microsoft · TomAugspurger · Apr 6, 2023 · Apr 3, 2023 · Apr 3, 2023 · Apr 3, 2023
diff --git a/datasets/aster/collection/template.json b/datasets/aster/collection/template.json
@@ -492,6 +492,7 @@
     },
     "stac_version": "1.0.0",
     "msft:container": "aster",
+    "msft:region": "westeurope",
     "stac_extensions": [
         "https://stac-extensions.github.io/item-assets/v1.0.0/schema.json",
         "https://stac-extensions.github.io/table/v1.2.0/schema.json"

diff --git a/datasets/chesapeake_lulc/collection/chesapeake-lc-13/template.json b/datasets/chesapeake_lulc/collection/chesapeake-lc-13/template.json
@@ -38,6 +38,7 @@
     "msft:short_description": "Chesapeake Bay Watershed land cover product with 13 classes at 1m resolution.",
     "msft:storage_account": "landcoverdata",
     "msft:container": "chesapeake",
+    "msft:region": "westeurope",
     "msft:group_id": "chesapeake-lulc",
     "providers": [
         {

diff --git a/datasets/chesapeake_lulc/collection/chesapeake-lc-7/template.json b/datasets/chesapeake_lulc/collection/chesapeake-lc-7/template.json
@@ -32,6 +32,7 @@
     "msft:short_description": "Chesapeake Bay Watershed land cover product with 7 classes at 1m resolution.",
     "msft:storage_account": "landcoverdata",
     "msft:container": "chesapeake",
+    "msft:region": "westeurope",
     "msft:group_id": "chesapeake-lulc",
     "providers": [
         {

diff --git a/datasets/chesapeake_lulc/collection/chesapeake-lu/template.json b/datasets/chesapeake_lulc/collection/chesapeake-lu/template.json
@@ -32,6 +32,7 @@
     "msft:short_description": "Chesapeake Bay Watershed land use product with 17 classes at 1m resolution.",
     "msft:storage_account": "landcoverdata",
     "msft:container": "chesapeake",
+    "msft:region": "westeurope",
     "msft:group_id": "chesapeake-lulc",
     "providers": [
         {

diff --git a/datasets/cil-gdpcir/collection/cil-gdpcir-cc-by-sa/template.json b/datasets/cil-gdpcir/collection/cil-gdpcir-cc-by-sa/template.json
@@ -28,6 +28,7 @@
   ],
   "msft:storage_account": "rhgeuwest",
   "msft:container": "cil-gdpcir",
+  "msft:region": "westeurope",
   "msft:short_description": "Climate Impact Lab Global Downscaled Projections for Climate Impacts Research (CC-BY-SA-4.0)",
   "msft:group_id": "cil-gdpcir",
   "sci:doi": "10.5194/egusphere-2022-1513",

diff --git a/datasets/cil-gdpcir/collection/cil-gdpcir-cc-by/template.json b/datasets/cil-gdpcir/collection/cil-gdpcir-cc-by/template.json
@@ -28,6 +28,7 @@
   ],
   "msft:storage_account": "rhgeuwest",
   "msft:container": "cil-gdpcir",
+  "msft:region": "westeurope",
   "msft:short_description": "Climate Impact Lab Global Downscaled Projections for Climate Impacts Research (CC-BY-4.0)",
   "msft:group_id": "cil-gdpcir",
   "sci:doi": "10.5194/egusphere-2022-1513",

diff --git a/datasets/cil-gdpcir/collection/cil-gdpcir-cc0/template.json b/datasets/cil-gdpcir/collection/cil-gdpcir-cc0/template.json
@@ -28,6 +28,7 @@
   ],
   "msft:storage_account": "rhgeuwest",
   "msft:container": "cil-gdpcir",
+  "msft:region": "westeurope",
   "msft:short_description": "Climate Impact Lab Global Downscaled Projections for Climate Impacts Research (CC0-1.0)",
   "msft:group_id": "cil-gdpcir",
   "sci:doi": "10.5194/egusphere-2022-1513",

diff --git a/datasets/deltaresfloods/collection/template.json b/datasets/deltaresfloods/collection/template.json
@@ -150,6 +150,7 @@
         }
     },
     "msft:container": "floods",
+    "msft:region": "westeurope",
     "cube:dimensions": {
         "lat": {
             "axis": "y",

diff --git a/datasets/eclipse/collection/template.json b/datasets/eclipse/collection/template.json
@@ -24,6 +24,7 @@
   ],
   "msft:short_description": "A network of low-cost air quality sensing network for cities and led by the Urban Innovation Group at Microsoft Research",
   "msft:container": "eclipse",
+  "msft:region": "westeurope",
   "msft:storage_account": "ai4edataeuwest",
   "table:columns": [
     {

diff --git a/datasets/era5-pds/collection/template.json b/datasets/era5-pds/collection/template.json
@@ -29,6 +29,7 @@
   ],
   "msft:storage_account": "cpdataeuwest",
   "msft:container": "era5",
+  "msft:region": "westeurope",
   "msft:short_description": "A comprehensive reanalysis, which assimilates as many observations as possible in the upper air and near surface.",
   "cube:variables": {
     "air_pressure_at_mean_sea_level": {

diff --git a/datasets/esa-cci-lc/collection/esa-cci-lc-netcdf/template.json b/datasets/esa-cci-lc/collection/esa-cci-lc-netcdf/template.json
@@ -60,6 +60,7 @@
     "msft:short_description": "ESA CCI global land cover maps in NetCDF format",
     "msft:storage_account": "landcoverdata",
     "msft:container": "esa-cci-lc",
+    "msft:region": "westeurope",
     "msft:group_id": "esa-cci-lc",
     "providers": [
         {

diff --git a/datasets/esa-cci-lc/collection/esa-cci-lc/template.json b/datasets/esa-cci-lc/collection/esa-cci-lc/template.json
@@ -63,6 +63,7 @@
     "msft:short_description": "Tiled ESA CCI global land cover maps in COG format",
     "msft:storage_account": "landcoverdata",
     "msft:container": "esa-cci-lc",
+    "msft:region": "westeurope",
     "msft:group_id": "esa-cci-lc",
     "providers": [
         {

diff --git a/datasets/fws-nwi/collection/template.json b/datasets/fws-nwi/collection/template.json
@@ -45,6 +45,7 @@
   "msft:short_description": "Vector dataset containing wetlands boundaries and identification across the United States.",
   "msft:storage_account": "ai4edataeuwest",
   "msft:container": "fws-nwi",
+  "msft:region": "westeurope",
   "title": "FWS National Wetlands Inventory",
   "extent": {
     "spatial": {

diff --git a/datasets/goes/goes-cmi/collection/template.json b/datasets/goes/goes-cmi/collection/template.json
@@ -27,6 +27,7 @@
     "msft:short_description": "High temporal cadence cloud and moisture imagery over the Western Hemisphere from the Advanced Baseline Imager (ABI) instrument.",
     "msft:storage_account": "goeseuwest",
     "msft:container": "noaa-goes-cogs",
+    "msft:region": "westeurope",
     "msft:group_id": "goes",
     "providers": [
         {

diff --git a/datasets/goes/goes-glm/collection/template.json b/datasets/goes/goes-glm/collection/template.json
@@ -52,6 +52,7 @@
     "msft:short_description": "Continuous lightning detection over the Western Hemisphere from the Geostationary Lightning Mapper (GLM) instrument.",
     "msft:storage_account": "goeseuwest",
     "msft:container": "noaa-goes-geoparquet",
+    "msft:region": "westeurope",
     "msft:group_id": "goes",
     "providers": [
         {

diff --git a/datasets/io-biodiversity/collection/template.json b/datasets/io-biodiversity/collection/template.json
@@ -31,6 +31,7 @@
     "msft:short_description": "Global terrestrial biodiversity intactness at 100m resolution for years 2017-2020",
     "msft:storage_account": "pcdata01euw",
     "msft:container": "impact",
+    "msft:region": "westeurope",
     "providers": [
         {
             "name": "Impact Observatory",

diff --git a/datasets/io-land-cover/collection/io-lulc-9-class/template.json b/datasets/io-land-cover/collection/io-lulc-9-class/template.json
@@ -33,6 +33,7 @@
   "msft:short_description": "Global land cover information with 9 classes for for 2017-2022 at 10m resolution",
   "msft:storage_account": "ai4edataeuwest",
   "msft:container": "io-lulc",
+  "msft:region": "westeurope",
   "msft:group_id": "io-land-cover",
   "providers": [
     {

diff --git a/datasets/io-land-cover/collection/io-lulc/template.json b/datasets/io-land-cover/collection/io-lulc/template.json
@@ -33,6 +33,7 @@
   "msft:short_description": "Global land cover information for 2020 at 10m resolution",
   "msft:storage_account": "ai4edataeuwest",
   "msft:container": "io-lulc",
+  "msft:region": "westeurope",
   "msft:group_id": "io-land-cover",
   "providers": [
     {

diff --git a/datasets/ms-buildings/collection/template.json b/datasets/ms-buildings/collection/template.json
@@ -37,6 +37,7 @@
   ],
   "msft:storage_account": "bingmlbuildings",
   "msft:container": "footprints",
+  "msft:region": "westeurope",
   "msft:short_description": "Machine learning detected buildings footprints.",
   "title": "Microsoft Building Footprints",
   "extent": {

diff --git a/datasets/noaa-mrms-qpe/collection/noaa-mrms-qpe-1h-pass1/template.json b/datasets/noaa-mrms-qpe/collection/noaa-mrms-qpe-1h-pass1/template.json
@@ -43,6 +43,7 @@
     "msft:short_description": "Integrated multi-sensor cumulative precipitation estimate for the past hour with a 1-hour latency.",
     "msft:storage_account": "mrms",
     "msft:container": "mrms-cogs",
+    "msft:region": "westeurope",
     "msft:group_id": "noaa-mrms-qpe",
     "providers": [
         {

diff --git a/datasets/noaa-mrms-qpe/collection/noaa-mrms-qpe-1h-pass2/template.json b/datasets/noaa-mrms-qpe/collection/noaa-mrms-qpe-1h-pass2/template.json
@@ -43,6 +43,7 @@
     "msft:short_description": "Integrated multi-sensor cumulative precipitation estimate for the past hour with a 2-hour latency.",
     "msft:storage_account": "mrms",
     "msft:container": "mrms-cogs",
+    "msft:region": "westeurope",
     "msft:group_id": "noaa-mrms-qpe",
     "providers": [
         {

diff --git a/datasets/noaa-mrms-qpe/collection/noaa-mrms-qpe-24h-pass2/template.json b/datasets/noaa-mrms-qpe/collection/noaa-mrms-qpe-24h-pass2/template.json
@@ -43,6 +43,7 @@
     "msft:short_description": "Integrated multi-sensor cumulative precipitation estimate for the past 24 hours with a 2-hour latency.",
     "msft:storage_account": "mrms",
     "msft:container": "mrms-cogs",
+    "msft:region": "westeurope",
     "msft:group_id": "noaa-mrms-qpe",
     "providers": [
         {

diff --git a/datasets/noaa_nclimgrid/collection/noaa-nclimgrid-daily-prelim/template.json b/datasets/noaa_nclimgrid/collection/noaa-nclimgrid-daily-prelim/template.json
@@ -40,6 +40,7 @@
     "msft:short_description": "Preliminary gridded surface observations of daily temperature and precipitation for the continental United States",
     "msft:storage_account": "nclimgridwesteurope",
     "msft:container": "nclimgrid-cogs",
+    "msft:region": "westeurope",
     "msft:group_id": "noaa-nclimgrid",
     "providers": [
         {

diff --git a/datasets/noaa_nclimgrid/collection/noaa-nclimgrid-daily-scaled/template.json b/datasets/noaa_nclimgrid/collection/noaa-nclimgrid-daily-scaled/template.json
@@ -40,6 +40,7 @@
     "msft:short_description": "Gridded surface observations of daily temperature and precipitation for the continental United States scaled to match the corresponding monthly values.",
     "msft:storage_account": "nclimgridwesteurope",
     "msft:container": "nclimgrid-cogs",
+    "msft:region": "westeurope",
     "msft:group_id": "noaa-nclimgrid",
     "providers": [
         {

diff --git a/datasets/noaa_nclimgrid/collection/noaa-nclimgrid-monthly/template.json b/datasets/noaa_nclimgrid/collection/noaa-nclimgrid-monthly/template.json
@@ -41,6 +41,7 @@
     "msft:short_description": "Gridded surface observations of monthly temperature and precipitation for the continental United States",
     "msft:storage_account": "nclimgridwesteurope",
     "msft:container": "nclimgrid-cogs",
+    "msft:region": "westeurope",
     "msft:group_id": "noaa-nclimgrid",
     "providers": [
         {

diff --git a/datasets/sentinel-1-grd/collection.json b/datasets/sentinel-1-grd/collection.json
@@ -72,6 +72,7 @@
       }
     ],
     "msft:container": "s1-grd",
+    "msft:region": "westeurope",
     "msft:storage_account": "sentinel1euwest",
     "msft:short_description": "Sentinel-1 comprises a constellation of two polar-orbiting satellites, operating day and night performing C-band synthetic aperture radar imaging. Level-1 Ground Range Detected (GRD) products consist of focused SAR data that has been detected, multi-looked and projected to ground range using an Earth ellipsoid model.",
     "summaries": {

diff --git a/datasets/sentinel-1-rtc/collection/template.json b/datasets/sentinel-1-rtc/collection/template.json
@@ -7,6 +7,7 @@
   "description": "{{ collection.description }}",
   "msft:storage_account": "sentinel1euwestrtc",
   "msft:container": "sentinel1-grd-rtc",
+  "msft:region": "westeurope",
   "msft:requires_account": true,
   "msft:group_id": "sentinel-1",
   "license": "CC-BY-4.0",

diff --git a/datasets/sentinel-3/sentinel-3-olci-l2.json b/datasets/sentinel-3/sentinel-3-olci-l2.json
@@ -89,6 +89,7 @@
     }
   ],
   "msft:container": "sentinel-3",
+  "msft:region": "westeurope",
   "msft:storage_account": "sentinel3euwest",
   "msft:short_description": "The [Sentinel-3](https://sentinel.esa.int/web/sentinel/missions/sentinel-3) mission is composed of three versatile satellites designed to provide data continuity for the ERS, ENVISAT and SPOT satellites and to support operational land and ocean observation services. Level 2 OLCI products provide land, water, and atmospheric geophysical parameters computed for Full Resolution and Reduced Resolution.",
   "summaries": {

diff --git a/datasets/sentinel-3/sentinel-3-slstr-l2.json b/datasets/sentinel-3/sentinel-3-slstr-l2.json
@@ -73,6 +73,7 @@
     }
   ],
   "msft:container": "sentinel-3",
+  "msft:region": "westeurope",
   "msft:storage_account": "sentinel3euwest",
   "msft:short_description": "The [Sentinel-3](https://sentinel.esa.int/web/sentinel/missions/sentinel-3) mission is composed of three versatile satellites designed to provide data continuity for the ERS, ENVISAT and SPOT satellites and to support operational land and ocean observation services. The SLSTR Level-2 processing includes five types of products: WCT products providing the sea surface temperature for single and dual view, for two or three channels, WST products providing L2P sea surface temperature, following the GHRSST specifications, LST products providing land surface temperature, FRP products providing global (over land and water) fire radiative power, and AOD products providing global (over land and water) aerosol optical depth.",
   "summaries": {

diff --git a/datasets/sentinel-3/sentinel-3-sral-l2.json b/datasets/sentinel-3/sentinel-3-sral-l2.json
@@ -73,6 +73,7 @@
     }
   ],
   "msft:container": "sentinel-3",
+  "msft:region": "westeurope",
   "msft:storage_account": "sentinel3euwest",
   "msft:short_description": "The [Sentinel-3](https://sentinel.esa.int/web/sentinel/missions/sentinel-3) mission is composed of three versatile satellites designed to provide data continuity for the ERS, ENVISAT and SPOT satellites and to support operational land and ocean observation services. Level-2 SRAL products provide geophysical parameters of ocean topography.",
   "summaries": {

diff --git a/datasets/sentinel-3/sentinel-3-synergy-l2.json b/datasets/sentinel-3/sentinel-3-synergy-l2.json
@@ -78,6 +78,7 @@
     }
   ],
   "msft:container": "sentinel-3",
+  "msft:region": "westeurope",
   "msft:storage_account": "sentinel3euwest",
   "msft:short_description": "The [Sentinel-3](https://sentinel.esa.int/web/sentinel/missions/sentinel-3) mission is composed of three versatile satellites designed to provide data continuity for the ERS, ENVISAT and SPOT satellites and to support operational land and ocean observation services. OLCI, in conjunction with the SLSTR instrument, provides the SYN products, providing continuity with SPOT VEGETATION.",
   "summaries": {

diff --git a/datasets/sentinel-5p/sentinel-5p-l2.json b/datasets/sentinel-5p/sentinel-5p-l2.json
@@ -76,6 +76,7 @@
     }
   ],
   "msft:container": "sentinel-5p",
+  "msft:region": "westeurope",
   "msft:storage_account": "sentinel5euwest",
   "msft:short_description": "The Copernicus [Sentinel-5 Precursor mission](https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-5p) is dedicated to monitoring our atmosphere and consists of one satellite carrying the TROPOspheric Monitoring Instrument (TROPOMI). Level 2 data provide total columns of ozone, sulfur dioxide, nitrogen dioxide, carbon monoxide and formaldehyde, tropospheric columns of ozone, vertical profiles of ozone and cloud & aerosol information.",
   "summaries": {

diff --git a/datasets/terraclimate/collection/template.json b/datasets/terraclimate/collection/template.json
@@ -96,6 +96,7 @@
   "msft:short_description": "High-resolution global dataset of monthly climate and climatic water balance",
   "msft:storage_account": "cpdataeuwest",
   "msft:container": "cpdata",
+  "msft:region": "westeurope",
   "cube:dimensions": {
     "time": {
       "extent": [

diff --git a/datasets/usda-cdl/collection/template.json b/datasets/usda-cdl/collection/template.json
@@ -795,6 +795,7 @@
   "msft:short_description": "The UDA Cropland Data Layer is an annual raster, geo-referenced, crop-specific land cover data layer produced using satellite imagery and extensive agricultural ground truth collected during the current growing season.",
   "msft:storage_account": "landcoverdata",
   "msft:container": "usda-cdl",
+  "msft:region": "westeurope",
   "title": "USDA Cropland Data Layers (CDLs)",
   "extent": {
     "spatial": {

diff --git a/datasets/usda-cdl/scripts/create_collection.py b/datasets/usda-cdl/scripts/create_collection.py
@@ -24,6 +24,7 @@
         ),
         "msft:storage_account": "landcoverdata",
         "msft:container": "usda-cdl",
+        "msft:region": "westeurope",
     }
 )
 collection.providers.append(

diff --git a/datasets/usgs-lcmap/collection/usgs-lcmap-conus-v13/template.json b/datasets/usgs-lcmap/collection/usgs-lcmap-conus-v13/template.json
@@ -54,6 +54,7 @@
     "msft:short_description": "USGS Land Change Monitoring, Assessment, and Projection (LCMAP) Collection 1.3 Science Products for the Conterminous United States.",
     "msft:storage_account": "landcoverdata",
     "msft:container": "lcmap",
+    "msft:region": "westeurope",
     "msft:group_id": "usgs-lcmap",
     "providers": [
         {

diff --git a/datasets/usgs-lcmap/collection/usgs-lcmap-hawaii-v10/template.json b/datasets/usgs-lcmap/collection/usgs-lcmap-hawaii-v10/template.json
@@ -54,6 +54,7 @@
     "msft:short_description": "USGS Land Change Monitoring, Assessment, and Projection (LCMAP) Collection 1.0 Science Products for Hawaii",
     "msft:storage_account": "landcoverdata",
     "msft:container": "lcmap",
+    "msft:region": "westeurope",
     "msft:group_id": "usgs-lcmap",
     "providers": [
         {

diff --git a/pctasks/dataset/pctasks/dataset/validate.py b/pctasks/dataset/pctasks/dataset/validate.py
@@ -21,6 +21,7 @@ def validate_collection(collection: Dict) -> Tuple[str, List[str]]:
         "msft:short_description",
         "msft:storage_account",
         "msft:container",
+        "msft:region",
         "title",
     ]
     errors = [
@@ -95,6 +96,9 @@ def validate_collection(collection: Dict) -> Tuple[str, List[str]]:
     if not has_license_link:
         errors.append("must have license link")
 
+    region = collection.get("msft:region", "")
+    if region.count(" "):
+        errors.append("'msft:region' should not contain any spaces.")
     return cid, errors
 
     # if errors:

diff --git a/pctasks/dataset/tests/test_validate_collection.py b/pctasks/dataset/tests/test_validate_collection.py
@@ -18,6 +18,7 @@
     "msft:short_description": "short",
     "msft:storage_account": "account",
     "msft:container": "container",
+    "msft:region": "westeurope",
     "providers": [
         {
             "name": "Microsoft",
@@ -59,6 +60,7 @@ def test_validate_required_keys() -> None:
         "msft:short_description",
         "msft:storage_account",
         "msft:container",
+        "msft:region",
         "title",
     ]
     for key in required_keys:
@@ -120,3 +122,10 @@ def test_has_license_link() -> None:
 
     _, [error] = validate.validate_collection(c)
     assert error == "must have license link"
+
+
+def test_msft_region_format() -> None:
+    c = copy.deepcopy(collection)
+    c["msft:region"] = "West Europe"
+    _, [error] = validate.validate_collection(c)
+    assert error == "'msft:region' should not contain any spaces."