Individual Tree Canopy Polygons for West African Drylands

West African Sahara and Sahel drylands contain a detailed geospatial dataset of individual tree canopy geometries. Over 1.8 billion non-forest trees across 1.3 million km² were identified using deep learning on 50-cm resolution satellite imagery. The dataset, produced by NASA, provides foundational data for estimating woody carbon in arid regions.

Use Cases

• Estimating woody carbon stocks in arid and semi-arid ecosystems using individual tree canopy area.
• Monitoring changes in dryland vegetation structure and tree density over time.
• Validating and improving large-scale ecological models with high-resolution, individual-tree data.
• Supporting biodiversity and land degradation assessments by mapping tree distribution outside forests.

Strengths

• Dataset identifies an exceptionally large count of over 1.8 billion individual trees.
• Uses high-resolution (0.5-meter) satellite imagery and supervised deep-learning techniques for detection.
• Covers a vast geographic area of approximately 1.3 million square kilometers.

Limitations

• Column names and specific data schema are not provided by any source.
• Sources conflict on the last updated date: Data.gov lists 2026-03-13, while NASA Earthdata lists 2018-03-31.
• License is specified as 'other-license-specified' on Data.gov but is 'None' on NASA Earthdata.

Provenance

Source

National Aeronautics and Space Administration (NASA)

Collection Method

Derived using an automatic tree detection framework based on supervised deep-learning techniques applied to panchromatic and pansharpened NDVI satellite imagery.

Time Range

null

Freshness

2026-03 13

Geography

Dryland areas in the West African Sahara and Sahel.