← Directory
software · Global
Prithvi-EO-1.0-100M-multi-temporal-crop-classification
Hugging Face model ibm-nasa-geospatial/Prithvi-EO-1.0-100M-multi-temporal-crop-classification (image-segmentation)
Claim this listing
Represent Prithvi-EO-1.0-100M-multi-temporal-crop-classification? 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
- Crop and land cover classification (13 classes, CDL-derived labels) · Multi-temporal HLS input chips: 6 bands x 3 time-steps (18 channels, 224x224 px)
- Formats docs-verified
- GeoTIFF
- Access docs-verified
- Free/open model; licence apache-2.0
Useful for
- Use cases llm-inferred
- Land-use baseline for catchment runoff inputs (crop, forest, wetland classes) from HLS imagery · Wetland and open-water extent mapping as an input to BNG habitat baselines · Multi-temporal crop-type context for agricultural land use in flood risk assessments
- Audience llm-inferred
- GIS analysts · hydrologists · ecologists · flood risk consultants · planners
Limitations
- Constraints docs-verified
- Training labels (CDL) are known to contain noise and are not entirely precise · Reported per-class IoU ranges from about 0.31 to 0.68 (mIoU 0.4269) · Inputs must be 18-band GeoTIFF (6 bands x 3 time-steps) in the specified band order · Not deployed by any Inference Provider
- 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; 0 downloads/30d, 51 likes.
Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Hugging Face models)