Skip to content
← Directory

software · Global

Prithvi-EO-2.0-600M-TL

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

Visit source ↗

Claim this listing

Represent Prithvi-EO-2.0-600M-TL? 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
HLS V2 multispectral image reconstruction (time series of HLS images from the same location) · Pretrained EO foundation-model weights (600M parameters, temporal and location embeddings) · Six-band input: Blue, Green, Red, Narrow NIR, SWIR, SWIR 2
Resolution docs-verified
30 m (HLS V2 pretraining granularity)
Formats docs-verified
GeoTIFF (inference input, reflectance units) · PyTorch / TerraTorch
Access docs-verified
Open weights under Apache-2.0 licence; no API key required (per entry metadata)

Useful for

Use cases llm-inferred
Landslide scar segmentation from multi-date HLS imagery for slope and geohazard screening (fine-tune with TerraTorch) · Multitemporal land-cover or crop segmentation for catchment and land-use change baselines · Gap-filling or reconstruction of cloudy HLS time series for habitat or land-cover monitoring
Audience llm-inferred
GIS analysts · hydrologists · ecologists · planners · remote-sensing and ML engineers

Limitations

Constraints llm-inferred
Foundation model only, not a ready-made data API or hosted service; no Inference Provider currently deploys it · Downstream tasks need fine-tuning with TerraTorch, which requires ML skills and labelled data · Inputs must be HLS-style six-band GeoTIFF reflectance at about 30 m, ordered chronologically · No UK-specific validation is stated in the docs
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; 964 downloads/30d, 16 likes.

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