IO Maps for Good
Understand risks and anticipate change at high resolution in near real time using Geospatial AI
Land Use & Land Cover Maps for Good
Impact Observatory’s Maps for Good enables you understand the world as it is now and multi-year trends of change impacting populations, infrastructure, agriculture, and natural resources anywhere in the world. We use AI-powered analysis of images from the best public satellite, released as open science data products on all major geospatial platforms, including Esri Living Atlas, Microsoft Planetary Computer, and AWS Registry of Open Data.
You can access our annual global land use & land cover maps via our partners Esri's Living Atlas, Microsoft Azure Planetary Computer, and the UN Biodiversity Lab. Our maps are based on Copernicus Sentinel-2 10m imagery provided by Planetary Computer.
Download a map and set of metrics clipped to your custom area with IO Monitor.
Get a Map
“Land cover maps sit at the core of everything we are going to have to do moving forward. It’s the foundational dataset to any nervous system for sustainability on the planet.”
- Lucas Joppa, Microsoft’s Chief Environmental Officer on stage at the Esri Imagery Summit 2021, Redlands, CA
Behind the Scenes
- This dataset was generated using billions of human-labeled pixels to train a deep learning model for land classification.
- The global map was produced by applying this model to the relevant yearly ESA Sentinel-2 satellite imagery.
- Consistent mapping across the globe based on IO’s robust AI algorithms.
9-class
LULC
Annual global estimates of 9-class land use/land cover for 2017-2021, derived from ESA Sentinel-2 imagery at 10m resolution.
85% overall
accuracy
Industry-leading multi-category maps with 85% overall accuracy.
Read our Methodology & Accuracy Summary for more information.
LULC Class Definitions
Water
Areas where water was predominantly present throughout the year; may not cover areas with sporadic or ephemeral water; contains little to no sparse vegetation, no rock outcrop nor built up features like docks; examples: rivers, ponds, lakes, oceans, flooded salt plains.
Trees
Any significant clustering of tall (~5 m or higher) dense vegetation, typically with a closed or dense canopy; examples: wooded vegetation, clusters of dense tall vegetation within savannas, plantations, swamp or mangroves (dense/tall vegetation with ephemeral water or canopy too thick to detect water underneath).
Rangeland
Any area of low, non-flooded vegetation with very little-to-no taller (~15m or higher) vegetation, homogeneous or heterogeneous, containing any degree of the following: wild cereals and grasses with no obvious human plotting (i.e. not a plotted field); mix of small clusters of plants or single plants dispersed on a landscape that shows exposed soil or rock; clearings of homogeneous grasses; scrub-filled clearings within dense forests that are clearly not taller than trees; examples: moderate to sparse cover of bushes, shrubs and tufts of grass, savannas with very sparse grasses, trees or other plants.
Flooded Vegetation
Areas of any type of vegetation with obvious intermixing of water throughout a majority of the year; seasonally flooded area that is a mix of grass / shrub / trees / bare ground; examples: flooded mangroves, emergent vegetation, rice paddies and other heavily irrigated and inundated agriculture.
Crops
Human planted / plotted cereals, grasses, and crops not at tree height; examples: corn, wheat, soy, fallow plots of structured land.
Built Area
Human made structures; major road and rail networks; large homogenous impervious surfaces including parking structures, office buildings and residential housing; examples: houses, dense villages / towns / cities, paved roads, asphalt.
Bare Ground
Areas of rock or soil with very sparse to no vegetation for the entire year; large areas of sand and deserts with no to little vegetation; examples: exposed rock or soil, desert and sand dunes, dry salt flats / pans, dried lake beds, mines.
Snow/Ice
Large homogenous areas of permanent snow or ice, typically only in mountain areas or highest latitudes; examples: glaciers, permanent snowpack, snow fields.
Clouds
No land cover information due to persistent cloud cover.
Karra, Kontgis, et al. “Global land use / land cover with Sentinel 2 and deep learning.” IGARSS 2021-2021 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2021.
We created these maps in partnership with Esri and Microsoft, and have made them available under an open license (CC BY 4.0) IO Monitor lets you download free land cover data over your custom area. You can access these maps on Esri’s Living Atlas and Planetary Computer.
Discover how we leveraged Microsoft’s Azure to create each of these maps in less than a week.
Maps on Demand
Interested in monitoring trends and anticipating threats in areas you care about using our AI-powered land use and land cover monitoring system?
See how we can help you through our custom 10m Land Cover.
Custom Map Details