Skip to content
← Directory

software · Global

Prithvi-EO-2.0-600M

Hugging Face model ibm-nasa-geospatial/Prithvi-EO-2.0-600M

Visit source ↗

Claim this listing

Represent Prithvi-EO-2.0-600M? 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
Prithvi-EO-2.0-600M pretrained 600M-parameter Earth observation foundation model · image reconstruction inference on multitemporal HLS image stacks
Coverage llm-inferred
Global (ENTRY regions field; pretraining geography not stated in DOCS)
Resolution docs-verified
30 m (HLS V2 pretraining granularity)
Formats docs-verified
GeoTIFF
Access docs-verified
Open model weights on Hugging Face under Apache-2.0 licence; no API key required (per ENTRY auth field)

Useful for

Use cases llm-inferred
Landslide extent segmentation from HLS imagery for slope and geotechnical screening, fine-tuned with TerraTorch · Multitemporal crop or land-cover segmentation for agricultural baselines in flood risk or catchment assessments · Reconstruction of cloud-affected HLS time series for habitat change baselines in BNG or ecological surveys
Audience llm-inferred
GIS analysts · remote sensing specialists · geotechnical engineers · ecologists · hydrologists

Limitations

Constraints llm-inferred
Foundation model, not a ready-to-use dataset: requires fine-tuning or a custom PyTorch/TerraTorch pipeline for end products · Inference expects six HLS bands (Blue, Green, Red, Narrow NIR, SWIR, SWIR 2) in reflectance units · No UK-specific coverage or validation stated in DOCS · Not deployed by any Inference Provider, so no hosted API is available
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; 1408 downloads/30d, 19 likes.

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