software · Global

Prithvi-EO-1.0-100M-burn-scar

Hugging Face model ibm-nasa-geospatial/Prithvi-EO-1.0-100M-burn-scar (image-segmentation)

Claim this listing

Represent Prithvi-EO-1.0-100M-burn-scar? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: burn scar segmentation (burn scar class mask) · 6-band HLS input tiles (Blue, Green, Red, Narrow NIR, SWIR 1, SWIR 2) at 512x512 pixels
Formats docs-verified: GeoTIFF
Access docs-verified: Open-source download, Apache-2.0 licence

Useful for

Use cases llm-inferred: Post-fire burn scar extent mapping from HLS scenes for flood and erosion risk assessments · Burn scar masks as inputs to post-wildfire runoff or sediment-risk screening for drainage and FRA work · Burn scar baseline for BNG habitat condition change after wildfire
Audience llm-inferred: GIS analysts · remote sensing specialists · hydrologists · flood consultants · ecologists

Limitations

Constraints llm-inferred: Fine-tuned on HLS data with a single timestep, whereas the base model was pretrained on three timesteps · Reported IoU of 0.73 on the burn scar class from a single 50-epoch mmseg run; docs say further development will likely improve performance · Not deployed by any inference provider; must be run locally using the GitHub inference script · Inputs must be 6-band GeoTIFF in reflectance units [0-1]; other sensors or UK imagery need preprocessing · Docs do not state the geographic extent of the training data, so transfer to UK conditions is unverified

Licence: apache-2.0
Authentication: No API key required (repository README, auto-extracted; check upstream requirements)
GitHub stars: Unknown
Last commit: Unknown
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Provenance & evidence

Verified 2026-10-15 via HF API: exists; 18 downloads/30d, 32 likes.

Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Hugging Face models)

https://huggingface.co/ibm-nasa-geospatial/Prithvi-EO-1.0-100M-burn-scar