVI_p2",
-          "MNDVI_p5",
-          "MNDVI_p25",
-          "MNDVI_median",
-          "MNDVI_p75",
-          "MNDVI_p95",
-          "MNDVI_p98",
-          "MNDVI_mean",
-          "MNDVI_sd",
-          "MNDVI_sum",
-          "MNDVI_iqr",
-          "MNDVI_iqr0595",
-          "NDMI_p2",
-          "NDMI_p5",
-          "NDMI_p25",
-          "NDMI_median",
-          "NDMI_p75",
-          "NDMI_p95",
-          "NDMI_p98",
-          "NDMI_mean",
-          "NDMI_sd",
-          "NDMI_sum",
-          "NDMI_iqr",
-          "NDMI_iqr0595",
-          "NDVI_p2",
-          "NDVI_p5",
-          "NDVI_p25",
-          "NDVI_median",
-          "NDVI_p75",
-          "NDVI_p95",
-          "NDVI_p98",
-          "NDVI_mean",
-          "NDVI_sd",
-          "NDVI_sum",
-          "NDVI_iqr",
-          "NDVI_iqr0595",
-          "NDVIMNDWI_p2",
-          "NDVIMNDWI_p5",
-          "NDVIMNDWI_p25",
-          "NDVIMNDWI_median",
-          "NDVIMNDWI_p75",
-          "NDVIMNDWI_p95",
-          "NDVIMNDWI_p98",
-          "NDVIMNDWI_mean",
-          "NDVIMNDWI_sd",
-          "NDVIMNDWI_sum",
-          "NDVIMNDWI_iqr",
-          "NDVIMNDWI_iqr0595",
-          "NDWI_p2",
-          "NDWI_p5",
-          "NDWI_p25",
-          "NDWI_median",
-          "NDWI_p75",
-          "NDWI_p95",
-          "NDWI_p98",
-          "NDWI_mean",
-          "NDWI_sd",
-          "NDWI_sum",
-          "NDWI_iqr",
-          "NDWI_iqr0595",
-          "NMDI_p2",
-          "NMDI_p5",
-          "NMDI_p25",
-          "NMDI_median",
-          "NMDI_p75",
-          "NMDI_p95",
-          "NMDI_p98",
-          "NMDI_mean",
-          "NMDI_sd",
-          "NMDI_sum",
-          "NMDI_iqr",
-          "NMDI_iqr0595",
-          "NIRv_p2",
-          "NIRv_p5",
-          "NIRv_p25",
-          "NIRv_median",
-          "NIRv_p75",
-          "NIRv_p95",
-          "NIRv_p98",
-          "NIRv_mean",
-          "NIRv_sd",
-          "NIRv_sum",
-          "NIRv_iqr",
-          "NIRv_iqr0595",
-          "S2WI_p2",
-          "S2WI_p5",
-          "S2WI_p25",
-          "S2WI_median",
-          "S2WI_p75",
-          "S2WI_p95",
-          "S2WI_p98",
-          "S2WI_mean",
-          "S2WI_sd",
-          "S2WI_sum",
-          "S2WI_iqr",
-          "S2WI_iqr0595",
-          "S2REP_p2",
-          "S2REP_p5",
-          "S2REP_p25",
-          "S2REP_median",
-          "S2REP_p75",
-          "S2REP_p95",
-          "S2REP_p98",
-          "S2REP_mean",
-          "S2REP_sd",
-          "S2REP_sum",
-          "S2REP_iqr",
-          "S2REP_iqr0595",
-          "WRI_p2",
-          "WRI_p5",
-          "WRI_p25",
-          "WRI_median",
-          "WRI_p75",
-          "WRI_p95",
-          "WRI_p98",
-          "WRI_mean",
-          "WRI_sd",
-          "WRI_sum",
-          "WRI_iqr",
-          "WRI_iqr0595"
+          "b02_p2",
+          "b02_p5",
+          "b02_p25",
+          "b02_median",
+          "b02_p75",
+          "b02_p95",
+          "b02_p98",
+          "b02_mean",
+          "b02_sd",
+          "b02_sum",
+          "b02_iqr",
+          "b02_iqr0595",
+          "b03_p2",
+          "b03_p5",
+          "b03_p25",
+          "b03_median",
+          "b03_p75",
+          "b03_p95",
+          "b03_p98",
+          "b03_mean",
+          "b03_sd",
+          "b03_sum",
+          "b03_iqr",
+          "b03_iqr0595",
+          "b04_p2",
+          "b04_p5",
+          "b04_p25",
+          "b04_median",
+          "b04_p75",
+          "b04_p95",
+          "b04_p98",
+          "b04_mean",
+          "b04_sd",
+          "b04_sum",
+          "b04_iqr",
+          "b04_iqr0595",
+          "b05_p2",
+          "b05_p5",
+          "b05_p25",
+          "b05_median",
+          "b05_p75",
+          "b05_p95",
+          "b05_p98",
+          "b05_mean",
+          "b05_sd",
+          "b05_sum",
+          "b05_iqr",
+          "b05_iqr0595",
+          "b06_p2",
+          "b06_p5",
+          "b06_p25",
+          "b06_median",
+          "b06_p75",
+          "b06_p95",
+          "b06_p98",
+          "b06_mean",
+          "b06_sd",
+          "b06_sum",
+          "b06_iqr",
+          "b06_iqr0595",
+          "b07_p2",
+          "b07_p5",
+          "b07_p25",
+          "b07_median",
+          "b07_p75",
+          "b07_p95",
+          "b07_p98",
+          "b07_mean",
+          "b07_sd",
+          "b07_sum",
+          "b07_iqr",
+          "b07_iqr0595",
+          "b08_p2",
+          "b08_p5",
+          "b08_p25",
+          "b08_median",
+          "b08_p75",
+          "b08_p95",
+          "b08_p98",
+          "b08_mean",
+          "b08_sd",
+          "b08_sum",
+          "b08_iqr",
+          "b08_iqr0595",
+          "b8a_p2",
+          "b8a_p5",
+          "b8a_p25",
+          "b8a_median",
+          "b8a_p75",
+          "b8a_p95",
+          "b8a_p98",
+          "b8a_mean",
+          "b8a_sd",
+          "b8a_sum",
+          "b8a_iqr",
+          "b8a_iqr0595",
+          "b11_p2",
+          "b11_p5",
+          "b11_p25",
+          "b11_median",
+          "b11_p75",
+          "b11_p95",
+          "b11_p98",
+          "b11_mean",
+          "b11_sd",
+          "b11_sum",
+          "b11_iqr",
+          "b11_iqr0595",
+          "b12_p2",
+          "b12_p5",
+          "b12_p25",
+          "b12_median",
+          "b12_p75",
+          "b12_p95",
+          "b12_p98",
+          "b12_mean",
+          "b12_sd",
+          "b12_sum",
+          "b12_iqr",
+          "b12_iqr0595",
+          "abdi1_p2",
+          "abdi1_p5",
+          "abdi1_p25",
+          "abdi1_median",
+          "abdi1_p75",
+          "abdi1_p95",
+          "abdi1_p98",
+          "abdi1_mean",
+          "abdi1_sd",
+          "abdi1_sum",
+          "abdi1_iqr",
+          "abdi1_iqr0595",
+          "abdi2_p2",
+          "abdi2_p5",
+          "abdi2_p25",
+          "abdi2_median",
+          "abdi2_p75",
+          "abdi2_p95",
+          "abdi2_p98",
+          "abdi2_mean",
+          "abdi2_sd",
+          "abdi2_sum",
+          "abdi2_iqr",
+          "abdi2_iqr0595",
+          "aweinsh_p2",
+          "aweinsh_p5",
+          "aweinsh_p25",
+          "aweinsh_median",
+          "aweinsh_p75",
+          "aweinsh_p95",
+          "aweinsh_p98",
+          "aweinsh_mean",
+          "aweinsh_sd",
+          "aweinsh_sum",
+          "aweinsh_iqr",
+          "aweinsh_iqr0595",
+          "avi_p2",
+          "avi_p5",
+          "avi_p25",
+          "avi_median",
+          "avi_p75",
+          "avi_p95",
+          "avi_p98",
+          "avi_mean",
+          "avi_sd",
+          "avi_sum",
+          "avi_iqr",
+          "avi_iqr0595",
+          "blfei_p2",
+          "blfei_p5",
+          "blfei_p25",
+          "blfei_median",
+          "blfei_p75",
+          "blfei_p95",
+          "blfei_p98",
+          "blfei_mean",
+          "blfei_sd",
+          "blfei_sum",
+          "blfei_iqr",
+          "blfei_iqr0595",
+          "cire_p2",
+          "cire_p5",
+          "cire_p25",
+          "cire_median",
+          "cire_p75",
+          "cire_p95",
+          "cire_p98",
+          "cire_mean",
+          "cire_sd",
+          "cire_sum",
+          "cire_iqr",
+          "cire_iqr0595",
+          "evi_p2",
+          "evi_p5",
+          "evi_p25",
+          "evi_median",
+          "evi_p75",
+          "evi_p95",
+          "evi_p98",
+          "evi_mean",
+          "evi_sd",
+          "evi_sum",
+          "evi_iqr",
+          "evi_iqr0595",
+          "ireci_p2",
+          "ireci_p5",
+          "ireci_p25",
+          "ireci_median",
+          "ireci_p75",
+          "ireci_p95",
+          "ireci_p98",
+          "ireci_mean",
+          "ireci_sd",
+          "ireci_sum",
+          "ireci_iqr",
+          "ireci_iqr0595",
+          "mbwi_p2",
+          "mbwi_p5",
+          "mbwi_p25",
+          "mbwi_median",
+          "mbwi_p75",
+          "mbwi_p95",
+          "mbwi_p98",
+          "mbwi_mean",
+          "mbwi_sd",
+          "mbwi_sum",
+          "mbwi_iqr",
+          "mbwi_iqr0595",
+          "mndwi_p2",
+          "mndwi_p5",
+          "mndwi_p25",
+          "mndwi_median",
+          "mndwi_p75",
+          "mndwi_p95",
+          "mndwi_p98",
+          "mndwi_mean",
+          "mndwi_sd",
+          "mndwi_sum",
+          "mndwi_iqr",
+          "mndwi_iqr0595",
+          "mndvi_p2",
+          "mndvi_p5",
+          "mndvi_p25",
+          "mndvi_median",
+          "mndvi_p75",
+          "mndvi_p95",
+          "mndvi_p98",
+          "mndvi_mean",
+          "mndvi_sd",
+          "mndvi_sum",
+          "mndvi_iqr",
+          "mndvi_iqr0595",
+          "ndmi_p2",
+          "ndmi_p5",
+          "ndmi_p25",
+          "ndmi_median",
+          "ndmi_p75",
+          "ndmi_p95",
+          "ndmi_p98",
+          "ndmi_mean",
+          "ndmi_sd",
+          "ndmi_sum",
+          "ndmi_iqr",
+          "ndmi_iqr0595",
+          "ndvi_p2",
+          "ndvi_p5",
+          "ndvi_p25",
+          "ndvi_median",
+          "ndvi_p75",
+          "ndvi_p95",
+          "ndvi_p98",
+          "ndvi_mean",
+          "ndvi_sd",
+          "ndvi_sum",
+          "ndvi_iqr",
+          "ndvi_iqr0595",
+          "ndvimndwi_p2",
+          "ndvimndwi_p5",
+          "ndvimndwi_p25",
+          "ndvimndwi_median",
+          "ndvimndwi_p75",
+          "ndvimndwi_p95",
+          "ndvimndwi_p98",
+          "ndvimndwi_mean",
+          "ndvimndwi_sd",
+          "ndvimndwi_sum",
+          "ndvimndwi_iqr",
+          "ndvimndwi_iqr0595",
+          "ndwi_p2",
+          "ndwi_p5",
+          "ndwi_p25",
+          "ndwi_median",
+          "ndwi_p75",
+          "ndwi_p95",
+          "ndwi_p98",
+          "ndwi_mean",
+          "ndwi_sd",
+          "ndwi_sum",
+          "ndwi_iqr",
+          "ndwi_iqr0595",
+          "nmdi_p2",
+          "nmdi_p5",
+          "nmdi_p25",
+          "nmdi_median",
+          "nmdi_p75",
+          "nmdi_p95",
+          "nmdi_p98",
+          "nmdi_mean",
+          "nmdi_sd",
+          "nmdi_sum",
+          "nmdi_iqr",
+          "nmdi_iqr0595",
+          "nirv_p2",
+          "nirv_p5",
+          "nirv_p25",
+          "nirv_median",
+          "nirv_p75",
+          "nirv_p95",
+          "nirv_p98",
+          "nirv_mean",
+          "nirv_sd",
+          "nirv_sum",
+          "nirv_iqr",
+          "nirv_iqr0595",
+          "s2wi_p2",
+          "s2wi_p5",
+          "s2wi_p25",
+          "s2wi_median",
+          "s2wi_p75",
+          "s2wi_p95",
+          "s2wi_p98",
+          "s2wi_mean",
+          "s2wi_sd",
+          "s2wi_sum",
+          "s2wi_iqr",
+          "s2wi_iqr0595",
+          "s2rep_p2",
+          "s2rep_p5",
+          "s2rep_p25",
+          "s2rep_median",
+          "s2rep_p75",
+          "s2rep_p95",
+          "s2rep_p98",
+          "s2rep_mean",
+          "s2rep_sd",
+          "s2rep_sum",
+          "s2rep_iqr",
+          "s2rep_iqr0595",
+          "wri_p2",
+          "wri_p5",
+          "wri_p25",
+          "wri_median",
+          "wri_p75",
+          "wri_p95",
+          "wri_p98",
+          "wri_mean",
+          "wri_sd",
+          "wri_sum",
+          "wri_iqr",
+          "wri_iqr0595"
         ]
       }
     },
@@ -1791,362 +1790,362 @@
       "process_id": "filter_bands",
       "arguments": {
         "bands": [
-          "B02_p2",
-          "B02_p5",
-          "B02_p25",
-          "B02_median",
-          "B02_p75",
-          "B02_p95",
-          "B02_p98",
-          "B02_mean",
-          "B02_sd",
-          "B02_sum",
-          "B02_iqr",
-          "B02_iqr0595",
-          "B03_p2",
-          "B03_p5",
-          "B03_p25",
-          "B03_median",
-          "B03_p75",
-          "B03_p95",
-          "B03_p98",
-          "B03_mean",
-          "B03_sd",
-          "B03_sum",
-          "B03_iqr",
-          "B03_iqr0595",
-          "B04_p2",
-          "B04_p5",
-          "B04_p25",
-          "B04_median",
-          "B04_p75",
-          "B04_p95",
-          "B04_p98",
-          "B04_mean",
-          "B04_sd",
-          "B04_sum",
-          "B04_iqr",
-          "B04_iqr0595",
-          "B05_p2",
-          "B05_p5",
-          "B05_p25",
-          "B05_median",
-          "B05_p75",
-          "B05_p95",
-          "B05_p98",
-          "B05_mean",
-          "B05_sd",
-          "B05_sum",
-          "B05_iqr",
-          "B05_iqr0595",
-          "B06_p2",
-          "B06_p5",
-          "B06_p25",
-          "B06_median",
-          "B06_p75",
-          "B06_p95",
-          "B06_p98",
-          "B06_mean",
-          "B06_sd",
-          "B06_sum",
-          "B06_iqr",
-          "B06_iqr0595",
-          "B07_p2",
-          "B07_p5",
-          "B07_p25",
-          "B07_median",
-          "B07_p75",
-          "B07_p95",
-          "B07_p98",
-          "B07_mean",
-          "B07_sd",
-          "B07_sum",
-          "B07_iqr",
-          "B07_iqr0595",
-          "B08_p2",
-          "B08_p5",
-          "B08_p25",
-          "B08_median",
-          "B08_p75",
-          "B08_p95",
-          "B08_p98",
-          "B08_mean",
-          "B08_sd",
-          "B08_sum",
-          "B08_iqr",
-          "B08_iqr0595",
-          "B8A_p2",
-          "B8A_p5",
-          "B8A_p25",
-          "B8A_median",
-          "B8A_p75",
-          "B8A_p95",
-          "B8A_p98",
-          "B8A_mean",
-          "B8A_sd",
-          "B8A_sum",
-          "B8A_iqr",
-          "B8A_iqr0595",
-          "B11_p2",
-          "B11_p5",
-          "B11_p25",
-          "B11_median",
-          "B11_p75",
-          "B11_p95",
-          "B11_p98",
-          "B11_mean",
-          "B11_sd",
-          "B11_sum",
-          "B11_iqr",
-          "B11_iqr0595",
-          "B12_p2",
-          "B12_p5",
-          "B12_p25",
-          "B12_median",
-          "B12_p75",
-          "B12_p95",
-          "B12_p98",
-          "B12_mean",
-          "B12_sd",
-          "B12_sum",
-          "B12_iqr",
-          "B12_iqr0595",
-          "ABDI1_p2",
-          "ABDI1_p5",
-          "ABDI1_p25",
-          "ABDI1_median",
-          "ABDI1_p75",
-          "ABDI1_p95",
-          "ABDI1_p98",
-          "ABDI1_mean",
-          "ABDI1_sd",
-          "ABDI1_sum",
-          "ABDI1_iqr",
-          "ABDI1_iqr0595",
-          "ABDI2_p2",
-          "ABDI2_p5",
-          "ABDI2_p25",
-          "ABDI2_median",
-          "ABDI2_p75",
-          "ABDI2_p95",
-          "ABDI2_p98",
-          "ABDI2_mean",
-          "ABDI2_sd",
-          "ABDI2_sum",
-          "ABDI2_iqr",
-          "ABDI2_iqr0595",
-          "AWEInsh_p2",
-          "AWEInsh_p5",
-          "AWEInsh_p25",
-          "AWEInsh_median",
-          "AWEInsh_p75",
-          "AWEInsh_p95",
-          "AWEInsh_p98",
-          "AWEInsh_mean",
-          "AWEInsh_sd",
-          "AWEInsh_sum",
-          "AWEInsh_iqr",
-          "AWEInsh_iqr0595",
-          "AVI_p2",
-          "AVI_p5",
-          "AVI_p25",
-          "AVI_median",
-          "AVI_p75",
-          "AVI_p95",
-          "AVI_p98",
-          "AVI_mean",
-          "AVI_sd",
-          "AVI_sum",
-          "AVI_iqr",
-          "AVI_iqr0595",
-          "BLFEI_p2",
-          "BLFEI_p5",
-          "BLFEI_p25",
-          "BLFEI_median",
-          "BLFEI_p75",
-          "BLFEI_p95",
-          "BLFEI_p98",
-          "BLFEI_mean",
-          "BLFEI_sd",
-          "BLFEI_sum",
-          "BLFEI_iqr",
-          "BLFEI_iqr0595",
-          "CIRE_p2",
-          "CIRE_p5",
-          "CIRE_p25",
-          "CIRE_median",
-          "CIRE_p75",
-          "CIRE_p95",
-          "CIRE_p98",
-          "CIRE_mean",
-          "CIRE_sd",
-          "CIRE_sum",
-          "CIRE_iqr",
-          "CIRE_iqr0595",
-          "EVI_p2",
-          "EVI_p5",
-          "EVI_p25",
-          "EVI_median",
-          "EVI_p75",
-          "EVI_p95",
-          "EVI_p98",
-          "EVI_mean",
-          "EVI_sd",
-          "EVI_sum",
-          "EVI_iqr",
-          "EVI_iqr0595",
-          "IRECI_p2",
-          "IRECI_p5",
-          "IRECI_p25",
-          "IRECI_median",
-          "IRECI_p75",
-          "IRECI_p95",
-          "IRECI_p98",
-          "IRECI_mean",
-          "IRECI_sd",
-          "IRECI_sum",
-          "IRECI_iqr",
-          "IRECI_iqr0595",
-          "MBWI_p2",
-          "MBWI_p5",
-          "MBWI_p25",
-          "MBWI_median",
-          "MBWI_p75",
-          "MBWI_p95",
-          "MBWI_p98",
-          "MBWI_mean",
-          "MBWI_sd",
-          "MBWI_sum",
-          "MBWI_iqr",
-          "MBWI_iqr0595",
-          "MNDWI_p2",
-          "MNDWI_p5",
-          "MNDWI_p25",
-          "MNDWI_median",
-          "MNDWI_p75",
-          "MNDWI_p95",
-          "MNDWI_p98",
-          "MNDWI_mean",
-          "MNDWI_sd",
-          "MNDWI_sum",
-          "MNDWI_iqr",
-          "MNDWI_iqr0595",
-          "MNDVI_p2",
-          "MNDVI_p5",
-          "MNDVI_p25",
-          "MNDVI_median",
-          "MNDVI_p75",
-          "MNDVI_p95",
-          "MNDVI_p98",
-          "MNDVI_mean",
-          "MNDVI_sd",
-          "MNDVI_sum",
-          "MNDVI_iqr",
-          "MNDVI_iqr0595",
-          "NDMI_p2",
-          "NDMI_p5",
-          "NDMI_p25",
-          "NDMI_median",
-          "NDMI_p75",
-          "NDMI_p95",
-          "NDMI_p98",
-          "NDMI_mean",
-          "NDMI_sd",
-          "NDMI_sum",
-          "NDMI_iqr",
-          "NDMI_iqr0595",
-          "NDVI_p2",
-          "NDVI_p5",
-          "NDVI_p25",
-          "NDVI_median",
-          "NDVI_p75",
-          "NDVI_p95",
-          "NDVI_p98",
-          "NDVI_mean",
-          "NDVI_sd",
-          "NDVI_sum",
-          "NDVI_iqr",
-          "NDVI_iqr0595",
-          "NDVIMNDWI_p2",
-          "NDVIMNDWI_p5",
-          "NDVIMNDWI_p25",
-          "NDVIMNDWI_median",
-          "NDVIMNDWI_p75",
-          "NDVIMNDWI_p95",
-          "NDVIMNDWI_p98",
-          "NDVIMNDWI_mean",
-          "NDVIMNDWI_sd",
-          "NDVIMNDWI_sum",
-          "NDVIMNDWI_iqr",
-          "NDVIMNDWI_iqr0595",
-          "NDWI_p2",
-          "NDWI_p5",
-          "NDWI_p25",
-          "NDWI_median",
-          "NDWI_p75",
-          "NDWI_p95",
-          "NDWI_p98",
-          "NDWI_mean",
-          "NDWI_sd",
-          "NDWI_sum",
-          "NDWI_iqr",
-          "NDWI_iqr0595",
-          "NMDI_p2",
-          "NMDI_p5",
-          "NMDI_p25",
-          "NMDI_median",
-          "NMDI_p75",
-          "NMDI_p95",
-          "NMDI_p98",
-          "NMDI_mean",
-          "NMDI_sd",
-          "NMDI_sum",
-          "NMDI_iqr",
-          "NMDI_iqr0595",
-          "NIRv_p2",
-          "NIRv_p5",
-          "NIRv_p25",
-          "NIRv_median",
-          "NIRv_p75",
-          "NIRv_p95",
-          "NIRv_p98",
-          "NIRv_mean",
-          "NIRv_sd",
-          "NIRv_sum",
-          "NIRv_iqr",
-          "NIRv_iqr0595",
-          "S2WI_p2",
-          "S2WI_p5",
-          "S2WI_p25",
-          "S2WI_median",
-          "S2WI_p75",
-          "S2WI_p95",
-          "S2WI_p98",
-          "S2WI_mean",
-          "S2WI_sd",
-          "S2WI_sum",
-          "S2WI_iqr",
-          "S2WI_iqr0595",
-          "S2REP_p2",
-          "S2REP_p5",
-          "S2REP_p25",
-          "S2REP_median",
-          "S2REP_p75",
-          "S2REP_p95",
-          "S2REP_p98",
-          "S2REP_mean",
-          "WRI_p2",
-          "WRI_p5",
-          "WRI_p25",
-          "WRI_median",
-          "WRI_p75",
-          "WRI_p95",
-          "WRI_p98",
-          "WRI_mean",
-          "WRI_sd",
-          "WRI_sum",
-          "WRI_iqr",
-          "WRI_iqr0595"
+          "b02_p2",
+          "b02_p5",
+          "b02_p25",
+          "b02_median",
+          "b02_p75",
+          "b02_p95",
+          "b02_p98",
+          "b02_mean",
+          "b02_sd",
+          "b02_sum",
+          "b02_iqr",
+          "b02_iqr0595",
+          "b03_p2",
+          "b03_p5",
+          "b03_p25",
+          "b03_median",
+          "b03_p75",
+          "b03_p95",
+          "b03_p98",
+          "b03_mean",
+          "b03_sd",
+          "b03_sum",
+          "b03_iqr",
+          "b03_iqr0595",
+          "b04_p2",
+          "b04_p5",
+          "b04_p25",
+          "b04_median",
+          "b04_p75",
+          "b04_p95",
+          "b04_p98",
+          "b04_mean",
+          "b04_sd",
+          "b04_sum",
+          "b04_iqr",
+          "b04_iqr0595",
+          "b05_p2",
+          "b05_p5",
+          "b05_p25",
+          "b05_median",
+          "b05_p75",
+          "b05_p95",
+          "b05_p98",
+          "b05_mean",
+          "b05_sd",
+          "b05_sum",
+          "b05_iqr",
+          "b05_iqr0595",
+          "b06_p2",
+          "b06_p5",
+          "b06_p25",
+          "b06_median",
+          "b06_p75",
+          "b06_p95",
+          "b06_p98",
+          "b06_mean",
+          "b06_sd",
+          "b06_sum",
+          "b06_iqr",
+          "b06_iqr0595",
+          "b07_p2",
+          "b07_p5",
+          "b07_p25",
+          "b07_median",
+          "b07_p75",
+          "b07_p95",
+          "b07_p98",
+          "b07_mean",
+          "b07_sd",
+          "b07_sum",
+          "b07_iqr",
+          "b07_iqr0595",
+          "b08_p2",
+          "b08_p5",
+          "b08_p25",
+          "b08_median",
+          "b08_p75",
+          "b08_p95",
+          "b08_p98",
+          "b08_mean",
+          "b08_sd",
+          "b08_sum",
+          "b08_iqr",
+          "b08_iqr0595",
+          "b8a_p2",
+          "b8a_p5",
+          "b8a_p25",
+          "b8a_median",
+          "b8a_p75",
+          "b8a_p95",
+          "b8a_p98",
+          "b8a_mean",
+          "b8a_sd",
+          "b8a_sum",
+          "b8a_iqr",
+          "b8a_iqr0595",
+          "b11_p2",
+          "b11_p5",
+          "b11_p25",
+          "b11_median",
+          "b11_p75",
+          "b11_p95",
+          "b11_p98",
+          "b11_mean",
+          "b11_sd",
+          "b11_sum",
+          "b11_iqr",
+          "b11_iqr0595",
+          "b12_p2",
+          "b12_p5",
+          "b12_p25",
+          "b12_median",
+          "b12_p75",
+          "b12_p95",
+          "b12_p98",
+          "b12_mean",
+          "b12_sd",
+          "b12_sum",
+          "b12_iqr",
+          "b12_iqr0595",
+          "abdi1_p2",
+          "abdi1_p5",
+          "abdi1_p25",
+          "abdi1_median",
+          "abdi1_p75",
+          "abdi1_p95",
+          "abdi1_p98",
+          "abdi1_mean",
+          "abdi1_sd",
+          "abdi1_sum",
+          "abdi1_iqr",
+          "abdi1_iqr0595",
+          "abdi2_p2",
+          "abdi2_p5",
+          "abdi2_p25",
+          "abdi2_median",
+          "abdi2_p75",
+          "abdi2_p95",
+          "abdi2_p98",
+          "abdi2_mean",
+          "abdi2_sd",
+          "abdi2_sum",
+          "abdi2_iqr",
+          "abdi2_iqr0595",
+          "aweinsh_p2",
+          "aweinsh_p5",
+          "aweinsh_p25",
+          "aweinsh_median",
+          "aweinsh_p75",
+          "aweinsh_p95",
+          "aweinsh_p98",
+          "aweinsh_mean",
+          "aweinsh_sd",
+          "aweinsh_sum",
+          "aweinsh_iqr",
+          "aweinsh_iqr0595",
+          "avi_p2",
+          "avi_p5",
+          "avi_p25",
+          "avi_median",
+          "avi_p75",
+          "avi_p95",
+          "avi_p98",
+          "avi_mean",
+          "avi_sd",
+          "avi_sum",
+          "avi_iqr",
+          "avi_iqr0595",
+          "blfei_p2",
+          "blfei_p5",
+          "blfei_p25",
+          "blfei_median",
+          "blfei_p75",
+          "blfei_p95",
+          "blfei_p98",
+          "blfei_mean",
+          "blfei_sd",
+          "blfei_sum",
+          "blfei_iqr",
+          "blfei_iqr0595",
+          "cire_p2",
+          "cire_p5",
+          "cire_p25",
+          "cire_median",
+          "cire_p75",
+          "cire_p95",
+          "cire_p98",
+          "cire_mean",
+          "cire_sd",
+          "cire_sum",
+          "cire_iqr",
+          "cire_iqr0595",
+          "evi_p2",
+          "evi_p5",
+          "evi_p25",
+          "evi_median",
+          "evi_p75",
+          "evi_p95",
+          "evi_p98",
+          "evi_mean",
+          "evi_sd",
+          "evi_sum",
+          "evi_iqr",
+          "evi_iqr0595",
+          "ireci_p2",
+          "ireci_p5",
+          "ireci_p25",
+          "ireci_median",
+          "ireci_p75",
+          "ireci_p95",
+          "ireci_p98",
+          "ireci_mean",
+          "ireci_sd",
+          "ireci_sum",
+          "ireci_iqr",
+          "ireci_iqr0595",
+          "mbwi_p2",
+          "mbwi_p5",
+          "mbwi_p25",
+          "mbwi_median",
+          "mbwi_p75",
+          "mbwi_p95",
+          "mbwi_p98",
+          "mbwi_mean",
+          "mbwi_sd",
+          "mbwi_sum",
+          "mbwi_iqr",
+          "mbwi_iqr0595",
+          "mndwi_p2",
+          "mndwi_p5",
+          "mndwi_p25",
+          "mndwi_median",
+          "mndwi_p75",
+          "mndwi_p95",
+          "mndwi_p98",
+          "mndwi_mean",
+          "mndwi_sd",
+          "mndwi_sum",
+          "mndwi_iqr",
+          "mndwi_iqr0595",
+          "mndvi_p2",
+          "mndvi_p5",
+          "mndvi_p25",
+          "mndvi_median",
+          "mndvi_p75",
+          "mndvi_p95",
+          "mndvi_p98",
+          "mndvi_mean",
+          "mndvi_sd",
+          "mndvi_sum",
+          "mndvi_iqr",
+          "mndvi_iqr0595",
+          "ndmi_p2",
+          "ndmi_p5",
+          "ndmi_p25",
+          "ndmi_median",
+          "ndmi_p75",
+          "ndmi_p95",
+          "ndmi_p98",
+          "ndmi_mean",
+          "ndmi_sd",
+          "ndmi_sum",
+          "ndmi_iqr",
+          "ndmi_iqr0595",
+          "ndvi_p2",
+          "ndvi_p5",
+          "ndvi_p25",
+          "ndvi_median",
+          "ndvi_p75",
+          "ndvi_p95",
+          "ndvi_p98",
+          "ndvi_mean",
+          "ndvi_sd",
+          "ndvi_sum",
+          "ndvi_iqr",
+          "ndvi_iqr0595",
+          "ndvimndwi_p2",
+          "ndvimndwi_p5",
+          "ndvimndwi_p25",
+          "ndvimndwi_median",
+          "ndvimndwi_p75",
+          "ndvimndwi_p95",
+          "ndvimndwi_p98",
+          "ndvimndwi_mean",
+          "ndvimndwi_sd",
+          "ndvimndwi_sum",
+          "ndvimndwi_iqr",
+          "ndvimndwi_iqr0595",
+          "ndwi_p2",
+          "ndwi_p5",
+          "ndwi_p25",
+          "ndwi_median",
+          "ndwi_p75",
+          "ndwi_p95",
+          "ndwi_p98",
+          "ndwi_mean",
+          "ndwi_sd",
+          "ndwi_sum",
+          "ndwi_iqr",
+          "ndwi_iqr0595",
+          "nmdi_p2",
+          "nmdi_p5",
+          "nmdi_p25",
+          "nmdi_median",
+          "nmdi_p75",
+          "nmdi_p95",
+          "nmdi_p98",
+          "nmdi_mean",
+          "nmdi_sd",
+          "nmdi_sum",
+          "nmdi_iqr",
+          "nmdi_iqr0595",
+          "nirv_p2",
+          "nirv_p5",
+          "nirv_p25",
+          "nirv_median",
+          "nirv_p75",
+          "nirv_p95",
+          "nirv_p98",
+          "nirv_mean",
+          "nirv_sd",
+          "nirv_sum",
+          "nirv_iqr",
+          "nirv_iqr0595",
+          "s2wi_p2",
+          "s2wi_p5",
+          "s2wi_p25",
+          "s2wi_median",
+          "s2wi_p75",
+          "s2wi_p95",
+          "s2wi_p98",
+          "s2wi_mean",
+          "s2wi_sd",
+          "s2wi_sum",
+          "s2wi_iqr",
+          "s2wi_iqr0595",
+          "s2rep_p2",
+          "s2rep_p5",
+          "s2rep_p25",
+          "s2rep_median",
+          "s2rep_p75",
+          "s2rep_p95",
+          "s2rep_p98",
+          "s2rep_mean",
+          "wri_p2",
+          "wri_p5",
+          "wri_p25",
+          "wri_median",
+          "wri_p75",
+          "wri_p95",
+          "wri_p98",
+          "wri_mean",
+          "wri_sd",
+          "wri_sum",
+          "wri_iqr",
+          "wri_iqr0595"
         ],
         "data": {
           "from_node": "renamelabels2"
diff --git a/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference.json b/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference.json
index d04e877..9b88482 100644
--- a/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference.json
+++ b/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference.json
@@ -1265,6 +1265,893 @@
         ]
       }
     },
+    "applydimension2": {
+      "process_id": "apply_dimension",
+      "arguments": {
+        "context": {
+          "TileSize": 128
+        },
+        "data": {
+          "from_node": "renamelabels1"
+        },
+        "dimension": "t",
+        "process": {
+          "process_graph": {
+            "quantiles1": {
+              "process_id": "quantiles",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                },
+                "probabilities": [
+                  0.02,
+                  0.05,
+                  0.25,
+                  0.5,
+                  0.75,
+                  0.95,
+                  0.98
+                ]
+              }
+            },
+            "mean1": {
+              "process_id": "mean",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                }
+              }
+            },
+            "sd1": {
+              "process_id": "sd",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                }
+              }
+            },
+            "sum1": {
+              "process_id": "sum",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                }
+              }
+            },
+            "quantiles2": {
+              "process_id": "quantiles",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                },
+                "probabilities": [
+                  0.75
+                ]
+              }
+            },
+            "quantiles3": {
+              "process_id": "quantiles",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                },
+                "probabilities": [
+                  0.25
+                ]
+              }
+            },
+            "subtract31": {
+              "process_id": "subtract",
+              "arguments": {
+                "x": {
+                  "from_node": "quantiles2"
+                },
+                "y": {
+                  "from_node": "quantiles3"
+                }
+              }
+            },
+            "quantiles4": {
+              "process_id": "quantiles",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                },
+                "probabilities": [
+                  0.95
+                ]
+              }
+            },
+            "quantiles5": {
+              "process_id": "quantiles",
+              "arguments": {
+                "data": {
+                  "from_parameter": "data"
+                },
+                "probabilities": [
+                  0.05
+                ]
+              }
+            },
+            "subtract32": {
+              "process_id": "subtract",
+              "arguments": {
+                "x": {
+                  "from_node": "quantiles4"
+                },
+                "y": {
+                  "from_node": "quantiles5"
+                }
+              }
+            },
+            "arrayconcat1": {
+              "process_id": "array_concat",
+              "arguments": {
+                "array1": {
+                  "from_node": "quantiles1"
+                },
+                "array2": [
+                  {
+                    "from_node": "mean1"
+                  },
+                  {
+                    "from_node": "sd1"
+                  },
+                  {
+                    "from_node": "sum1"
+                  },
+                  {
+                    "from_node": "subtract31"
+                  },
+                  {
+                    "from_node": "subtract32"
+                  }
+                ]
+              },
+              "result": true
+            }
+          }
+        },
+        "target_dimension": "bands"
+      }
+    },
+    "renamelabels2": {
+      "process_id": "rename_labels",
+      "arguments": {
+        "data": {
+          "from_node": "applydimension2"
+        },
+        "dimension": "bands",
+        "target": [
+          "b02_p2",
+          "b02_p5",
+          "b02_p25",
+          "b02_median",
+          "b02_p75",
+          "b02_p95",
+          "b02_p98",
+          "b02_mean",
+          "b02_sd",
+          "b02_sum",
+          "b02_iqr",
+          "b02_iqr0595",
+          "b03_p2",
+          "b03_p5",
+          "b03_p25",
+          "b03_median",
+          "b03_p75",
+          "b03_p95",
+          "b03_p98",
+          "b03_mean",
+          "b03_sd",
+          "b03_sum",
+          "b03_iqr",
+          "b03_iqr0595",
+          "b04_p2",
+          "b04_p5",
+          "b04_p25",
+          "b04_median",
+          "b04_p75",
+          "b04_p95",
+          "b04_p98",
+          "b04_mean",
+          "b04_sd",
+          "b04_sum",
+          "b04_iqr",
+          "b04_iqr0595",
+          "b05_p2",
+          "b05_p5",
+          "b05_p25",
+          "b05_median",
+          "b05_p75",
+          "b05_p95",
+          "b05_p98",
+          "b05_mean",
+          "b05_sd",
+          "b05_sum",
+          "b05_iqr",
+          "b05_iqr0595",
+          "b06_p2",
+          "b06_p5",
+          "b06_p25",
+          "b06_median",
+          "b06_p75",
+          "b06_p95",
+          "b06_p98",
+          "b06_mean",
+          "b06_sd",
+          "b06_sum",
+          "b06_iqr",
+          "b06_iqr0595",
+          "b07_p2",
+          "b07_p5",
+          "b07_p25",
+          "b07_median",
+          "b07_p75",
+          "b07_p95",
+          "b07_p98",
+          "b07_mean",
+          "b07_sd",
+          "b07_sum",
+          "b07_iqr",
+          "b07_iqr0595",
+          "b08_p2",
+          "b08_p5",
+          "b08_p25",
+          "b08_median",
+          "b08_p75",
+          "b08_p95",
+          "b08_p98",
+          "b08_mean",
+          "b08_sd",
+          "b08_sum",
+          "b08_iqr",
+          "b08_iqr0595",
+          "b8a_p2",
+          "b8a_p5",
+          "b8a_p25",
+          "b8a_median",
+          "b8a_p75",
+          "b8a_p95",
+          "b8a_p98",
+          "b8a_mean",
+          "b8a_sd",
+          "b8a_sum",
+          "b8a_iqr",
+          "b8a_iqr0595",
+          "b11_p2",
+          "b11_p5",
+          "b11_p25",
+          "b11_median",
+          "b11_p75",
+          "b11_p95",
+          "b11_p98",
+          "b11_mean",
+          "b11_sd",
+          "b11_sum",
+          "b11_iqr",
+          "b11_iqr0595",
+          "b12_p2",
+          "b12_p5",
+          "b12_p25",
+          "b12_median",
+          "b12_p75",
+          "b12_p95",
+          "b12_p98",
+          "b12_mean",
+          "b12_sd",
+          "b12_sum",
+          "b12_iqr",
+          "b12_iqr0595",
+          "abdi1_p2",
+          "abdi1_p5",
+          "abdi1_p25",
+          "abdi1_median",
+          "abdi1_p75",
+          "abdi1_p95",
+          "abdi1_p98",
+          "abdi1_mean",
+          "abdi1_sd",
+          "abdi1_sum",
+          "abdi1_iqr",
+          "abdi1_iqr0595",
+          "abdi2_p2",
+          "abdi2_p5",
+          "abdi2_p25",
+          "abdi2_median",
+          "abdi2_p75",
+          "abdi2_p95",
+          "abdi2_p98",
+          "abdi2_mean",
+          "abdi2_sd",
+          "abdi2_sum",
+          "abdi2_iqr",
+          "abdi2_iqr0595",
+          "aweinsh_p2",
+          "aweinsh_p5",
+          "aweinsh_p25",
+          "aweinsh_median",
+          "aweinsh_p75",
+          "aweinsh_p95",
+          "aweinsh_p98",
+          "aweinsh_mean",
+          "aweinsh_sd",
+          "aweinsh_sum",
+          "aweinsh_iqr",
+          "aweinsh_iqr0595",
+          "avi_p2",
+          "avi_p5",
+          "avi_p25",
+          "avi_median",
+          "avi_p75",
+          "avi_p95",
+          "avi_p98",
+          "avi_mean",
+          "avi_sd",
+          "avi_sum",
+          "avi_iqr",
+          "avi_iqr0595",
+          "blfei_p2",
+          "blfei_p5",
+          "blfei_p25",
+          "blfei_median",
+          "blfei_p75",
+          "blfei_p95",
+          "blfei_p98",
+          "blfei_mean",
+          "blfei_sd",
+          "blfei_sum",
+          "blfei_iqr",
+          "blfei_iqr0595",
+          "cire_p2",
+          "cire_p5",
+          "cire_p25",
+          "cire_median",
+          "cire_p75",
+          "cire_p95",
+          "cire_p98",
+          "cire_mean",
+          "cire_sd",
+          "cire_sum",
+          "cire_iqr",
+          "cire_iqr0595",
+          "evi_p2",
+          "evi_p5",
+          "evi_p25",
+          "evi_median",
+          "evi_p75",
+          "evi_p95",
+          "evi_p98",
+          "evi_mean",
+          "evi_sd",
+          "evi_sum",
+          "evi_iqr",
+          "evi_iqr0595",
+          "ireci_p2",
+          "ireci_p5",
+          "ireci_p25",
+          "ireci_median",
+          "ireci_p75",
+          "ireci_p95",
+          "ireci_p98",
+          "ireci_mean",
+          "ireci_sd",
+          "ireci_sum",
+          "ireci_iqr",
+          "ireci_iqr0595",
+          "mbwi_p2",
+          "mbwi_p5",
+          "mbwi_p25",
+          "mbwi_median",
+          "mbwi_p75",
+          "mbwi_p95",
+          "mbwi_p98",
+          "mbwi_mean",
+          "mbwi_sd",
+          "mbwi_sum",
+          "mbwi_iqr",
+          "mbwi_iqr0595",
+          "mndwi_p2",
+          "mndwi_p5",
+          "mndwi_p25",
+          "mndwi_median",
+          "mndwi_p75",
+          "mndwi_p95",
+          "mndwi_p98",
+          "mndwi_mean",
+          "mndwi_sd",
+          "mndwi_sum",
+          "mndwi_iqr",
+          "mndwi_iqr0595",
+          "mndvi_p2",
+          "mndvi_p5",
+          "mndvi_p25",
+          "mndvi_median",
+          "mndvi_p75",
+          "mndvi_p95",
+          "mndvi_p98",
+          "mndvi_mean",
+          "mndvi_sd",
+          "mndvi_sum",
+          "mndvi_iqr",
+          "mndvi_iqr0595",
+          "ndmi_p2",
+          "ndmi_p5",
+          "ndmi_p25",
+          "ndmi_median",
+          "ndmi_p75",
+          "ndmi_p95",
+          "ndmi_p98",
+          "ndmi_mean",
+          "ndmi_sd",
+          "ndmi_sum",
+          "ndmi_iqr",
+          "ndmi_iqr0595",
+          "ndvi_p2",
+          "ndvi_p5",
+          "ndvi_p25",
+          "ndvi_median",
+          "ndvi_p75",
+          "ndvi_p95",
+          "ndvi_p98",
+          "ndvi_mean",
+          "ndvi_sd",
+          "ndvi_sum",
+          "ndvi_iqr",
+          "ndvi_iqr0595",
+          "ndvimndwi_p2",
+          "ndvimndwi_p5",
+          "ndvimndwi_p25",
+          "ndvimndwi_median",
+          "ndvimndwi_p75",
+          "ndvimndwi_p95",
+          "ndvimndwi_p98",
+          "ndvimndwi_mean",
+          "ndvimndwi_sd",
+          "ndvimndwi_sum",
+          "ndvimndwi_iqr",
+          "ndvimndwi_iqr0595",
+          "ndwi_p2",
+          "ndwi_p5",
+          "ndwi_p25",
+          "ndwi_median",
+          "ndwi_p75",
+          "ndwi_p95",
+          "ndwi_p98",
+          "ndwi_mean",
+          "ndwi_sd",
+          "ndwi_sum",
+          "ndwi_iqr",
+          "ndwi_iqr0595",
+          "nmdi_p2",
+          "nmdi_p5",
+          "nmdi_p25",
+          "nmdi_median",
+          "nmdi_p75",
+          "nmdi_p95",
+          "nmdi_p98",
+          "nmdi_mean",
+          "nmdi_sd",
+          "nmdi_sum",
+          "nmdi_iqr",
+          "nmdi_iqr0595",
+          "nirv_p2",
+          "nirv_p5",
+          "nirv_p25",
+          "nirv_median",
+          "nirv_p75",
+          "nirv_p95",
+          "nirv_p98",
+          "nirv_mean",
+          "nirv_sd",
+          "nirv_sum",
+          "nirv_iqr",
+          "nirv_iqr0595",
+          "s2wi_p2",
+          "s2wi_p5",
+          "s2wi_p25",
+          "s2wi_median",
+          "s2wi_p75",
+          "s2wi_p95",
+          "s2wi_p98",
+          "s2wi_mean",
+          "s2wi_sd",
+          "s2wi_sum",
+          "s2wi_iqr",
+          "s2wi_iqr0595",
+          "s2rep_p2",
+          "s2rep_p5",
+          "s2rep_p25",
+          "s2rep_median",
+          "s2rep_p75",
+          "s2rep_p95",
+          "s2rep_p98",
+          "s2rep_mean",
+          "s2rep_sd",
+          "s2rep_sum",
+          "s2rep_iqr",
+          "s2rep_iqr0595",
+          "wri_p2",
+          "wri_p5",
+          "wri_p25",
+          "wri_median",
+          "wri_p75",
+          "wri_p95",
+          "wri_p98",
+          "wri_mean",
+          "wri_sd",
+          "wri_sum",
+          "wri_iqr",
+          "wri_iqr0595"
+        ]
+      }
+    },
+    "filterbands1": {
+      "process_id": "filter_bands",
+      "arguments": {
+        "bands": [
+          "b02_p2",
+          "b02_p5",
+          "b02_p25",
+          "b02_median",
+          "b02_p75",
+          "b02_p95",
+          "b02_p98",
+          "b02_mean",
+          "b02_sd",
+          "b02_sum",
+          "b02_iqr",
+          "b02_iqr0595",
+          "b03_p2",
+          "b03_p5",
+          "b03_p25",
+          "b03_median",
+          "b03_p75",
+          "b03_p95",
+          "b03_p98",
+          "b03_mean",
+          "b03_sd",
+          "b03_sum",
+          "b03_iqr",
+          "b03_iqr0595",
+          "b04_p2",
+          "b04_p5",
+          "b04_p25",
+          "b04_median",
+          "b04_p75",
+          "b04_p95",
+          "b04_p98",
+          "b04_mean",
+          "b04_sd",
+          "b04_sum",
+          "b04_iqr",
+          "b04_iqr0595",
+          "b05_p2",
+          "b05_p5",
+          "b05_p25",
+          "b05_median",
+          "b05_p75",
+          "b05_p95",
+          "b05_p98",
+          "b05_mean",
+          "b05_sd",
+          "b05_sum",
+          "b05_iqr",
+          "b05_iqr0595",
+          "b06_p2",
+          "b06_p5",
+          "b06_p25",
+          "b06_median",
+          "b06_p75",
+          "b06_p95",
+          "b06_p98",
+          "b06_mean",
+          "b06_sd",
+          "b06_sum",
+          "b06_iqr",
+          "b06_iqr0595",
+          "b07_p2",
+          "b07_p5",
+          "b07_p25",
+          "b07_median",
+          "b07_p75",
+          "b07_p95",
+          "b07_p98",
+          "b07_mean",
+          "b07_sd",
+          "b07_sum",
+          "b07_iqr",
+          "b07_iqr0595",
+          "b08_p2",
+          "b08_p5",
+          "b08_p25",
+          "b08_median",
+          "b08_p75",
+          "b08_p95",
+          "b08_p98",
+          "b08_mean",
+          "b08_sd",
+          "b08_sum",
+          "b08_iqr",
+          "b08_iqr0595",
+          "b8a_p2",
+          "b8a_p5",
+          "b8a_p25",
+          "b8a_median",
+          "b8a_p75",
+          "b8a_p95",
+          "b8a_p98",
+          "b8a_mean",
+          "b8a_sd",
+          "b8a_sum",
+          "b8a_iqr",
+          "b8a_iqr0595",
+          "b11_p2",
+          "b11_p5",
+          "b11_p25",
+          "b11_median",
+          "b11_p75",
+          "b11_p95",
+          "b11_p98",
+          "b11_mean",
+          "b11_sd",
+          "b11_sum",
+          "b11_iqr",
+          "b11_iqr0595",
+          "b12_p2",
+          "b12_p5",
+          "b12_p25",
+          "b12_median",
+          "b12_p75",
+          "b12_p95",
+          "b12_p98",
+          "b12_mean",
+          "b12_sd",
+          "b12_sum",
+          "b12_iqr",
+          "b12_iqr0595",
+          "abdi1_p2",
+          "abdi1_p5",
+          "abdi1_p25",
+          "abdi1_median",
+          "abdi1_p75",
+          "abdi1_p95",
+          "abdi1_p98",
+          "abdi1_mean",
+          "abdi1_sd",
+          "abdi1_sum",
+          "abdi1_iqr",
+          "abdi1_iqr0595",
+          "abdi2_p2",
+          "abdi2_p5",
+          "abdi2_p25",
+          "abdi2_median",
+          "abdi2_p75",
+          "abdi2_p95",
+          "abdi2_p98",
+          "abdi2_mean",
+          "abdi2_sd",
+          "abdi2_sum",
+          "abdi2_iqr",
+          "abdi2_iqr0595",
+          "aweinsh_p2",
+          "aweinsh_p5",
+          "aweinsh_p25",
+          "aweinsh_median",
+          "aweinsh_p75",
+          "aweinsh_p95",
+          "aweinsh_p98",
+          "aweinsh_mean",
+          "aweinsh_sd",
+          "aweinsh_sum",
+          "aweinsh_iqr",
+          "aweinsh_iqr0595",
+          "avi_p2",
+          "avi_p5",
+          "avi_p25",
+          "avi_median",
+          "avi_p75",
+          "avi_p95",
+          "avi_p98",
+          "avi_mean",
+          "avi_sd",
+          "avi_sum",
+          "avi_iqr",
+          "avi_iqr0595",
+          "blfei_p2",
+          "blfei_p5",
+          "blfei_p25",
+          "blfei_median",
+          "blfei_p75",
+          "blfei_p95",
+          "blfei_p98",
+          "blfei_mean",
+          "blfei_sd",
+          "blfei_sum",
+          "blfei_iqr",
+          "blfei_iqr0595",
+          "cire_p2",
+          "cire_p5",
+          "cire_p25",
+          "cire_median",
+          "cire_p75",
+          "cire_p95",
+          "cire_p98",
+          "cire_mean",
+          "cire_sd",
+          "cire_sum",
+          "cire_iqr",
+          "cire_iqr0595",
+          "evi_p2",
+          "evi_p5",
+          "evi_p25",
+          "evi_median",
+          "evi_p75",
+          "evi_p95",
+          "evi_p98",
+          "evi_mean",
+          "evi_sd",
+          "evi_sum",
+          "evi_iqr",
+          "evi_iqr0595",
+          "ireci_p2",
+          "ireci_p5",
+          "ireci_p25",
+          "ireci_median",
+          "ireci_p75",
+          "ireci_p95",
+          "ireci_p98",
+          "ireci_mean",
+          "ireci_sd",
+          "ireci_sum",
+          "ireci_iqr",
+          "ireci_iqr0595",
+          "mbwi_p2",
+          "mbwi_p5",
+          "mbwi_p25",
+          "mbwi_median",
+          "mbwi_p75",
+          "mbwi_p95",
+          "mbwi_p98",
+          "mbwi_mean",
+          "mbwi_sd",
+          "mbwi_sum",
+          "mbwi_iqr",
+          "mbwi_iqr0595",
+          "mndwi_p2",
+          "mndwi_p5",
+          "mndwi_p25",
+          "mndwi_median",
+          "mndwi_p75",
+          "mndwi_p95",
+          "mndwi_p98",
+          "mndwi_mean",
+          "mndwi_sd",
+          "mndwi_sum",
+          "mndwi_iqr",
+          "mndwi_iqr0595",
+          "mndvi_p2",
+          "mndvi_p5",
+          "mndvi_p25",
+          "mndvi_median",
+          "mndvi_p75",
+          "mndvi_p95",
+          "mndvi_p98",
+          "mndvi_mean",
+          "mndvi_sd",
+          "mndvi_sum",
+          "mndvi_iqr",
+          "mndvi_iqr0595",
+          "ndmi_p2",
+          "ndmi_p5",
+          "ndmi_p25",
+          "ndmi_median",
+          "ndmi_p75",
+          "ndmi_p95",
+          "ndmi_p98",
+          "ndmi_mean",
+          "ndmi_sd",
+          "ndmi_sum",
+          "ndmi_iqr",
+          "ndmi_iqr0595",
+          "ndvi_p2",
+          "ndvi_p5",
+          "ndvi_p25",
+          "ndvi_median",
+          "ndvi_p75",
+          "ndvi_p95",
+          "ndvi_p98",
+          "ndvi_mean",
+          "ndvi_sd",
+          "ndvi_sum",
+          "ndvi_iqr",
+          "ndvi_iqr0595",
+          "ndvimndwi_p2",
+          "ndvimndwi_p5",
+          "ndvimndwi_p25",
+          "ndvimndwi_median",
+          "ndvimndwi_p75",
+          "ndvimndwi_p95",
+          "ndvimndwi_p98",
+          "ndvimndwi_mean",
+          "ndvimndwi_sd",
+          "ndvimndwi_sum",
+          "ndvimndwi_iqr",
+          "ndvimndwi_iqr0595",
+          "ndwi_p2",
+          "ndwi_p5",
+          "ndwi_p25",
+          "ndwi_median",
+          "ndwi_p75",
+          "ndwi_p95",
+          "ndwi_p98",
+          "ndwi_mean",
+          "ndwi_sd",
+          "ndwi_sum",
+          "ndwi_iqr",
+          "ndwi_iqr0595",
+          "nmdi_p2",
+          "nmdi_p5",
+          "nmdi_p25",
+          "nmdi_median",
+          "nmdi_p75",
+          "nmdi_p95",
+          "nmdi_p98",
+          "nmdi_mean",
+          "nmdi_sd",
+          "nmdi_sum",
+          "nmdi_iqr",
+          "nmdi_iqr0595",
+          "nirv_p2",
+          "nirv_p5",
+          "nirv_p25",
+          "nirv_median",
+          "nirv_p75",
+          "nirv_p95",
+          "nirv_p98",
+          "nirv_mean",
+          "nirv_sd",
+          "nirv_sum",
+          "nirv_iqr",
+          "nirv_iqr0595",
+          "s2wi_p2",
+          "s2wi_p5",
+          "s2wi_p25",
+          "s2wi_median",
+          "s2wi_p75",
+          "s2wi_p95",
+          "s2wi_p98",
+          "s2wi_mean",
+          "s2wi_sd",
+          "s2wi_sum",
+          "s2wi_iqr",
+          "s2wi_iqr0595",
+          "s2rep_p2",
+          "s2rep_p5",
+          "s2rep_p25",
+          "s2rep_median",
+          "s2rep_p75",
+          "s2rep_p95",
+          "s2rep_p98",
+          "s2rep_mean",
+          "wri_p2",
+          "wri_p5",
+          "wri_p25",
+          "wri_median",
+          "wri_p75",
+          "wri_p95",
+          "wri_p98",
+          "wri_mean",
+          "wri_sd",
+          "wri_sum",
+          "wri_iqr",
+          "wri_iqr0595"
+        ],
+        "data": {
+          "from_node": "renamelabels2"
+        }
+      }
+    },
     "loadcollection2": {
       "process_id": "load_collection",
       "arguments": {
@@ -1277,7 +2164,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -1285,7 +2172,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }
@@ -1321,7 +2211,6 @@
         "options": {
           "implementation_version": "2",
           "tile_size": 128,
-          "otb_memory": 1024,
           "debug": false,
           "elev_geoid": "/opt/openeo-vito-aux-data/egm96.tif"
         }
@@ -1339,7 +2228,7 @@
         "resolution": 10.0
       }
     },
-    "applydimension2": {
+    "applydimension3": {
       "process_id": "apply_dimension",
       "arguments": {
         "data": {
@@ -1536,7 +2425,7 @@
       "process_id": "apply",
       "arguments": {
         "data": {
-          "from_node": "applydimension2"
+          "from_node": "applydimension3"
         },
         "process": {
           "process_graph": {
@@ -1557,7 +2446,7 @@
         }
       }
     },
-    "applydimension3": {
+    "applydimension4": {
       "process_id": "apply_dimension",
       "arguments": {
         "data": {
@@ -1593,7 +2482,7 @@
                 }
               }
             },
-            "subtract31": {
+            "subtract33": {
               "process_id": "subtract",
               "arguments": {
                 "x": {
@@ -1629,7 +2518,7 @@
                 }
               }
             },
-            "subtract32": {
+            "subtract34": {
               "process_id": "subtract",
               "arguments": {
                 "x": {
@@ -1643,10 +2532,10 @@
               "arguments": {
                 "data": [
                   {
-                    "from_node": "subtract31"
+                    "from_node": "subtract33"
                   },
                   {
-                    "from_node": "subtract32"
+                    "from_node": "subtract34"
                   }
                 ]
               },
@@ -1656,11 +2545,11 @@
         }
       }
     },
-    "applydimension4": {
+    "applydimension5": {
       "process_id": "apply_dimension",
       "arguments": {
         "data": {
-          "from_node": "applydimension3"
+          "from_node": "applydimension4"
         },
         "dimension": "bands",
         "process": {
@@ -1683,7 +2572,7 @@
                 "index": 1
               }
             },
-            "subtract33": {
+            "subtract35": {
               "process_id": "subtract",
               "arguments": {
                 "x": {
@@ -1745,7 +2634,7 @@
                 "index": 2,
                 "values": [
                   {
-                    "from_node": "subtract33"
+                    "from_node": "subtract35"
                   },
                   {
                     "from_node": "divide25"
@@ -1761,11 +2650,11 @@
         }
       }
     },
-    "renamelabels2": {
+    "renamelabels3": {
       "process_id": "rename_labels",
       "arguments": {
         "data": {
-          "from_node": "applydimension4"
+          "from_node": "applydimension5"
         },
         "dimension": "bands",
         "target": [
@@ -1777,31 +2666,19 @@
         ]
       }
     },
-    "mergecubes1": {
-      "process_id": "merge_cubes",
-      "arguments": {
-        "cube1": {
-          "from_node": "renamelabels1"
-        },
-        "cube2": {
-          "from_node": "renamelabels2"
-        }
-      }
-    },
-    "applydimension5": {
+    "applydimension6": {
       "process_id": "apply_dimension",
       "arguments": {
         "context": {
-          "parallel": true,
           "TileSize": 128
         },
         "data": {
-          "from_node": "mergecubes1"
+          "from_node": "renamelabels3"
         },
         "dimension": "t",
         "process": {
           "process_graph": {
-            "quantiles1": {
+            "quantiles6": {
               "process_id": "quantiles",
               "arguments": {
                 "data": {
@@ -1818,7 +2695,7 @@
                 ]
               }
             },
-            "mean1": {
+            "mean2": {
               "process_id": "mean",
               "arguments": {
                 "data": {
@@ -1826,7 +2703,7 @@
                 }
               }
             },
-            "sd1": {
+            "sd2": {
               "process_id": "sd",
               "arguments": {
                 "data": {
@@ -1834,7 +2711,7 @@
                 }
               }
             },
-            "sum1": {
+            "sum2": {
               "process_id": "sum",
               "arguments": {
                 "data": {
@@ -1842,7 +2719,7 @@
                 }
               }
             },
-            "quantiles2": {
+            "quantiles7": {
               "process_id": "quantiles",
               "arguments": {
                 "data": {
@@ -1853,7 +2730,7 @@
                 ]
               }
             },
-            "quantiles3": {
+            "quantiles8": {
               "process_id": "quantiles",
               "arguments": {
                 "data": {
@@ -1864,18 +2741,18 @@
                 ]
               }
             },
-            "subtract34": {
+            "subtract36": {
               "process_id": "subtract",
               "arguments": {
                 "x": {
-                  "from_node": "quantiles2"
+                  "from_node": "quantiles7"
                 },
                 "y": {
-                  "from_node": "quantiles3"
+                  "from_node": "quantiles8"
                 }
               }
             },
-            "quantiles4": {
+            "quantiles9": {
               "process_id": "quantiles",
               "arguments": {
                 "data": {
@@ -1886,7 +2763,7 @@
                 ]
               }
             },
-            "quantiles5": {
+            "quantiles10": {
               "process_id": "quantiles",
               "arguments": {
                 "data": {
@@ -1897,38 +2774,38 @@
                 ]
               }
             },
-            "subtract35": {
+            "subtract37": {
               "process_id": "subtract",
               "arguments": {
                 "x": {
-                  "from_node": "quantiles4"
+                  "from_node": "quantiles9"
                 },
                 "y": {
-                  "from_node": "quantiles5"
+                  "from_node": "quantiles10"
                 }
               }
             },
-            "arrayconcat1": {
+            "arrayconcat2": {
               "process_id": "array_concat",
               "arguments": {
                 "array1": {
-                  "from_node": "quantiles1"
+                  "from_node": "quantiles6"
                 },
                 "array2": [
                   {
-                    "from_node": "mean1"
+                    "from_node": "mean2"
                   },
                   {
-                    "from_node": "sd1"
+                    "from_node": "sd2"
                   },
                   {
-                    "from_node": "sum1"
+                    "from_node": "sum2"
                   },
                   {
-                    "from_node": "subtract34"
+                    "from_node": "subtract36"
                   },
                   {
-                    "from_node": "subtract35"
+                    "from_node": "subtract37"
                   }
                 ]
               },
@@ -1939,857 +2816,152 @@
         "target_dimension": "bands"
       }
     },
-    "renamelabels3": {
+    "renamelabels4": {
       "process_id": "rename_labels",
       "arguments": {
         "data": {
-          "from_node": "applydimension5"
+          "from_node": "applydimension6"
         },
         "dimension": "bands",
         "target": [
-          "B02_p2",
-          "B02_p5",
-          "B02_p25",
-          "B02_median",
-          "B02_p75",
-          "B02_p95",
-          "B02_p98",
-          "B02_mean",
-          "B02_sd",
-          "B02_sum",
-          "B02_iqr",
-          "B02_iqr0595",
-          "B03_p2",
-          "B03_p5",
-          "B03_p25",
-          "B03_median",
-          "B03_p75",
-          "B03_p95",
-          "B03_p98",
-          "B03_mean",
-          "B03_sd",
-          "B03_sum",
-          "B03_iqr",
-          "B03_iqr0595",
-          "B04_p2",
-          "B04_p5",
-          "B04_p25",
-          "B04_median",
-          "B04_p75",
-          "B04_p95",
-          "B04_p98",
-          "B04_mean",
-          "B04_sd",
-          "B04_sum",
-          "B04_iqr",
-          "B04_iqr0595",
-          "B05_p2",
-          "B05_p5",
-          "B05_p25",
-          "B05_median",
-          "B05_p75",
-          "B05_p95",
-          "B05_p98",
-          "B05_mean",
-          "B05_sd",
-          "B05_sum",
-          "B05_iqr",
-          "B05_iqr0595",
-          "B06_p2",
-          "B06_p5",
-          "B06_p25",
-          "B06_median",
-          "B06_p75",
-          "B06_p95",
-          "B06_p98",
-          "B06_mean",
-          "B06_sd",
-          "B06_sum",
-          "B06_iqr",
-          "B06_iqr0595",
-          "B07_p2",
-          "B07_p5",
-          "B07_p25",
-          "B07_median",
-          "B07_p75",
-          "B07_p95",
-          "B07_p98",
-          "B07_mean",
-          "B07_sd",
-          "B07_sum",
-          "B07_iqr",
-          "B07_iqr0595",
-          "B08_p2",
-          "B08_p5",
-          "B08_p25",
-          "B08_median",
-          "B08_p75",
-          "B08_p95",
-          "B08_p98",
-          "B08_mean",
-          "B08_sd",
-          "B08_sum",
-          "B08_iqr",
-          "B08_iqr0595",
-          "B8A_p2",
-          "B8A_p5",
-          "B8A_p25",
-          "B8A_median",
-          "B8A_p75",
-          "B8A_p95",
-          "B8A_p98",
-          "B8A_mean",
-          "B8A_sd",
-          "B8A_sum",
-          "B8A_iqr",
-          "B8A_iqr0595",
-          "B11_p2",
-          "B11_p5",
-          "B11_p25",
-          "B11_median",
-          "B11_p75",
-          "B11_p95",
-          "B11_p98",
-          "B11_mean",
-          "B11_sd",
-          "B11_sum",
-          "B11_iqr",
-          "B11_iqr0595",
-          "B12_p2",
-          "B12_p5",
-          "B12_p25",
-          "B12_median",
-          "B12_p75",
-          "B12_p95",
-          "B12_p98",
-          "B12_mean",
-          "B12_sd",
-          "B12_sum",
-          "B12_iqr",
-          "B12_iqr0595",
-          "ABDI1_p2",
-          "ABDI1_p5",
-          "ABDI1_p25",
-          "ABDI1_median",
-          "ABDI1_p75",
-          "ABDI1_p95",
-          "ABDI1_p98",
-          "ABDI1_mean",
-          "ABDI1_sd",
-          "ABDI1_sum",
-          "ABDI1_iqr",
-          "ABDI1_iqr0595",
-          "ABDI2_p2",
-          "ABDI2_p5",
-          "ABDI2_p25",
-          "ABDI2_median",
-          "ABDI2_p75",
-          "ABDI2_p95",
-          "ABDI2_p98",
-          "ABDI2_mean",
-          "ABDI2_sd",
-          "ABDI2_sum",
-          "ABDI2_iqr",
-          "ABDI2_iqr0595",
-          "AWEInsh_p2",
-          "AWEInsh_p5",
-          "AWEInsh_p25",
-          "AWEInsh_median",
-          "AWEInsh_p75",
-          "AWEInsh_p95",
-          "AWEInsh_p98",
-          "AWEInsh_mean",
-          "AWEInsh_sd",
-          "AWEInsh_sum",
-          "AWEInsh_iqr",
-          "AWEInsh_iqr0595",
-          "AVI_p2",
-          "AVI_p5",
-          "AVI_p25",
-          "AVI_median",
-          "AVI_p75",
-          "AVI_p95",
-          "AVI_p98",
-          "AVI_mean",
-          "AVI_sd",
-          "AVI_sum",
-          "AVI_iqr",
-          "AVI_iqr0595",
-          "BLFEI_p2",
-          "BLFEI_p5",
-          "BLFEI_p25",
-          "BLFEI_median",
-          "BLFEI_p75",
-          "BLFEI_p95",
-          "BLFEI_p98",
-          "BLFEI_mean",
-          "BLFEI_sd",
-          "BLFEI_sum",
-          "BLFEI_iqr",
-          "BLFEI_iqr0595",
-          "CIRE_p2",
-          "CIRE_p5",
-          "CIRE_p25",
-          "CIRE_median",
-          "CIRE_p75",
-          "CIRE_p95",
-          "CIRE_p98",
-          "CIRE_mean",
-          "CIRE_sd",
-          "CIRE_sum",
-          "CIRE_iqr",
-          "CIRE_iqr0595",
-          "EVI_p2",
-          "EVI_p5",
-          "EVI_p25",
-          "EVI_median",
-          "EVI_p75",
-          "EVI_p95",
-          "EVI_p98",
-          "EVI_mean",
-          "EVI_sd",
-          "EVI_sum",
-          "EVI_iqr",
-          "EVI_iqr0595",
-          "IRECI_p2",
-          "IRECI_p5",
-          "IRECI_p25",
-          "IRECI_median",
-          "IRECI_p75",
-          "IRECI_p95",
-          "IRECI_p98",
-          "IRECI_mean",
-          "IRECI_sd",
-          "IRECI_sum",
-          "IRECI_iqr",
-          "IRECI_iqr0595",
-          "MBWI_p2",
-          "MBWI_p5",
-          "MBWI_p25",
-          "MBWI_median",
-          "MBWI_p75",
-          "MBWI_p95",
-          "MBWI_p98",
-          "MBWI_mean",
-          "MBWI_sd",
-          "MBWI_sum",
-          "MBWI_iqr",
-          "MBWI_iqr0595",
-          "MNDWI_p2",
-          "MNDWI_p5",
-          "MNDWI_p25",
-          "MNDWI_median",
-          "MNDWI_p75",
-          "MNDWI_p95",
-          "MNDWI_p98",
-          "MNDWI_mean",
-          "MNDWI_sd",
-          "MNDWI_sum",
-          "MNDWI_iqr",
-          "MNDWI_iqr0595",
-          "MNDVI_p2",
-          "MNDVI_p5",
-          "MNDVI_p25",
-          "MNDVI_median",
-          "MNDVI_p75",
-          "MNDVI_p95",
-          "MNDVI_p98",
-          "MNDVI_mean",
-          "MNDVI_sd",
-          "MNDVI_sum",
-          "MNDVI_iqr",
-          "MNDVI_iqr0595",
-          "NDMI_p2",
-          "NDMI_p5",
-          "NDMI_p25",
-          "NDMI_median",
-          "NDMI_p75",
-          "NDMI_p95",
-          "NDMI_p98",
-          "NDMI_mean",
-          "NDMI_sd",
-          "NDMI_sum",
-          "NDMI_iqr",
-          "NDMI_iqr0595",
-          "NDVI_p2",
-          "NDVI_p5",
-          "NDVI_p25",
-          "NDVI_median",
-          "NDVI_p75",
-          "NDVI_p95",
-          "NDVI_p98",
-          "NDVI_mean",
-          "NDVI_sd",
-          "NDVI_sum",
-          "NDVI_iqr",
-          "NDVI_iqr0595",
-          "NDVIMNDWI_p2",
-          "NDVIMNDWI_p5",
-          "NDVIMNDWI_p25",
-          "NDVIMNDWI_median",
-          "NDVIMNDWI_p75",
-          "NDVIMNDWI_p95",
-          "NDVIMNDWI_p98",
-          "NDVIMNDWI_mean",
-          "NDVIMNDWI_sd",
-          "NDVIMNDWI_sum",
-          "NDVIMNDWI_iqr",
-          "NDVIMNDWI_iqr0595",
-          "NDWI_p2",
-          "NDWI_p5",
-          "NDWI_p25",
-          "NDWI_median",
-          "NDWI_p75",
-          "NDWI_p95",
-          "NDWI_p98",
-          "NDWI_mean",
-          "NDWI_sd",
-          "NDWI_sum",
-          "NDWI_iqr",
-          "NDWI_iqr0595",
-          "NMDI_p2",
-          "NMDI_p5",
-          "NMDI_p25",
-          "NMDI_median",
-          "NMDI_p75",
-          "NMDI_p95",
-          "NMDI_p98",
-          "NMDI_mean",
-          "NMDI_sd",
-          "NMDI_sum",
-          "NMDI_iqr",
-          "NMDI_iqr0595",
-          "NIRv_p2",
-          "NIRv_p5",
-          "NIRv_p25",
-          "NIRv_median",
-          "NIRv_p75",
-          "NIRv_p95",
-          "NIRv_p98",
-          "NIRv_mean",
-          "NIRv_sd",
-          "NIRv_sum",
-          "NIRv_iqr",
-          "NIRv_iqr0595",
-          "S2WI_p2",
-          "S2WI_p5",
-          "S2WI_p25",
-          "S2WI_median",
-          "S2WI_p75",
-          "S2WI_p95",
-          "S2WI_p98",
-          "S2WI_mean",
-          "S2WI_sd",
-          "S2WI_sum",
-          "S2WI_iqr",
-          "S2WI_iqr0595",
-          "S2REP_p2",
-          "S2REP_p5",
-          "S2REP_p25",
-          "S2REP_median",
-          "S2REP_p75",
-          "S2REP_p95",
-          "S2REP_p98",
-          "S2REP_mean",
-          "S2REP_sd",
-          "S2REP_sum",
-          "S2REP_iqr",
-          "S2REP_iqr0595",
-          "WRI_p2",
-          "WRI_p5",
-          "WRI_p25",
-          "WRI_median",
-          "WRI_p75",
-          "WRI_p95",
-          "WRI_p98",
-          "WRI_mean",
-          "WRI_sd",
-          "WRI_sum",
-          "WRI_iqr",
-          "WRI_iqr0595",
-          "VH_p2",
-          "VH_p5",
-          "VH_p25",
-          "VH_median",
-          "VH_p75",
-          "VH_p95",
-          "VH_p98",
-          "VH_mean",
-          "VH_sd",
-          "VH_sum",
-          "VH_iqr",
-          "VH_iqr0595",
-          "VV_p2",
-          "VV_p5",
-          "VV_p25",
-          "VV_median",
-          "VV_p75",
-          "VV_p95",
-          "VV_p98",
-          "VV_mean",
-          "VV_sd",
-          "VV_sum",
-          "VV_iqr",
-          "VV_iqr0595",
-          "VHVVD_p2",
-          "VHVVD_p5",
-          "VHVVD_p25",
-          "VHVVD_median",
-          "VHVVD_p75",
-          "VHVVD_p95",
-          "VHVVD_p98",
-          "VHVVD_mean",
-          "VHVVD_sd",
-          "VHVVD_sum",
-          "VHVVD_iqr",
-          "VHVVD_iqr0595",
-          "VHVVR_p2",
-          "VHVVR_p5",
-          "VHVVR_p25",
-          "VHVVR_median",
-          "VHVVR_p75",
-          "VHVVR_p95",
-          "VHVVR_p98",
-          "VHVVR_mean",
-          "VHVVR_sd",
-          "VHVVR_sum",
-          "VHVVR_iqr",
-          "VHVVR_iqr0595",
-          "DpRVIVV_p2",
-          "DpRVIVV_p5",
-          "DpRVIVV_p25",
-          "DpRVIVV_median",
-          "DpRVIVV_p75",
-          "DpRVIVV_p95",
-          "DpRVIVV_p98",
-          "DpRVIVV_mean",
-          "DpRVIVV_sd",
-          "DpRVIVV_sum",
-          "DpRVIVV_iqr",
-          "DpRVIVV_iqr0595"
+          "vh_p2",
+          "vh_p5",
+          "vh_p25",
+          "vh_median",
+          "vh_p75",
+          "vh_p95",
+          "vh_p98",
+          "vh_mean",
+          "vh_sd",
+          "vh_sum",
+          "vh_iqr",
+          "vh_iqr0595",
+          "vv_p2",
+          "vv_p5",
+          "vv_p25",
+          "vv_median",
+          "vv_p75",
+          "vv_p95",
+          "vv_p98",
+          "vv_mean",
+          "vv_sd",
+          "vv_sum",
+          "vv_iqr",
+          "vv_iqr0595",
+          "vhvvd_p2",
+          "vhvvd_p5",
+          "vhvvd_p25",
+          "vhvvd_median",
+          "vhvvd_p75",
+          "vhvvd_p95",
+          "vhvvd_p98",
+          "vhvvd_mean",
+          "vhvvd_sd",
+          "vhvvd_sum",
+          "vhvvd_iqr",
+          "vhvvd_iqr0595",
+          "vhvvr_p2",
+          "vhvvr_p5",
+          "vhvvr_p25",
+          "vhvvr_median",
+          "vhvvr_p75",
+          "vhvvr_p95",
+          "vhvvr_p98",
+          "vhvvr_mean",
+          "vhvvr_sd",
+          "vhvvr_sum",
+          "vhvvr_iqr",
+          "vhvvr_iqr0595",
+          "dprvivv_p2",
+          "dprvivv_p5",
+          "dprvivv_p25",
+          "dprvivv_median",
+          "dprvivv_p75",
+          "dprvivv_p95",
+          "dprvivv_p98",
+          "dprvivv_mean",
+          "dprvivv_sd",
+          "dprvivv_sum",
+          "dprvivv_iqr",
+          "dprvivv_iqr0595"
         ]
       }
     },
-    "filterbands1": {
+    "filterbands2": {
       "process_id": "filter_bands",
       "arguments": {
         "bands": [
-          "B02_p2",
-          "B02_p5",
-          "B02_p25",
-          "B02_median",
-          "B02_p75",
-          "B02_p95",
-          "B02_p98",
-          "B02_mean",
-          "B02_sd",
-          "B02_sum",
-          "B02_iqr",
-          "B02_iqr0595",
-          "B03_p2",
-          "B03_p5",
-          "B03_p25",
-          "B03_median",
-          "B03_p75",
-          "B03_p95",
-          "B03_p98",
-          "B03_mean",
-          "B03_sd",
-          "B03_sum",
-          "B03_iqr",
-          "B03_iqr0595",
-          "B04_p2",
-          "B04_p5",
-          "B04_p25",
-          "B04_median",
-          "B04_p75",
-          "B04_p95",
-          "B04_p98",
-          "B04_mean",
-          "B04_sd",
-          "B04_sum",
-          "B04_iqr",
-          "B04_iqr0595",
-          "B05_p2",
-          "B05_p5",
-          "B05_p25",
-          "B05_median",
-          "B05_p75",
-          "B05_p95",
-          "B05_p98",
-          "B05_mean",
-          "B05_sd",
-          "B05_sum",
-          "B05_iqr",
-          "B05_iqr0595",
-          "B06_p2",
-          "B06_p5",
-          "B06_p25",
-          "B06_median",
-          "B06_p75",
-          "B06_p95",
-          "B06_p98",
-          "B06_mean",
-          "B06_sd",
-          "B06_sum",
-          "B06_iqr",
-          "B06_iqr0595",
-          "B07_p2",
-          "B07_p5",
-          "B07_p25",
-          "B07_median",
-          "B07_p75",
-          "B07_p95",
-          "B07_p98",
-          "B07_mean",
-          "B07_sd",
-          "B07_sum",
-          "B07_iqr",
-          "B07_iqr0595",
-          "B08_p2",
-          "B08_p5",
-          "B08_p25",
-          "B08_median",
-          "B08_p75",
-          "B08_p95",
-          "B08_p98",
-          "B08_mean",
-          "B08_sd",
-          "B08_sum",
-          "B08_iqr",
-          "B08_iqr0595",
-          "B8A_p2",
-          "B8A_p5",
-          "B8A_p25",
-          "B8A_median",
-          "B8A_p75",
-          "B8A_p95",
-          "B8A_p98",
-          "B8A_mean",
-          "B8A_sd",
-          "B8A_sum",
-          "B8A_iqr",
-          "B8A_iqr0595",
-          "B11_p2",
-          "B11_p5",
-          "B11_p25",
-          "B11_median",
-          "B11_p75",
-          "B11_p95",
-          "B11_p98",
-          "B11_mean",
-          "B11_sd",
-          "B11_sum",
-          "B11_iqr",
-          "B11_iqr0595",
-          "B12_p2",
-          "B12_p5",
-          "B12_p25",
-          "B12_median",
-          "B12_p75",
-          "B12_p95",
-          "B12_p98",
-          "B12_mean",
-          "B12_sd",
-          "B12_sum",
-          "B12_iqr",
-          "B12_iqr0595",
-          "ABDI1_p2",
-          "ABDI1_p5",
-          "ABDI1_p25",
-          "ABDI1_median",
-          "ABDI1_p75",
-          "ABDI1_p95",
-          "ABDI1_p98",
-          "ABDI1_mean",
-          "ABDI1_sd",
-          "ABDI1_sum",
-          "ABDI1_iqr",
-          "ABDI1_iqr0595",
-          "ABDI2_p2",
-          "ABDI2_p5",
-          "ABDI2_p25",
-          "ABDI2_median",
-          "ABDI2_p75",
-          "ABDI2_p95",
-          "ABDI2_p98",
-          "ABDI2_mean",
-          "ABDI2_sd",
-          "ABDI2_sum",
-          "ABDI2_iqr",
-          "ABDI2_iqr0595",
-          "AWEInsh_p2",
-          "AWEInsh_p5",
-          "AWEInsh_p25",
-          "AWEInsh_median",
-          "AWEInsh_p75",
-          "AWEInsh_p95",
-          "AWEInsh_p98",
-          "AWEInsh_mean",
-          "AWEInsh_sd",
-          "AWEInsh_sum",
-          "AWEInsh_iqr",
-          "AWEInsh_iqr0595",
-          "AVI_p2",
-          "AVI_p5",
-          "AVI_p25",
-          "AVI_median",
-          "AVI_p75",
-          "AVI_p95",
-          "AVI_p98",
-          "AVI_mean",
-          "AVI_sd",
-          "AVI_sum",
-          "AVI_iqr",
-          "AVI_iqr0595",
-          "BLFEI_p2",
-          "BLFEI_p5",
-          "BLFEI_p25",
-          "BLFEI_median",
-          "BLFEI_p75",
-          "BLFEI_p95",
-          "BLFEI_p98",
-          "BLFEI_mean",
-          "BLFEI_sd",
-          "BLFEI_sum",
-          "BLFEI_iqr",
-          "BLFEI_iqr0595",
-          "CIRE_p2",
-          "CIRE_p5",
-          "CIRE_p25",
-          "CIRE_median",
-          "CIRE_p75",
-          "CIRE_p95",
-          "CIRE_p98",
-          "CIRE_mean",
-          "CIRE_sd",
-          "CIRE_sum",
-          "CIRE_iqr",
-          "CIRE_iqr0595",
-          "EVI_p2",
-          "EVI_p5",
-          "EVI_p25",
-          "EVI_median",
-          "EVI_p75",
-          "EVI_p95",
-          "EVI_p98",
-          "EVI_mean",
-          "EVI_sd",
-          "EVI_sum",
-          "EVI_iqr",
-          "EVI_iqr0595",
-          "IRECI_p2",
-          "IRECI_p5",
-          "IRECI_p25",
-          "IRECI_median",
-          "IRECI_p75",
-          "IRECI_p95",
-          "IRECI_p98",
-          "IRECI_mean",
-          "IRECI_sd",
-          "IRECI_sum",
-          "IRECI_iqr",
-          "IRECI_iqr0595",
-          "MBWI_p2",
-          "MBWI_p5",
-          "MBWI_p25",
-          "MBWI_median",
-          "MBWI_p75",
-          "MBWI_p95",
-          "MBWI_p98",
-          "MBWI_mean",
-          "MBWI_sd",
-          "MBWI_sum",
-          "MBWI_iqr",
-          "MBWI_iqr0595",
-          "MNDWI_p2",
-          "MNDWI_p5",
-          "MNDWI_p25",
-          "MNDWI_median",
-          "MNDWI_p75",
-          "MNDWI_p95",
-          "MNDWI_p98",
-          "MNDWI_mean",
-          "MNDWI_sd",
-          "MNDWI_sum",
-          "MNDWI_iqr",
-          "MNDWI_iqr0595",
-          "MNDVI_p2",
-          "MNDVI_p5",
-          "MNDVI_p25",
-          "MNDVI_median",
-          "MNDVI_p75",
-          "MNDVI_p95",
-          "MNDVI_p98",
-          "MNDVI_mean",
-          "MNDVI_sd",
-          "MNDVI_sum",
-          "MNDVI_iqr",
-          "MNDVI_iqr0595",
-          "NDMI_p2",
-          "NDMI_p5",
-          "NDMI_p25",
-          "NDMI_median",
-          "NDMI_p75",
-          "NDMI_p95",
-          "NDMI_p98",
-          "NDMI_mean",
-          "NDMI_sd",
-          "NDMI_sum",
-          "NDMI_iqr",
-          "NDMI_iqr0595",
-          "NDVI_p2",
-          "NDVI_p5",
-          "NDVI_p25",
-          "NDVI_median",
-          "NDVI_p75",
-          "NDVI_p95",
-          "NDVI_p98",
-          "NDVI_mean",
-          "NDVI_sd",
-          "NDVI_sum",
-          "NDVI_iqr",
-          "NDVI_iqr0595",
-          "NDVIMNDWI_p2",
-          "NDVIMNDWI_p5",
-          "NDVIMNDWI_p25",
-          "NDVIMNDWI_median",
-          "NDVIMNDWI_p75",
-          "NDVIMNDWI_p95",
-          "NDVIMNDWI_p98",
-          "NDVIMNDWI_mean",
-          "NDVIMNDWI_sd",
-          "NDVIMNDWI_sum",
-          "NDVIMNDWI_iqr",
-          "NDVIMNDWI_iqr0595",
-          "NDWI_p2",
-          "NDWI_p5",
-          "NDWI_p25",
-          "NDWI_median",
-          "NDWI_p75",
-          "NDWI_p95",
-          "NDWI_p98",
-          "NDWI_mean",
-          "NDWI_sd",
-          "NDWI_sum",
-          "NDWI_iqr",
-          "NDWI_iqr0595",
-          "NMDI_p2",
-          "NMDI_p5",
-          "NMDI_p25",
-          "NMDI_median",
-          "NMDI_p75",
-          "NMDI_p95",
-          "NMDI_p98",
-          "NMDI_mean",
-          "NMDI_sd",
-          "NMDI_sum",
-          "NMDI_iqr",
-          "NMDI_iqr0595",
-          "NIRv_p2",
-          "NIRv_p5",
-          "NIRv_p25",
-          "NIRv_median",
-          "NIRv_p75",
-          "NIRv_p95",
-          "NIRv_p98",
-          "NIRv_mean",
-          "NIRv_sd",
-          "NIRv_sum",
-          "NIRv_iqr",
-          "NIRv_iqr0595",
-          "S2WI_p2",
-          "S2WI_p5",
-          "S2WI_p25",
-          "S2WI_median",
-          "S2WI_p75",
-          "S2WI_p95",
-          "S2WI_p98",
-          "S2WI_mean",
-          "S2WI_sd",
-          "S2WI_sum",
-          "S2WI_iqr",
-          "S2WI_iqr0595",
-          "S2REP_p2",
-          "S2REP_p5",
-          "S2REP_p25",
-          "S2REP_median",
-          "S2REP_p75",
-          "S2REP_p95",
-          "S2REP_p98",
-          "S2REP_mean",
-          "WRI_p2",
-          "WRI_p5",
-          "WRI_p25",
-          "WRI_median",
-          "WRI_p75",
-          "WRI_p95",
-          "WRI_p98",
-          "WRI_mean",
-          "WRI_sd",
-          "WRI_sum",
-          "WRI_iqr",
-          "WRI_iqr0595",
-          "VH_p2",
-          "VH_p5",
-          "VH_p25",
-          "VH_median",
-          "VH_p75",
-          "VH_p95",
-          "VH_p98",
-          "VH_mean",
-          "VH_sd",
-          "VH_iqr",
-          "VH_iqr0595",
-          "VV_p2",
-          "VV_p5",
-          "VV_p25",
-          "VV_median",
-          "VV_p75",
-          "VV_p95",
-          "VV_p98",
-          "VV_mean",
-          "VV_sd",
-          "VV_iqr",
-          "VV_iqr0595",
-          "VHVVD_p2",
-          "VHVVD_p5",
-          "VHVVD_p25",
-          "VHVVD_median",
-          "VHVVD_p75",
-          "VHVVD_p95",
-          "VHVVD_p98",
-          "VHVVD_mean",
-          "VHVVD_sd",
-          "VHVVD_iqr",
-          "VHVVD_iqr0595",
-          "VHVVR_p2",
-          "VHVVR_p5",
-          "VHVVR_p25",
-          "VHVVR_median",
-          "VHVVR_p75",
-          "VHVVR_p95",
-          "VHVVR_p98",
-          "VHVVR_mean",
-          "VHVVR_sd",
-          "VHVVR_sum",
-          "VHVVR_iqr",
-          "VHVVR_iqr0595",
-          "DpRVIVV_p2",
-          "DpRVIVV_p5",
-          "DpRVIVV_p25",
-          "DpRVIVV_median",
-          "DpRVIVV_p75",
-          "DpRVIVV_p95",
-          "DpRVIVV_p98",
-          "DpRVIVV_mean",
-          "DpRVIVV_sd",
-          "DpRVIVV_sum",
-          "DpRVIVV_iqr",
-          "DpRVIVV_iqr0595"
+          "vh_p2",
+          "vh_p5",
+          "vh_p25",
+          "vh_median",
+          "vh_p75",
+          "vh_p95",
+          "vh_p98",
+          "vh_mean",
+          "vh_sd",
+          "vh_iqr",
+          "vh_iqr0595",
+          "vv_p2",
+          "vv_p5",
+          "vv_p25",
+          "vv_median",
+          "vv_p75",
+          "vv_p95",
+          "vv_p98",
+          "vv_mean",
+          "vv_sd",
+          "vv_iqr",
+          "vv_iqr0595",
+          "vhvvd_p2",
+          "vhvvd_p5",
+          "vhvvd_p25",
+          "vhvvd_median",
+          "vhvvd_p75",
+          "vhvvd_p95",
+          "vhvvd_p98",
+          "vhvvd_mean",
+          "vhvvd_sd",
+          "vhvvd_iqr",
+          "vhvvd_iqr0595",
+          "vhvvr_p2",
+          "vhvvr_p5",
+          "vhvvr_p25",
+          "vhvvr_median",
+          "vhvvr_p75",
+          "vhvvr_p95",
+          "vhvvr_p98",
+          "vhvvr_mean",
+          "vhvvr_sd",
+          "vhvvr_sum",
+          "vhvvr_iqr",
+          "vhvvr_iqr0595",
+          "dprvivv_p2",
+          "dprvivv_p5",
+          "dprvivv_p25",
+          "dprvivv_median",
+          "dprvivv_p75",
+          "dprvivv_p95",
+          "dprvivv_p98",
+          "dprvivv_mean",
+          "dprvivv_sd",
+          "dprvivv_sum",
+          "dprvivv_iqr",
+          "dprvivv_iqr0595"
         ],
         "data": {
-          "from_node": "renamelabels3"
+          "from_node": "renamelabels4"
+        }
+      }
+    },
+    "mergecubes1": {
+      "process_id": "merge_cubes",
+      "arguments": {
+        "cube1": {
+          "from_node": "filterbands1"
+        },
+        "cube2": {
+          "from_node": "filterbands2"
         }
       }
     },
@@ -2858,7 +3030,7 @@
       "process_id": "merge_cubes",
       "arguments": {
         "cube1": {
-          "from_node": "filterbands1"
+          "from_node": "mergecubes1"
         },
         "cube2": {
           "from_node": "filterbbox1"
@@ -2918,7 +3090,7 @@
         }
       }
     },
-    "applydimension6": {
+    "applydimension7": {
       "process_id": "apply_dimension",
       "arguments": {
         "data": {
@@ -2950,7 +3122,7 @@
       "process_id": "apply",
       "arguments": {
         "data": {
-          "from_node": "applydimension6"
+          "from_node": "applydimension7"
         },
         "process": {
           "process_graph": {
diff --git a/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference_integration.json b/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference_integration.json
index cafa0c0..862ee3b 100644
--- a/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference_integration.json
+++ b/tests/resources/cube_generation/generate_master_feature_cube_with_catboost_inference_integration.json
@@ -848,7 +848,7 @@
         },
         "id": "SENTINEL1_GRD",
         "properties": {
-          "polarisation": {
+          "sar:polarizations": {
             "process_graph": {
               "eq1": {
                 "process_id": "eq",
@@ -856,7 +856,10 @@
                   "x": {
                     "from_parameter": "value"
                   },
-                  "y": "VV&VH"
+                  "y": [
+                    "VV",
+                    "VH"
+                  ]
                 },
                 "result": true
               }