Satlas Tree Cover: Global 10 m Five-Level Tree Canopy Cover Rasters from Sentinel-2, January and July 2016-2023 (Ai2)
- Provider
- Allen Institute for AI (Ai2)
- License
- ODC-By-1.0 (source)
- Format
- TIFF (in sampled files)
- Stored at
- Google Cloud Storage, gs://satlas-explorer-public/outputs/tree-cover (us)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Earth Observation & Geospatial
- Source
- https://github.com/allenai/satlas
About this dataset
Satlas Tree Cover is a global raster estimate of tree canopy cover at 10 m per pixel, predicted by Ai2's deep learning models from Sentinel-2 satellite imagery. Each GeoTIFF has a single 8-bit band with six values: 0 no data, 1 no trees, 2 low, 3 medium, 4 high and 5 full tree cover. Files are organized as outputs/tree-cover/YYYY-MM/X_Y.tif, one folder per date and one file per Web Mercator tile at zoom level 7 (tile indices 0 to 127 counted from the top-left; for example 2022-07/20_44.tif covers Seattle). Dates run from 2016-01 to 2023-01 in January and July only, giving a twice-yearly time series for change analysis such as deforestation, reforestation, urban tree canopy and forest degradation. Read with rasterio, GDAL or xarray/rioxarray. License: ODC-By (Open Data Commons Attribution). Cite Satlas, Allen Institute for AI (satlas.allen.ai).
How to access this dataset in Python
import gcsfs
fs = gcsfs.GCSFileSystem(token='anon')
fs.ls('satlas-explorer-public/outputs/tree-cover/', detail=False)[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
File types in sampled files: TIFF
Files
Example file: outputs/tree-cover/2016-01/0_32.tif
Analyze this dataset without downloading it
On Scigantic, Satlas Tree Cover: Global 10 m Five-Level Tree Canopy Cover Rasters from Sentinel-2, January and July 2016-2023 (Ai2) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Earth Observation & Geospatial datasets
- DEM-Terrain
- SSL4EO-L Benchmark: Landsat Land Cover (NLCD) and Crop Type (CDL) Segmentation
- New Zealand National Coastal LiDAR 1 m Digital Elevation Model (Topo-Bathymetric DEM), LINZ
- Digital Earth Africa - Copernicus Global Land Service - Lake Water Quality
- GWL_FCS30D: Global 30 m Annual Wetland Maps, eight wetland classes, 2000-2022 (AIRCAS, Source Cooperative)
- BigEarthNet v2.0 (reBEN) Sentinel-1/Sentinel-2 Multi-Label Benchmark, LMDB Format
- Digital Earth Africa Cropland Extent Map (2019)
- Satellite - Ocean Colour - MODIS - 1 day - Chlorophyll-a concentration (Carder model)