Updated datasets 2023-07-07 UTC

aws_open_datasets.json

@@ -92,7 +92,7 @@
     {
         "Name": "10m Annual Land Use Land Cover (9-class)",
         "Description": "10m Annual Land Use Land Cover (9-class)",
-        "ARN": "arn:aws:s3:::io-10m-annual-lulc",
+        "ARN": "arn:aws:s3:::io-10m-annual-lulc-v1.2",
         "Region": "us-west-2",
         "Type": "S3 Bucket",
         "Documentation": "https://www.impactobservatory.com/global_maps",
@@ -102,7 +102,7 @@
         "License": "[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)",
         "Tags": "aws-pds, earth observation, environmental, geospatial, satellite imagery, sustainability, stac, cog, land cover, land use, machine learning, mapping, planetary",
         "Explore": [
-            "[STAC 1.0.0 endpoint](https://api.impactobservatory.com/stac-aws/)"
+            "[STAC 1.0.0 endpoint](https://api.impactobservatory.com/stac-aws/collections/io-annual-lulc-v1.2)"
         ],
         "RequesterPays": null,
         "ControlledAccess": null,

aws_open_datasets.tsv

@@ -4,7 +4,7 @@ Name	Description	ARN	Region	Type	Documentation	Contact	ManagedBy	UpdateFrequency
 1000 Genomes Phase 3 Reanalysis with DRAGEN 3.5 and 3.7 - BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2	BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2	arn:aws:s3:::1000genomes-dragen-3.7.6	us-west-2	S3 Bucket	[DRAGEN Support Resources](https://support.illumina.com/sequencing/sequencing_so	[Illumina, Inc.](mailto:[email protected])	[Illumina, Inc.](https://www.illumina.com/products/by-type/informatics-products/	Files may be updated subsequent to changes to the 1000 Genomes Project data set 	TBD	aws-pds, life sciences, health, biology, genetic, genomic, bam, vcf					
 1000 Genomes Phase 3 Reanalysis with DRAGEN 3.5 and 3.7 - BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2	BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2	arn:aws:s3:::1000genomes-dragen-v3.7.6	us-east-1	S3 Bucket	[DRAGEN Support Resources](https://support.illumina.com/sequencing/sequencing_so	[Illumina, Inc.](mailto:[email protected])	[Illumina, Inc.](https://www.illumina.com/products/by-type/informatics-products/	Files may be updated subsequent to changes to the 1000 Genomes Project data set 	TBD	aws-pds, life sciences, health, biology, genetic, genomic, bam, vcf					
 1000 Genomes Phase 3 Reanalysis with DRAGEN 3.5 and 3.7 - BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, metr	BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, metr	arn:aws:s3:::1000genomes-dragen	us-west-2	S3 Bucket	[DRAGEN Support Resources](https://support.illumina.com/sequencing/sequencing_so	[Illumina, Inc.](mailto:[email protected])	[Illumina, Inc.](https://www.illumina.com/products/by-type/informatics-products/	Files may be updated subsequent to changes to the 1000 Genomes Project data set 	TBD	aws-pds, life sciences, health, biology, genetic, genomic, bam, vcf					
-10m Annual Land Use Land Cover (9-class)	10m Annual Land Use Land Cover (9-class)	arn:aws:s3:::io-10m-annual-lulc	us-west-2	S3 Bucket	https://www.impactobservatory.com/global_maps	[email protected]	[Impact Observatory](https://www.impactobservatory.com/)	Annually, each January	[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)	aws-pds, earth observation, environmental, geospatial, satellite imagery, sustainability, stac, cog, land cover, land use, machine learning, mapping, planetary	['[STAC 1.0.0 endpoint](https://api.impactobservatory.com/stac-aws/)']				
+10m Annual Land Use Land Cover (9-class)	10m Annual Land Use Land Cover (9-class)	arn:aws:s3:::io-10m-annual-lulc-v1.2	us-west-2	S3 Bucket	https://www.impactobservatory.com/global_maps	[email protected]	[Impact Observatory](https://www.impactobservatory.com/)	Annually, each January	[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)	aws-pds, earth observation, environmental, geospatial, satellite imagery, sustainability, stac, cog, land cover, land use, machine learning, mapping, planetary	['[STAC 1.0.0 endpoint](https://api.impactobservatory.com/stac-aws/collections/io-annual-lulc-v1.2)']				
 1940 Census Population Schedules, Enumeration District Maps, and Enumeration District Descriptions	1940 Census	arn:aws:s3:::nara-1940-census	us-east-2	S3 Bucket	https://www.archives.gov/developer/1940-census	[email protected]	National Archives and Records Administration (NARA)	Not updated	US Government work	nara, census, archives, 1940 census, demography, aws-pds					
 1950 Census Population Schedules, Enumeration District Maps, and Enumeration District Descriptions	1950 Census	arn:aws:s3:::nara-1950-census	us-east-2	S3 Bucket	https://www.archives.gov/developer/1950-census	[email protected]	National Archives and Records Administration (NARA)	Not updated	US Government work	nara, census, archives, 1950 census, demography, aws-pds					
 2021 Amazon Last Mile Routing Research Challenge Dataset	Dataset including training and testing data Folder almrrc2021_data_training inc	arn:aws:s3:::amazon-last-mile-challenges	us-west-2	S3 Bucket	https://github.com/MIT-CAVE/rc-cli/blob/main/templates/data_structures.md	[email protected]	[Amazon](https://www.amazon.com/)	None	Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. The material 	transportation, machine learning, deep learning, amazon.science, urban, analytics, geospatial, logistics, last mile, optimization, routing					

datasets/io-lulc.yaml

@@ -1,21 +1,26 @@
 Name: 10m Annual Land Use Land Cover (9-class)
 Description: |
-  This dataset, produced by Impact Observatory, Microsoft, and Esri, displays a global map of land use/land cover (LULC)
-  derived from ESA Sentinel-2 imagery at 10m resolution for the years
-  2017 - 2022. Each year is generated from Impact Observatory’s deep
-  learning AI land classification model using a massive training
-  dataset of billions of human-labeled image pixels. The global maps
-  were produced by applying this model to every Sentinel-2 scene,
-  processing over 2,000,000 satellite Earth observations. Leaders in governments, 
-  NGOs, finance and industry need trustworthy,
-  actionable information about the changing world to understand opportunities,
-  identify threats, and measure the impacts of actions. Many of the most useful
-  applications of LULC maps require the ability to measure changes in land use
-  and land cover over time. With a time-series of LULC maps, monitoring of
-  deforestation, urban expansion, agricultural land conversion, and surface
-  water scarcity all become possible. The algorithm generates LULC predictions
-  for 9 classes globally. These classifications include Built, Crops, Trees,
-  Water, Rangeland, Flooded Vegetation, Snow/Ice, Bare Ground, and Clouds. 
+  This dataset, produced by Impact Observatory, Microsoft, and Esri, displays a global map of land use and land cover (LULC)
+  derived from ESA Sentinel-2 imagery at 10 meter resolution for the years 2017 - 2022.
+
+  Each map is a composite of LULC predictions for 9 classes throughout the year
+  in order to generate a representative snapshot of each year.
+
+  This dataset was generated by Impact Observatory, which used billions of human-labeled pixels 
+  (curated by the National Geographic Society) to train a deep learning model for land classification. 
+  Each global map was produced by applying this model to the Sentinel-2 annual scene collections
+  from the Mircosoft Planetary Computer. Each of the maps has an assessed average accuracy of over 75%.
+
+  These maps, v1.2, have been improved from Impact Observatory’s previous release and provide
+  a relative reduction in the amount of anomalous change between classes,
+  particularly between “Bare” and any of the vegetative classes
+  “Trees,” “Crops,” “Flooded Vegetation,” and “Rangeland”.
+  This updated time series of annual global maps is also re-aligned to match the ESA UTM tiling grid for Sentinel-2 imagery.
+
+  Impact Observatory’s previous 9-class time series remains available in the AWS Registry of Open Data
+  through the STAC endpoint in the collection named io-annual-lulc-v1.1. 
+  New applications should use the updated v1.2 time series to take advantage of the updated classifications
+  and the alignment with Sentinel-2 imagery to ease comparisons.
 
 Documentation: https://www.impactobservatory.com/global_maps
 Contact: [email protected]
@@ -38,11 +43,11 @@ Tags:
 License: "[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)"
 Resources:
   - Description: 10m Annual Land Use Land Cover (9-class)
-    ARN: arn:aws:s3:::io-10m-annual-lulc
+    ARN: arn:aws:s3:::io-10m-annual-lulc-v1.2
     Region: us-west-2
     Type: S3 Bucket
     Explore:
-    - '[STAC 1.0.0 endpoint](https://api.impactobservatory.com/stac-aws/)'
+    - '[STAC 1.0.0 endpoint](https://api.impactobservatory.com/stac-aws/collections/io-annual-lulc-v1.2)'
 DataAtWork:
   Tools & Applications:
     - Title: View the dataset on UN Biodiversity Lab Map Viewer