cog earth observation environmental geospatial land cover land use machine learning mapping planetary satellite imagery stac sustainability
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 - 2023. 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 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. Data can be accessed directly from the Registry of Open Data on AWS, from the STAC 1.0.0 endpoint, or from the IO Store for a specific Area of Interest (AOI).
A new year is made available annually, each January. A new time series was provided July 2023 to reduce anomalous change.
https://www.impactobservatory.com/global_maps
See all datasets managed by Impact Observatory.
10m Annual Land Use Land Cover (9-class) was accessed on DATE from https://registry.opendata.aws/io-lulc.
arn:aws:s3:::io-10m-annual-lulcus-west-2aws s3 ls --no-sign-request s3://io-10m-annual-lulc/