software · Global

granite-geospatial-biomass

Hugging Face model ibm-granite/granite-geospatial-biomass (image-feature-extraction)

Claim this listing

Represent granite-geospatial-biomass? 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: above-ground biomass estimate (regression) from optical satellite imagery
Coverage docs-verified: Global (training data from 15 biomes)
Resolution llm-inferred: 30 m
Formats docs-verified: PyTorch Lightning checkpoint (.ckpt) · YAML config (.yaml)
Access llm-inferred: Free and open; Apache-2.0 licence; weights downloaded from Hugging Face, no API key required

Useful for

Use cases llm-inferred: Desk-level above-ground biomass screening for nature-based solution carbon estimates · Vegetation biomass context layer for ecological baseline reports · Regional woodland or crop biomass context for land-use assessments
Audience llm-inferred: ecologists · GIS analysts · remote-sensing specialists · environmental consultants

Limitations

Constraints llm-inferred: Requires TerraTorch to run the documented inference path · No Inference Provider deployment, so it must be run locally · High RAM may be needed for the Colab notebook · Training labels are sparse GEDI points, with no-data filled where GEDI is absent · Trained on HLS L30 optical imagery only; no UK-specific validation is stated · IBM will not maintain the code going forward and makes no quality or security assertions

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; 119 downloads/30d, 51 likes.

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

https://huggingface.co/ibm-granite/granite-geospatial-biomass