← Directory
software · Global
Prithvi-EO-1.0-100M
Hugging Face model ibm-nasa-geospatial/Prithvi-EO-1.0-100M
Claim this listing
Represent Prithvi-EO-1.0-100M? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.
What's in it
- Data offered docs-verified
- image reconstruction on HLS image time series · temporal ViT embeddings (masked autoencoder, 6-band reflectance input) · downstream segmentation/classification (burn scars, flood, land cover) via finetuning
- Coverage docs-verified
- Contiguous United States (pre-training data); coverage outside CONUS not stated
- Resolution docs-verified
- 30 m (HLS V2 L30 product, pre-training data)
- Formats docs-verified
- GeoTIFF
- Access docs-verified
- Open model weights under Apache-2.0 licence, downloaded from Hugging Face; no hosted inference endpoint (not deployed by any Inference Provider)
Useful for
- Use cases llm-inferred
- Burn scar mapping from HLS time series for post-fire ecological or flood-risk assessment (requires finetuning) · Flood extent segmentation for FRA baseline mapping from satellite imagery (requires finetuning) · Land cover classification for BNG habitat baseline mapping (requires finetuning)
- Audience llm-inferred
- GIS analysts · remote sensing specialists · hydrologists · ecologists · ML engineers
Limitations
- Constraints llm-inferred
- Pre-trained only on contiguous US HLS data; transfer to other regions is not documented · Inputs must be six HLS bands in reflectance units, in chronological order · Downstream tasks such as flood mapping require finetuning · No hosted inference provider; self-hosting and a Python/PyTorch environment required · 30 m spatial resolution limits fine-scale detail · ENTRY auth note is auto-extracted and upstream requirements are 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; 2047 downloads/30d, 289 likes.
Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Hugging Face models)