BIOMASS-3126-Maap jupyter clean dockerfile and add librairies

77ec669d · jessica · 2a2e49f3 · 77ec669d · 77ec669d · 77ec669d
Commit 77ec669d authored 1 year ago by jessica
--- a/maap_jupyter/.ipynb_checkpoints/maap_notebook-checkpoint.ipynb
+++ b/maap_jupyter/.ipynb_checkpoints/maap_notebook-checkpoint.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1a70970d",
+   "metadata": {},
+   "source": [
+    "# <center> Tree Classification Demo </center>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bf3c2a51",
+   "metadata": {},
+   "source": [
+    "<center>Tests for geopandas and gdal<center>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c55216cb",
+   "metadata": {},
+   "source": [
+    "## Import Packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4d9291fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "import json\n",
+    "import time\n",
+    "import configparser\n",
+    "import requests\n",
+    "# On NASA , install with pip install geopandas\n",
+    "# On ESA; use a PolinSAR stack ( geopandas already embedded) \n",
+    "import geopandas as gpd\n",
+    "import pandas as pd\n",
+    "from creodias_finder import query\n",
+    "from shapely.geometry import Polygon,shape\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "711e5ecd",
+   "metadata": {},
+   "source": [
+    "## Define Functions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "2b694047",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def __get_result_S1( geometry_search, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date):\n",
+    "    '''\n",
+    "        Recupere dans un dataframe les produits S1 qui intersectent la zone de recherche\n",
+    "\n",
+    "        :geometry_search: geometrie de la zone de recherche\n",
+    "        :str_plateformeS1: nom de la plateforme\n",
+    "        :str_product_type: nom du product type\n",
+    "        :str_sensor_mode: nom du sensor mode\n",
+    "        :start_date: date debut interval recherche au format datetime\n",
+    "        :end_date: date fin interval recherche au format datetime\n",
+    "\n",
+    "\n",
+    "        return: df_groupby\n",
+    "        :rtype: dataframe\n",
+    "    '''\n",
+    "\n",
+    "    # liste des produits de l'api creodias\n",
+    "    results = query.query(\n",
+    "        str_plateformeS1,\n",
+    "        start_date=start_date,\n",
+    "        end_date=end_date,\n",
+    "        productType=str_product_type,\n",
+    "        sensorMode=str_sensor_mode,\n",
+    "        status=\"ONLINE\",\n",
+    "        geometry=geometry_search\n",
+    "    )\n",
+    "\n",
+    "    # init des listes des parametres a conserver \n",
+    "    list_title = []\n",
+    "    list_date = []\n",
+    "    list_orbit = []\n",
+    "    list_orbitDirection = []\n",
+    "    list_geom = []\n",
+    "    list_url = []\n",
+    "\n",
+    "    # remplissage des listes avec les parametres des produits du results de l'api\n",
+    "    for idproduct, dict_product in results.items():\n",
+    "        list_title.append(dict_product['properties']['title'])\n",
+    "        list_orbit.append(dict_product['properties']['relativeOrbitNumber'])\n",
+    "        list_orbitDirection.append(dict_product['properties']['orbitDirection'])\n",
+    "        list_geom.append(shape(dict_product['geometry']))\n",
+    "        list_url.append(dict_product['properties']['productIdentifier'])\n",
+    "        list_date.append(dict_product['properties']['title'][17:25])\n",
+    "\n",
+    "    # genere le gdf avec les produits s1\n",
+    "    gdf_product = gpd.GeoDataFrame({'title' : list_title, 'date' : list_date, 'orbit' : list_orbit, 'direction' : list_orbitDirection,'geometry' : list_geom, 'url' : list_url}, crs = \"4326\")\n",
+    "    # regroupe les produits qui ont les memes parametres de date, orbit et direction\n",
+    "    df_groupby = gdf_product.groupby(['date', 'orbit', 'direction']).agg({'title' : list, 'url' : list, 'geometry' : list}).reset_index()\n",
+    "\n",
+    "    return df_groupby\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2573ab84",
+   "metadata": {},
+   "source": [
+    "## Define the study area or list of tile"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7e14efe8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search_zone = [[4.751930185604931,45.37522170186796],[4.468812157001305,45.24092464324643],[4.018935832120382,44.88158298080388],[3.852035966569818,44.75014456444579],[3.898047329546759,44.56923769773521],[4.038870891160542,44.31329708744024],[4.241954580160842,44.26894961414283],[4.674279531570155,44.26246269728098],[4.882500597010154,44.8652889083827],[4.905098845459158,45.06277528749476],[4.782524828980907,45.368587240900965],[4.751930185604931,45.37522170186796]]\n",
+    "search_poly = Polygon(search_zone)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9b8ee178",
+   "metadata": {},
+   "source": [
+    "## Search S1 products"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "f7fd2a1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# parametres de recherche\n",
+    "str_plateformeS1 = 'Sentinel1'\n",
+    "str_product_type = 'GRD'\n",
+    "str_sensor_mode = 'IW'\n",
+    "start_date = datetime(2022, 6, 3)\n",
+    "end_date = datetime(2023, 1, 31)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "3cb6aa8f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query_url http://datahub.creodias.eu/resto/api/collections/Sentinel1/search.json?maxRecords=1000&startDate=2022-06-03T00%3A00%3A00&completionDate=2023-01-31T23%3A59%3A59&geometry=POLYGON+%28%284.751930185604931+45.37522170186796%2C+4.468812157001305+45.24092464324643%2C+4.018935832120382+44.88158298080388%2C+3.852035966569818+44.75014456444579%2C+3.898047329546759+44.56923769773521%2C+4.038870891160542+44.31329708744024%2C+4.241954580160842+44.26894961414283%2C+4.674279531570155+44.26246269728098%2C+4.882500597010154+44.8652889083827%2C+4.905098845459158+45.06277528749476%2C+4.782524828980907+45.368587240900965%2C+4.751930185604931+45.37522170186796%29%29&status=ONLINE&productType=GRD&sensorMode=IW\n",
+      "<Response [200]>\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "df_product = __get_result_S1( search_poly, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "568856bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "20\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_product\n",
+    "df_product = df_product[df_product['orbit']==37]\n",
+    "df_product\n",
+    "print(len(df_product))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f85d0273",
+   "metadata": {},
+   "source": [
+    "## Extract list of URL "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "6cfbf9c7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[\"Sentinel-1/SAR/GRD/2022/06/04/S1A_IW_GRDH_1SDV_20220604T055236_20220604T055301_043509_0531E5_DC1B.SAFE,\"Sentinel-1/SAR/GRD/2022/06/16/S1A_IW_GRDH_1SDV_20220616T055236_20220616T055301_043684_05371A_E51A.SAFE,\"Sentinel-1/SAR/GRD/2022/06/28/S1A_IW_GRDH_1SDV_20220628T055237_20220628T055302_043859_053C5F_3096.SAFE,\"Sentinel-1/SAR/GRD/2022/07/22/S1A_IW_GRDH_1SDV_20220722T055238_20220722T055303_044209_0546C9_677E.SAFE,\"Sentinel-1/SAR/GRD/2022/08/03/S1A_IW_GRDH_1SDV_20220803T055239_20220803T055304_044384_054BF3_4ACD.SAFE,\"Sentinel-1/SAR/GRD/2022/08/15/S1A_IW_GRDH_1SDV_20220815T055240_20220815T055305_044559_05516B_B0D3.SAFE,\"Sentinel-1/SAR/GRD/2022/08/27/S1A_IW_GRDH_1SDV_20220827T055240_20220827T055305_044734_055755_77D7.SAFE,\"Sentinel-1/SAR/GRD/2022/09/08/S1A_IW_GRDH_1SDV_20220908T055241_20220908T055306_044909_055D33_8C27.SAFE,\"Sentinel-1/SAR/GRD/2022/09/20/S1A_IW_GRDH_1SDV_20220920T055241_20220920T055306_045084_056320_8ED8.SAFE,\"Sentinel-1/SAR/GRD/2022/10/02/S1A_IW_GRDH_1SDV_20221002T055242_20221002T055307_045259_0568FD_84DA.SAFE,\"Sentinel-1/SAR/GRD/2022/10/14/S1A_IW_GRDH_1SDV_20221014T055242_20221014T055307_045434_056EDB_346E.SAFE,\"Sentinel-1/SAR/GRD/2022/10/26/S1A_IW_GRDH_1SDV_20221026T055242_20221026T055307_045609_05740C_5826.SAFE,\"Sentinel-1/SAR/GRD/2022/11/07/S1A_IW_GRDH_1SDV_20221107T055241_20221107T055306_045784_0579F9_649C.SAFE,\"Sentinel-1/SAR/GRD/2022/11/19/S1A_IW_GRDH_1SDV_20221119T055241_20221119T055306_045959_057FDC_E997.SAFE,\"Sentinel-1/SAR/GRD/2022/12/01/S1A_IW_GRDH_1SDV_20221201T055240_20221201T055305_046134_0585CE_836F.SAFE,\"Sentinel-1/SAR/GRD/2022/12/13/S1A_IW_GRDH_1SDV_20221213T055240_20221213T055305_046309_058BCE_F90F.SAFE,\"Sentinel-1/SAR/GRD/2022/12/25/S1A_IW_GRDH_1SDV_20221225T055239_20221225T055304_046484_0591C3_7C2C.SAFE,\"Sentinel-1/SAR/GRD/2023/01/06/S1A_IW_GRDH_1SDV_20230106T055239_20230106T055304_046659_0597A7_7ED7.SAFE,\"Sentinel-1/SAR/GRD/2023/01/18/S1A_IW_GRDH_1SDV_20230118T055238_20230118T055303_046834_059D93_5C5F.SAFE,\"Sentinel-1/SAR/GRD/2023/01/30/S1A_IW_GRDH_1SDV_20230130T055238_20230130T055303_047009_05A37A_61B6.SAFE\"]\n"
+     ]
+    }
+   ],
+   "source": [
+    "tmp_list_product_path = []\n",
+    "for prd in df_product['url']:\n",
+    "    hour_1 = int(prd[0].split('/')[-1].split('_')[4].split('T')[1])\n",
+    "    hour_2 = int(prd[1].split('/')[-1].split('_')[4].split('T')[1])\n",
+    "    \n",
+    "    if hour_1 > hour_2:\n",
+    "        tmp_list_product_path.append(prd[0])\n",
+    "    else:\n",
+    "        tmp_list_product_path.append(prd[1])\n",
+    "\n",
+    "list_product_path = []\n",
+    "for path_url in tmp_list_product_path:\n",
+    "    list_product_path.append(path_url[8:])\n",
+    "\n",
+    "prod_payload = \"[\\\"\"+\",\\\"\".join(list_product_path)+\"\\\"]\"\n",
+    "print(prod_payload)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "0142ecbc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Test Gdal"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "ae1c9c71",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Creating output file that is 4680P x 5400L.\n",
+      "0...10...20...30...40...50...60...70...80...90...100 - done.\n",
+      "\n",
+      "[02/28 16:51:44] [INFO dem.py] Bounds: -156.0 18.8 -154.7 20.3\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] Creating /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] Fetching remote tiles...\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] Running GDAL command:\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] gdalwarp /vsicurl/https://raw.githubusercontent.com/scottstanie/sardem/master/sardem/data/cop_global.vrt /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif -of GTiff -ot Int16 -te -156 18.8000000000000007 -154.699999999999989 20.3000000000000007 -tr 0.000277777777777777778 0.000277777777777777778 -s_srs \"epsg:4326+3855\" -t_srs \"epsg:4326\" -wo NUM_THREADS=4 -r nearest -wm 5000 -multi\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!conda run -n maap sardem --bbox -156 18.8 -154.7 20.3 --data-source COP -o \"/projects/treeclassificationdemo/driver/maap_utils/L1_MSI_pixel_value_Composite_123.tif\" --output-format GTiff\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Maap",
+   "language": "python",
+   "name": "maap"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
+%% Cell type:markdown id:1a70970d tags:
+
+# <center> Tree Classification Demo </center>
+
+%% Cell type:markdown id:bf3c2a51 tags:
+
+<center>Tests for geopandas and gdal<center>
+
+%% Cell type:markdown id:c55216cb tags:
+
+## Import Packages
+
+%% Cell type:code id:4d9291fa tags:
+
+``` python
+from datetime import datetime
+import json
+import time
+import configparser
+import requests
+# On NASA , install with pip install geopandas
+# On ESA; use a PolinSAR stack ( geopandas already embedded)
+import geopandas as gpd
+import pandas as pd
+from creodias_finder import query
+from shapely.geometry import Polygon,shape
+```
+
+%% Cell type:markdown id:711e5ecd tags:
+
+## Define Functions
+
+%% Cell type:code id:2b694047 tags:
+
+``` python
+def __get_result_S1( geometry_search, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date):
+    '''
+        Recupere dans un dataframe les produits S1 qui intersectent la zone de recherche
+
+        :geometry_search: geometrie de la zone de recherche
+        :str_plateformeS1: nom de la plateforme
+        :str_product_type: nom du product type
+        :str_sensor_mode: nom du sensor mode
+        :start_date: date debut interval recherche au format datetime
+        :end_date: date fin interval recherche au format datetime
+
+
+        return: df_groupby
+        :rtype: dataframe
+    '''
+
+    # liste des produits de l'api creodias
+    results = query.query(
+        str_plateformeS1,
+        start_date=start_date,
+        end_date=end_date,
+        productType=str_product_type,
+        sensorMode=str_sensor_mode,
+        status="ONLINE",
+        geometry=geometry_search
+    )
+
+    # init des listes des parametres a conserver
+    list_title = []
+    list_date = []
+    list_orbit = []
+    list_orbitDirection = []
+    list_geom = []
+    list_url = []
+
+    # remplissage des listes avec les parametres des produits du results de l'api
+    for idproduct, dict_product in results.items():
+        list_title.append(dict_product['properties']['title'])
+        list_orbit.append(dict_product['properties']['relativeOrbitNumber'])
+        list_orbitDirection.append(dict_product['properties']['orbitDirection'])
+        list_geom.append(shape(dict_product['geometry']))
+        list_url.append(dict_product['properties']['productIdentifier'])
+        list_date.append(dict_product['properties']['title'][17:25])
+
+    # genere le gdf avec les produits s1
+    gdf_product = gpd.GeoDataFrame({'title' : list_title, 'date' : list_date, 'orbit' : list_orbit, 'direction' : list_orbitDirection,'geometry' : list_geom, 'url' : list_url}, crs = "4326")
+    # regroupe les produits qui ont les memes parametres de date, orbit et direction
+    df_groupby = gdf_product.groupby(['date', 'orbit', 'direction']).agg({'title' : list, 'url' : list, 'geometry' : list}).reset_index()
+
+    return df_groupby
+
+```
+
+%% Cell type:markdown id:2573ab84 tags:
+
+## Define the study area or list of tile
+
+%% Cell type:code id:7e14efe8 tags:
+
+``` python
+search_zone = [[4.751930185604931,45.37522170186796],[4.468812157001305,45.24092464324643],[4.018935832120382,44.88158298080388],[3.852035966569818,44.75014456444579],[3.898047329546759,44.56923769773521],[4.038870891160542,44.31329708744024],[4.241954580160842,44.26894961414283],[4.674279531570155,44.26246269728098],[4.882500597010154,44.8652889083827],[4.905098845459158,45.06277528749476],[4.782524828980907,45.368587240900965],[4.751930185604931,45.37522170186796]]
+search_poly = Polygon(search_zone)
+```
+
+%% Cell type:markdown id:9b8ee178 tags:
+
+## Search S1 products
+
+%% Cell type:code id:f7fd2a1c tags:
+
+``` python
+# parametres de recherche
+str_plateformeS1 = 'Sentinel1'
+str_product_type = 'GRD'
+str_sensor_mode = 'IW'
+start_date = datetime(2022, 6, 3)
+end_date = datetime(2023, 1, 31)
+```
+
+%% Cell type:code id:3cb6aa8f tags:
+
+``` python
+
+df_product = __get_result_S1( search_poly, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date)
+```
+
+%% Output
+
+    query_url http://datahub.creodias.eu/resto/api/collections/Sentinel1/search.json?maxRecords=1000&startDate=2022-06-03T00%3A00%3A00&completionDate=2023-01-31T23%3A59%3A59&geometry=POLYGON+%28%284.751930185604931+45.37522170186796%2C+4.468812157001305+45.24092464324643%2C+4.018935832120382+44.88158298080388%2C+3.852035966569818+44.75014456444579%2C+3.898047329546759+44.56923769773521%2C+4.038870891160542+44.31329708744024%2C+4.241954580160842+44.26894961414283%2C+4.674279531570155+44.26246269728098%2C+4.882500597010154+44.8652889083827%2C+4.905098845459158+45.06277528749476%2C+4.782524828980907+45.368587240900965%2C+4.751930185604931+45.37522170186796%29%29&status=ONLINE&productType=GRD&sensorMode=IW
+    <Response [200]>
+
+%% Cell type:code id:568856bd tags:
+
+``` python
+df_product
+df_product = df_product[df_product['orbit']==37]
+df_product
+print(len(df_product))
+```
+
+%% Output
+
+    20
+
+%% Cell type:markdown id:f85d0273 tags:
+
+## Extract list of URL
+
+%% Cell type:code id:6cfbf9c7 tags:
+
+``` python
+tmp_list_product_path = []
+for prd in df_product['url']:
+    hour_1 = int(prd[0].split('/')[-1].split('_')[4].split('T')[1])
+    hour_2 = int(prd[1].split('/')[-1].split('_')[4].split('T')[1])
+
+    if hour_1 > hour_2:
+        tmp_list_product_path.append(prd[0])
+    else:
+        tmp_list_product_path.append(prd[1])
+
+list_product_path = []
+for path_url in tmp_list_product_path:
+    list_product_path.append(path_url[8:])
+
+prod_payload = "[\""+",\"".join(list_product_path)+"\"]"
+print(prod_payload)
+```
+
+%% Output
+
+    ["Sentinel-1/SAR/GRD/2022/06/04/S1A_IW_GRDH_1SDV_20220604T055236_20220604T055301_043509_0531E5_DC1B.SAFE,"Sentinel-1/SAR/GRD/2022/06/16/S1A_IW_GRDH_1SDV_20220616T055236_20220616T055301_043684_05371A_E51A.SAFE,"Sentinel-1/SAR/GRD/2022/06/28/S1A_IW_GRDH_1SDV_20220628T055237_20220628T055302_043859_053C5F_3096.SAFE,"Sentinel-1/SAR/GRD/2022/07/22/S1A_IW_GRDH_1SDV_20220722T055238_20220722T055303_044209_0546C9_677E.SAFE,"Sentinel-1/SAR/GRD/2022/08/03/S1A_IW_GRDH_1SDV_20220803T055239_20220803T055304_044384_054BF3_4ACD.SAFE,"Sentinel-1/SAR/GRD/2022/08/15/S1A_IW_GRDH_1SDV_20220815T055240_20220815T055305_044559_05516B_B0D3.SAFE,"Sentinel-1/SAR/GRD/2022/08/27/S1A_IW_GRDH_1SDV_20220827T055240_20220827T055305_044734_055755_77D7.SAFE,"Sentinel-1/SAR/GRD/2022/09/08/S1A_IW_GRDH_1SDV_20220908T055241_20220908T055306_044909_055D33_8C27.SAFE,"Sentinel-1/SAR/GRD/2022/09/20/S1A_IW_GRDH_1SDV_20220920T055241_20220920T055306_045084_056320_8ED8.SAFE,"Sentinel-1/SAR/GRD/2022/10/02/S1A_IW_GRDH_1SDV_20221002T055242_20221002T055307_045259_0568FD_84DA.SAFE,"Sentinel-1/SAR/GRD/2022/10/14/S1A_IW_GRDH_1SDV_20221014T055242_20221014T055307_045434_056EDB_346E.SAFE,"Sentinel-1/SAR/GRD/2022/10/26/S1A_IW_GRDH_1SDV_20221026T055242_20221026T055307_045609_05740C_5826.SAFE,"Sentinel-1/SAR/GRD/2022/11/07/S1A_IW_GRDH_1SDV_20221107T055241_20221107T055306_045784_0579F9_649C.SAFE,"Sentinel-1/SAR/GRD/2022/11/19/S1A_IW_GRDH_1SDV_20221119T055241_20221119T055306_045959_057FDC_E997.SAFE,"Sentinel-1/SAR/GRD/2022/12/01/S1A_IW_GRDH_1SDV_20221201T055240_20221201T055305_046134_0585CE_836F.SAFE,"Sentinel-1/SAR/GRD/2022/12/13/S1A_IW_GRDH_1SDV_20221213T055240_20221213T055305_046309_058BCE_F90F.SAFE,"Sentinel-1/SAR/GRD/2022/12/25/S1A_IW_GRDH_1SDV_20221225T055239_20221225T055304_046484_0591C3_7C2C.SAFE,"Sentinel-1/SAR/GRD/2023/01/06/S1A_IW_GRDH_1SDV_20230106T055239_20230106T055304_046659_0597A7_7ED7.SAFE,"Sentinel-1/SAR/GRD/2023/01/18/S1A_IW_GRDH_1SDV_20230118T055238_20230118T055303_046834_059D93_5C5F.SAFE,"Sentinel-1/SAR/GRD/2023/01/30/S1A_IW_GRDH_1SDV_20230130T055238_20230130T055303_047009_05A37A_61B6.SAFE"]
+
+%% Cell type:code id:0142ecbc tags:
+
+``` python
+## Test Gdal
+```
+
+%% Cell type:code id:ae1c9c71 tags:
+
+``` python
+!conda run -n maap sardem --bbox -156 18.8 -154.7 20.3 --data-source COP -o "/projects/treeclassificationdemo/driver/maap_utils/L1_MSI_pixel_value_Composite_123.tif" --output-format GTiff
+```
+
+%% Output
+
+    Creating output file that is 4680P x 5400L.
+    0...10...20...30...40...50...60...70...80...90...100 - done.
+    
+    [02/28 16:51:44] [INFO dem.py] Bounds: -156.0 18.8 -154.7 20.3
+    [02/28 16:51:44] [INFO cop_dem.py] Creating /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif
+    [02/28 16:51:44] [INFO cop_dem.py] Fetching remote tiles...
+    [02/28 16:51:44] [INFO cop_dem.py] Running GDAL command:
+    [02/28 16:51:44] [INFO cop_dem.py] gdalwarp /vsicurl/https://raw.githubusercontent.com/scottstanie/sardem/master/sardem/data/cop_global.vrt /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif -of GTiff -ot Int16 -te -156 18.8000000000000007 -154.699999999999989 20.3000000000000007 -tr 0.000277777777777777778 0.000277777777777777778 -s_srs "epsg:4326+3855" -t_srs "epsg:4326" -wo NUM_THREADS=4 -r nearest -wm 5000 -multi
+    
--- a/maap_jupyter/maap_notebook.ipynb
+++ b/maap_jupyter/maap_notebook.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1a70970d",
+   "metadata": {},
+   "source": [
+    "# <center> Tree Classification Demo </center>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bf3c2a51",
+   "metadata": {},
+   "source": [
+    "<center>Tests for geopandas and gdal<center>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c55216cb",
+   "metadata": {},
+   "source": [
+    "## Import Packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4d9291fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "import json\n",
+    "import time\n",
+    "import configparser\n",
+    "import requests\n",
+    "# On NASA , install with pip install geopandas\n",
+    "# On ESA; use a PolinSAR stack ( geopandas already embedded) \n",
+    "import geopandas as gpd\n",
+    "import pandas as pd\n",
+    "from creodias_finder import query\n",
+    "from shapely.geometry import Polygon,shape\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "711e5ecd",
+   "metadata": {},
+   "source": [
+    "## Define Functions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "2b694047",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def __get_result_S1( geometry_search, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date):\n",
+    "    '''\n",
+    "        Recupere dans un dataframe les produits S1 qui intersectent la zone de recherche\n",
+    "\n",
+    "        :geometry_search: geometrie de la zone de recherche\n",
+    "        :str_plateformeS1: nom de la plateforme\n",
+    "        :str_product_type: nom du product type\n",
+    "        :str_sensor_mode: nom du sensor mode\n",
+    "        :start_date: date debut interval recherche au format datetime\n",
+    "        :end_date: date fin interval recherche au format datetime\n",
+    "\n",
+    "\n",
+    "        return: df_groupby\n",
+    "        :rtype: dataframe\n",
+    "    '''\n",
+    "\n",
+    "    # liste des produits de l'api creodias\n",
+    "    results = query.query(\n",
+    "        str_plateformeS1,\n",
+    "        start_date=start_date,\n",
+    "        end_date=end_date,\n",
+    "        productType=str_product_type,\n",
+    "        sensorMode=str_sensor_mode,\n",
+    "        status=\"ONLINE\",\n",
+    "        geometry=geometry_search\n",
+    "    )\n",
+    "\n",
+    "    # init des listes des parametres a conserver \n",
+    "    list_title = []\n",
+    "    list_date = []\n",
+    "    list_orbit = []\n",
+    "    list_orbitDirection = []\n",
+    "    list_geom = []\n",
+    "    list_url = []\n",
+    "\n",
+    "    # remplissage des listes avec les parametres des produits du results de l'api\n",
+    "    for idproduct, dict_product in results.items():\n",
+    "        list_title.append(dict_product['properties']['title'])\n",
+    "        list_orbit.append(dict_product['properties']['relativeOrbitNumber'])\n",
+    "        list_orbitDirection.append(dict_product['properties']['orbitDirection'])\n",
+    "        list_geom.append(shape(dict_product['geometry']))\n",
+    "        list_url.append(dict_product['properties']['productIdentifier'])\n",
+    "        list_date.append(dict_product['properties']['title'][17:25])\n",
+    "\n",
+    "    # genere le gdf avec les produits s1\n",
+    "    gdf_product = gpd.GeoDataFrame({'title' : list_title, 'date' : list_date, 'orbit' : list_orbit, 'direction' : list_orbitDirection,'geometry' : list_geom, 'url' : list_url}, crs = \"4326\")\n",
+    "    # regroupe les produits qui ont les memes parametres de date, orbit et direction\n",
+    "    df_groupby = gdf_product.groupby(['date', 'orbit', 'direction']).agg({'title' : list, 'url' : list, 'geometry' : list}).reset_index()\n",
+    "\n",
+    "    return df_groupby\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2573ab84",
+   "metadata": {},
+   "source": [
+    "## Define the study area or list of tile"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7e14efe8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search_zone = [[4.751930185604931,45.37522170186796],[4.468812157001305,45.24092464324643],[4.018935832120382,44.88158298080388],[3.852035966569818,44.75014456444579],[3.898047329546759,44.56923769773521],[4.038870891160542,44.31329708744024],[4.241954580160842,44.26894961414283],[4.674279531570155,44.26246269728098],[4.882500597010154,44.8652889083827],[4.905098845459158,45.06277528749476],[4.782524828980907,45.368587240900965],[4.751930185604931,45.37522170186796]]\n",
+    "search_poly = Polygon(search_zone)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9b8ee178",
+   "metadata": {},
+   "source": [
+    "## Search S1 products"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "f7fd2a1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# parametres de recherche\n",
+    "str_plateformeS1 = 'Sentinel1'\n",
+    "str_product_type = 'GRD'\n",
+    "str_sensor_mode = 'IW'\n",
+    "start_date = datetime(2022, 6, 3)\n",
+    "end_date = datetime(2023, 1, 31)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "3cb6aa8f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query_url http://datahub.creodias.eu/resto/api/collections/Sentinel1/search.json?maxRecords=1000&startDate=2022-06-03T00%3A00%3A00&completionDate=2023-01-31T23%3A59%3A59&geometry=POLYGON+%28%284.751930185604931+45.37522170186796%2C+4.468812157001305+45.24092464324643%2C+4.018935832120382+44.88158298080388%2C+3.852035966569818+44.75014456444579%2C+3.898047329546759+44.56923769773521%2C+4.038870891160542+44.31329708744024%2C+4.241954580160842+44.26894961414283%2C+4.674279531570155+44.26246269728098%2C+4.882500597010154+44.8652889083827%2C+4.905098845459158+45.06277528749476%2C+4.782524828980907+45.368587240900965%2C+4.751930185604931+45.37522170186796%29%29&status=ONLINE&productType=GRD&sensorMode=IW\n",
+      "<Response [200]>\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "df_product = __get_result_S1( search_poly, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "568856bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "20\n"
+     ]
+    }
+   ],
+   "source": [
+    "df_product\n",
+    "df_product = df_product[df_product['orbit']==37]\n",
+    "df_product\n",
+    "print(len(df_product))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f85d0273",
+   "metadata": {},
+   "source": [
+    "## Extract list of URL "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "6cfbf9c7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[\"Sentinel-1/SAR/GRD/2022/06/04/S1A_IW_GRDH_1SDV_20220604T055236_20220604T055301_043509_0531E5_DC1B.SAFE,\"Sentinel-1/SAR/GRD/2022/06/16/S1A_IW_GRDH_1SDV_20220616T055236_20220616T055301_043684_05371A_E51A.SAFE,\"Sentinel-1/SAR/GRD/2022/06/28/S1A_IW_GRDH_1SDV_20220628T055237_20220628T055302_043859_053C5F_3096.SAFE,\"Sentinel-1/SAR/GRD/2022/07/22/S1A_IW_GRDH_1SDV_20220722T055238_20220722T055303_044209_0546C9_677E.SAFE,\"Sentinel-1/SAR/GRD/2022/08/03/S1A_IW_GRDH_1SDV_20220803T055239_20220803T055304_044384_054BF3_4ACD.SAFE,\"Sentinel-1/SAR/GRD/2022/08/15/S1A_IW_GRDH_1SDV_20220815T055240_20220815T055305_044559_05516B_B0D3.SAFE,\"Sentinel-1/SAR/GRD/2022/08/27/S1A_IW_GRDH_1SDV_20220827T055240_20220827T055305_044734_055755_77D7.SAFE,\"Sentinel-1/SAR/GRD/2022/09/08/S1A_IW_GRDH_1SDV_20220908T055241_20220908T055306_044909_055D33_8C27.SAFE,\"Sentinel-1/SAR/GRD/2022/09/20/S1A_IW_GRDH_1SDV_20220920T055241_20220920T055306_045084_056320_8ED8.SAFE,\"Sentinel-1/SAR/GRD/2022/10/02/S1A_IW_GRDH_1SDV_20221002T055242_20221002T055307_045259_0568FD_84DA.SAFE,\"Sentinel-1/SAR/GRD/2022/10/14/S1A_IW_GRDH_1SDV_20221014T055242_20221014T055307_045434_056EDB_346E.SAFE,\"Sentinel-1/SAR/GRD/2022/10/26/S1A_IW_GRDH_1SDV_20221026T055242_20221026T055307_045609_05740C_5826.SAFE,\"Sentinel-1/SAR/GRD/2022/11/07/S1A_IW_GRDH_1SDV_20221107T055241_20221107T055306_045784_0579F9_649C.SAFE,\"Sentinel-1/SAR/GRD/2022/11/19/S1A_IW_GRDH_1SDV_20221119T055241_20221119T055306_045959_057FDC_E997.SAFE,\"Sentinel-1/SAR/GRD/2022/12/01/S1A_IW_GRDH_1SDV_20221201T055240_20221201T055305_046134_0585CE_836F.SAFE,\"Sentinel-1/SAR/GRD/2022/12/13/S1A_IW_GRDH_1SDV_20221213T055240_20221213T055305_046309_058BCE_F90F.SAFE,\"Sentinel-1/SAR/GRD/2022/12/25/S1A_IW_GRDH_1SDV_20221225T055239_20221225T055304_046484_0591C3_7C2C.SAFE,\"Sentinel-1/SAR/GRD/2023/01/06/S1A_IW_GRDH_1SDV_20230106T055239_20230106T055304_046659_0597A7_7ED7.SAFE,\"Sentinel-1/SAR/GRD/2023/01/18/S1A_IW_GRDH_1SDV_20230118T055238_20230118T055303_046834_059D93_5C5F.SAFE,\"Sentinel-1/SAR/GRD/2023/01/30/S1A_IW_GRDH_1SDV_20230130T055238_20230130T055303_047009_05A37A_61B6.SAFE\"]\n"
+     ]
+    }
+   ],
+   "source": [
+    "tmp_list_product_path = []\n",
+    "for prd in df_product['url']:\n",
+    "    hour_1 = int(prd[0].split('/')[-1].split('_')[4].split('T')[1])\n",
+    "    hour_2 = int(prd[1].split('/')[-1].split('_')[4].split('T')[1])\n",
+    "    \n",
+    "    if hour_1 > hour_2:\n",
+    "        tmp_list_product_path.append(prd[0])\n",
+    "    else:\n",
+    "        tmp_list_product_path.append(prd[1])\n",
+    "\n",
+    "list_product_path = []\n",
+    "for path_url in tmp_list_product_path:\n",
+    "    list_product_path.append(path_url[8:])\n",
+    "\n",
+    "prod_payload = \"[\\\"\"+\",\\\"\".join(list_product_path)+\"\\\"]\"\n",
+    "print(prod_payload)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "0142ecbc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Test Gdal"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "ae1c9c71",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Creating output file that is 4680P x 5400L.\n",
+      "0...10...20...30...40...50...60...70...80...90...100 - done.\n",
+      "\n",
+      "[02/28 16:51:44] [INFO dem.py] Bounds: -156.0 18.8 -154.7 20.3\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] Creating /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] Fetching remote tiles...\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] Running GDAL command:\n",
+      "[02/28 16:51:44] [INFO cop_dem.py] gdalwarp /vsicurl/https://raw.githubusercontent.com/scottstanie/sardem/master/sardem/data/cop_global.vrt /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif -of GTiff -ot Int16 -te -156 18.8000000000000007 -154.699999999999989 20.3000000000000007 -tr 0.000277777777777777778 0.000277777777777777778 -s_srs \"epsg:4326+3855\" -t_srs \"epsg:4326\" -wo NUM_THREADS=4 -r nearest -wm 5000 -multi\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!conda run -n maap sardem --bbox -156 18.8 -154.7 20.3 --data-source COP -o \"/projects/treeclassificationdemo/driver/maap_utils/L1_MSI_pixel_value_Composite_123.tif\" --output-format GTiff\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Maap",
+   "language": "python",
+   "name": "maap"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
+%% Cell type:markdown id:1a70970d tags:
+
+# <center> Tree Classification Demo </center>
+
+%% Cell type:markdown id:bf3c2a51 tags:
+
+<center>Tests for geopandas and gdal<center>
+
+%% Cell type:markdown id:c55216cb tags:
+
+## Import Packages
+
+%% Cell type:code id:4d9291fa tags:
+
+``` python
+from datetime import datetime
+import json
+import time
+import configparser
+import requests
+# On NASA , install with pip install geopandas
+# On ESA; use a PolinSAR stack ( geopandas already embedded)
+import geopandas as gpd
+import pandas as pd
+from creodias_finder import query
+from shapely.geometry import Polygon,shape
+```
+
+%% Cell type:markdown id:711e5ecd tags:
+
+## Define Functions
+
+%% Cell type:code id:2b694047 tags:
+
+``` python
+def __get_result_S1( geometry_search, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date):
+    '''
+        Recupere dans un dataframe les produits S1 qui intersectent la zone de recherche
+
+        :geometry_search: geometrie de la zone de recherche
+        :str_plateformeS1: nom de la plateforme
+        :str_product_type: nom du product type
+        :str_sensor_mode: nom du sensor mode
+        :start_date: date debut interval recherche au format datetime
+        :end_date: date fin interval recherche au format datetime
+
+
+        return: df_groupby
+        :rtype: dataframe
+    '''
+
+    # liste des produits de l'api creodias
+    results = query.query(
+        str_plateformeS1,
+        start_date=start_date,
+        end_date=end_date,
+        productType=str_product_type,
+        sensorMode=str_sensor_mode,
+        status="ONLINE",
+        geometry=geometry_search
+    )
+
+    # init des listes des parametres a conserver
+    list_title = []
+    list_date = []
+    list_orbit = []
+    list_orbitDirection = []
+    list_geom = []
+    list_url = []
+
+    # remplissage des listes avec les parametres des produits du results de l'api
+    for idproduct, dict_product in results.items():
+        list_title.append(dict_product['properties']['title'])
+        list_orbit.append(dict_product['properties']['relativeOrbitNumber'])
+        list_orbitDirection.append(dict_product['properties']['orbitDirection'])
+        list_geom.append(shape(dict_product['geometry']))
+        list_url.append(dict_product['properties']['productIdentifier'])
+        list_date.append(dict_product['properties']['title'][17:25])
+
+    # genere le gdf avec les produits s1
+    gdf_product = gpd.GeoDataFrame({'title' : list_title, 'date' : list_date, 'orbit' : list_orbit, 'direction' : list_orbitDirection,'geometry' : list_geom, 'url' : list_url}, crs = "4326")
+    # regroupe les produits qui ont les memes parametres de date, orbit et direction
+    df_groupby = gdf_product.groupby(['date', 'orbit', 'direction']).agg({'title' : list, 'url' : list, 'geometry' : list}).reset_index()
+
+    return df_groupby
+
+```
+
+%% Cell type:markdown id:2573ab84 tags:
+
+## Define the study area or list of tile
+
+%% Cell type:code id:7e14efe8 tags:
+
+``` python
+search_zone = [[4.751930185604931,45.37522170186796],[4.468812157001305,45.24092464324643],[4.018935832120382,44.88158298080388],[3.852035966569818,44.75014456444579],[3.898047329546759,44.56923769773521],[4.038870891160542,44.31329708744024],[4.241954580160842,44.26894961414283],[4.674279531570155,44.26246269728098],[4.882500597010154,44.8652889083827],[4.905098845459158,45.06277528749476],[4.782524828980907,45.368587240900965],[4.751930185604931,45.37522170186796]]
+search_poly = Polygon(search_zone)
+```
+
+%% Cell type:markdown id:9b8ee178 tags:
+
+## Search S1 products
+
+%% Cell type:code id:f7fd2a1c tags:
+
+``` python
+# parametres de recherche
+str_plateformeS1 = 'Sentinel1'
+str_product_type = 'GRD'
+str_sensor_mode = 'IW'
+start_date = datetime(2022, 6, 3)
+end_date = datetime(2023, 1, 31)
+```
+
+%% Cell type:code id:3cb6aa8f tags:
+
+``` python
+
+df_product = __get_result_S1( search_poly, str_plateformeS1, str_product_type, str_sensor_mode, start_date, end_date)
+```
+
+%% Output
+
+    query_url http://datahub.creodias.eu/resto/api/collections/Sentinel1/search.json?maxRecords=1000&startDate=2022-06-03T00%3A00%3A00&completionDate=2023-01-31T23%3A59%3A59&geometry=POLYGON+%28%284.751930185604931+45.37522170186796%2C+4.468812157001305+45.24092464324643%2C+4.018935832120382+44.88158298080388%2C+3.852035966569818+44.75014456444579%2C+3.898047329546759+44.56923769773521%2C+4.038870891160542+44.31329708744024%2C+4.241954580160842+44.26894961414283%2C+4.674279531570155+44.26246269728098%2C+4.882500597010154+44.8652889083827%2C+4.905098845459158+45.06277528749476%2C+4.782524828980907+45.368587240900965%2C+4.751930185604931+45.37522170186796%29%29&status=ONLINE&productType=GRD&sensorMode=IW
+    <Response [200]>
+
+%% Cell type:code id:568856bd tags:
+
+``` python
+df_product
+df_product = df_product[df_product['orbit']==37]
+df_product
+print(len(df_product))
+```
+
+%% Output
+
+    20
+
+%% Cell type:markdown id:f85d0273 tags:
+
+## Extract list of URL
+
+%% Cell type:code id:6cfbf9c7 tags:
+
+``` python
+tmp_list_product_path = []
+for prd in df_product['url']:
+    hour_1 = int(prd[0].split('/')[-1].split('_')[4].split('T')[1])
+    hour_2 = int(prd[1].split('/')[-1].split('_')[4].split('T')[1])
+
+    if hour_1 > hour_2:
+        tmp_list_product_path.append(prd[0])
+    else:
+        tmp_list_product_path.append(prd[1])
+
+list_product_path = []
+for path_url in tmp_list_product_path:
+    list_product_path.append(path_url[8:])
+
+prod_payload = "[\""+",\"".join(list_product_path)+"\"]"
+print(prod_payload)
+```
+
+%% Output
+
+    ["Sentinel-1/SAR/GRD/2022/06/04/S1A_IW_GRDH_1SDV_20220604T055236_20220604T055301_043509_0531E5_DC1B.SAFE,"Sentinel-1/SAR/GRD/2022/06/16/S1A_IW_GRDH_1SDV_20220616T055236_20220616T055301_043684_05371A_E51A.SAFE,"Sentinel-1/SAR/GRD/2022/06/28/S1A_IW_GRDH_1SDV_20220628T055237_20220628T055302_043859_053C5F_3096.SAFE,"Sentinel-1/SAR/GRD/2022/07/22/S1A_IW_GRDH_1SDV_20220722T055238_20220722T055303_044209_0546C9_677E.SAFE,"Sentinel-1/SAR/GRD/2022/08/03/S1A_IW_GRDH_1SDV_20220803T055239_20220803T055304_044384_054BF3_4ACD.SAFE,"Sentinel-1/SAR/GRD/2022/08/15/S1A_IW_GRDH_1SDV_20220815T055240_20220815T055305_044559_05516B_B0D3.SAFE,"Sentinel-1/SAR/GRD/2022/08/27/S1A_IW_GRDH_1SDV_20220827T055240_20220827T055305_044734_055755_77D7.SAFE,"Sentinel-1/SAR/GRD/2022/09/08/S1A_IW_GRDH_1SDV_20220908T055241_20220908T055306_044909_055D33_8C27.SAFE,"Sentinel-1/SAR/GRD/2022/09/20/S1A_IW_GRDH_1SDV_20220920T055241_20220920T055306_045084_056320_8ED8.SAFE,"Sentinel-1/SAR/GRD/2022/10/02/S1A_IW_GRDH_1SDV_20221002T055242_20221002T055307_045259_0568FD_84DA.SAFE,"Sentinel-1/SAR/GRD/2022/10/14/S1A_IW_GRDH_1SDV_20221014T055242_20221014T055307_045434_056EDB_346E.SAFE,"Sentinel-1/SAR/GRD/2022/10/26/S1A_IW_GRDH_1SDV_20221026T055242_20221026T055307_045609_05740C_5826.SAFE,"Sentinel-1/SAR/GRD/2022/11/07/S1A_IW_GRDH_1SDV_20221107T055241_20221107T055306_045784_0579F9_649C.SAFE,"Sentinel-1/SAR/GRD/2022/11/19/S1A_IW_GRDH_1SDV_20221119T055241_20221119T055306_045959_057FDC_E997.SAFE,"Sentinel-1/SAR/GRD/2022/12/01/S1A_IW_GRDH_1SDV_20221201T055240_20221201T055305_046134_0585CE_836F.SAFE,"Sentinel-1/SAR/GRD/2022/12/13/S1A_IW_GRDH_1SDV_20221213T055240_20221213T055305_046309_058BCE_F90F.SAFE,"Sentinel-1/SAR/GRD/2022/12/25/S1A_IW_GRDH_1SDV_20221225T055239_20221225T055304_046484_0591C3_7C2C.SAFE,"Sentinel-1/SAR/GRD/2023/01/06/S1A_IW_GRDH_1SDV_20230106T055239_20230106T055304_046659_0597A7_7ED7.SAFE,"Sentinel-1/SAR/GRD/2023/01/18/S1A_IW_GRDH_1SDV_20230118T055238_20230118T055303_046834_059D93_5C5F.SAFE,"Sentinel-1/SAR/GRD/2023/01/30/S1A_IW_GRDH_1SDV_20230130T055238_20230130T055303_047009_05A37A_61B6.SAFE"]
+
+%% Cell type:code id:0142ecbc tags:
+
+``` python
+## Test Gdal
+```
+
+%% Cell type:code id:ae1c9c71 tags:
+
+``` python
+!conda run -n maap sardem --bbox -156 18.8 -154.7 20.3 --data-source COP -o "/projects/treeclassificationdemo/driver/maap_utils/L1_MSI_pixel_value_Composite_123.tif" --output-format GTiff
+```
+
+%% Output
+
+    Creating output file that is 4680P x 5400L.
+    0...10...20...30...40...50...60...70...80...90...100 - done.
+    
+    [02/28 16:51:44] [INFO dem.py] Bounds: -156.0 18.8 -154.7 20.3
+    [02/28 16:51:44] [INFO cop_dem.py] Creating /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif
+    [02/28 16:51:44] [INFO cop_dem.py] Fetching remote tiles...
+    [02/28 16:51:44] [INFO cop_dem.py] Running GDAL command:
+    [02/28 16:51:44] [INFO cop_dem.py] gdalwarp /vsicurl/https://raw.githubusercontent.com/scottstanie/sardem/master/sardem/data/cop_global.vrt /projects/treeclassificationdemo/driver/L1_MSI_pixel_value_Composite_123.tif -of GTiff -ot Int16 -te -156 18.8000000000000007 -154.699999999999989 20.3000000000000007 -tr 0.000277777777777777778 0.000277777777777777778 -s_srs "epsg:4326+3855" -t_srs "epsg:4326" -wo NUM_THREADS=4 -r nearest -wm 5000 -multi
+    
--- a/maap_jupyter/maap_utils/.ipynb_checkpoints/L1_MSI_pixel_value_Composite_123-checkpoint.tif
+++ b/maap_jupyter/maap_utils/.ipynb_checkpoints/L1_MSI_pixel_value_Composite_123-checkpoint.tif
--- a/maap_jupyter/maap_utils/L1_MSI_pixel_value_Composite_123.tif
+++ b/maap_jupyter/maap_utils/L1_MSI_pixel_value_Composite_123.tif