Skip to content

Maps for Good#

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. Our Land Use & Land Cover maps meet this need with free data at a previously unobtainable temporal and spatial scale.

Annual global Land Use Land Cover (LULC) maps are 9-class, 10-meter resolution and available for 2017 through 2023 with a CC BY 4.0 license.

You can access our annual global land use & land cover Maps for Good from the IO Store, clipped to just your Area of Interest (AOI). With a subscription to ArcGIS Image Dedicated Services you can transfer maps from the IO Store to ArcGIS Online.

You can also access the data from our partners Esri Living Atlas, Microsoft's Planetary Computer and the AWS Open Data Registry. Note this dataset is sometimes called the "Esri Land Cover" by other providers.

  • This dataset was generated using billions of human-labeled pixels to train a deep-learning model for land classification.

  • The global maps are produced by applying this model to the relevant yearly ESA Sentinel-2 10-meter satellite imagery.

  • Consistent mapping across the globe based on IO’s robust AI algorithms.

What is included in a Map for Good download form the IO Store?#

  • Custom Maps for Good LULC Map order
  • a 9 class land use map for the specified year
    • as a GeoTIFF - see techncial specs
    • as a PNG image - easy to drop into other media like blogs, slides and websites
  • Metrics are provided in a CSV file showing the number of square kilometers of each land cover class in the AOI
  • the Area of Interest (AOI) specified by the customer is available as a GeoJSON file

Access the Maps for Good on AWS#

See our Tutoral on AWS Open Data Exchange for additional info

Maps for Good Technical Specifications#

Name Specification
File Types Cloud Optimized GeoTIFF (COG), PNG, CSV of metrics
Compression LZW
Projection EPSG:3857 - WGS 84 / Pseudo-Mercator – Spherical Mercator
Spatial Extent Global
Resolution 10 meters
Data Type 8-bit unsigned integer (uint8)
No data value 0

LULC Class Definitions#

Class Labels Description
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.
Tree Any significant clustering of tall dense vegetation, typically with a closed or dense canopy; examples: wooded vegetation, clusters of dense tall vegetation within savannas, plantations, swamps or mangroves.
Rangeland Areas of low, non-flooded vegetation with very little or no taller vegetation, containing any degree of the following: wild grasses; small clusters of plants on a landscape that shows exposed soil or rock; clearings of scrub or homogeneous grasses.
Flooded Vegetation Areas of any type of vegetation with obvious intermixing of water throughout the majority of the year; seasonally flooded areas that are a mix of grass/shrubs/trees/bare ground.
Crops Human planted/plotted cereals, grasses, and crops not at tree height; examples: corn, wheat, soy, and fallow plots of structured land.
Built 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, dry salt flats, dry lake beds.
Snow/Ice Large homogenous areas of permanent snow or ice, typically only in mountain areas or highest latitudes.
Clouds No land cover information due to persistent cloud cover.

9-Class Colors Map#

Raster Value Land Cover Class Hex Color Value
0 No data #000000
1 Water #419bdf
2 Trees #397d49
4 Flooded Vegetation #7a87c6
5 Crops #e49635
7 Built Area #c4281b
8 Bare Ground #a59b8f
9 Snow/Ice #a8ebff
10 Clouds #616161
11 Rangeland #e3e2c3


Grass and Scrub classes, represented by the raster values 3 and 6 from our release v1.0 map are no longer used. Grass and Scrub classes were merged into the Rangeland Class, represented by raster value 11, in release v1.1 and v1.2.

Impact Observatory Maps for Good - Annual Maps are released under a CC BY 4.0 license.

The CC BY 4.0 license does not apply to maps and data ordered through IO Monitor, which are licensed under our EULA.