software · Global

Prithvi-WxC-1.0-2300m-gravity-wave-parameterization

Hugging Face model ibm-nasa-geospatial/Prithvi-WxC-1.0-2300m-gravity-wave-parameterization

Claim this listing

Represent Prithvi-WxC-1.0-2300m-gravity-wave-parameterization? 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: gravity-wave momentum flux prediction (zonal flux u'ω' and meridional flux v'ω', 122 channels each) · potential temperature θ (122 channels) as output · atmospheric inputs: zonal wind u, meridional wind v, temperature T, pressure P (122 channels each), plus latitude, longitude and surface elevation
Coverage llm-inferred: Global (catalogue region tag); evaluation reported for the Andes and the Southern Ocean
Formats llm-inferred: PyTorch model weights
Access docs-verified: Apache-2.0 licence; model hosted openly on Hugging Face

Useful for

Use cases llm-inferred: Comparing a gravity-wave momentum flux parameterisation against reference flux fields in an atmospheric modelling study · Benchmarking ML emulators of sub-grid gravity-wave drag for climate or weather model research · Screening mountain-wave versus non-mountain-wave momentum flux patterns in a regional atmospheric research dataset
Audience llm-inferred: climate modellers · atmospheric scientists · meteorologists · machine learning researchers

Limitations

Constraints llm-inferred: Fine-tuned for gravity-wave momentum flux only; not a general weather forecast or hydrology model · Requires 491 gridded input channels (122 levels of u, v, T, P plus lat, lon, elevation) in the layout used by the training dataset · Reported skill (r = 0.99 Andes, 0.97 Southern Ocean) covers only two regions; performance elsewhere is not documented · Not deployed by any inference provider, so no hosted endpoint is available · Requires PyTorch and the upstream Prithvi-WxC code to run; not relevant to typical water or civils workflows without a research setup

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; 367 downloads/30d, 10 likes.

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

https://huggingface.co/ibm-nasa-geospatial/Prithvi-WxC-1.0-2300m-gravity-wave-parameterization