AI Potluck
Back to Gap Map Model components / Scientific AI models

Pangu-Weather

Huawei
restricted / Overall score: 2.0

Pangu-Weather is Huawei Cloud's 3D transformer for medium-range global weather forecasting, released as four ONNX checkpoints with lead times of 1, 3, 6, and 24 hours that are chained to build longer forecasts. The repository provides inference scripts and algorithm pseudocode; ECMWF has run the published models in its own charts.

The repository carries no LICENSE file, so GitHub reports none; the grant over the trained parameters is stated in the README instead. Verified 2026-09-10 via the repository README, the GitHub license endpoint, and the GitHub API.

Openness

2 high confidence
2.0
license
CC-BY-NC-SA-4.0(non-commercial use only)
weights
open(four ungated ONNX checkpoints on Google Drive and Baidu Netdisk, roughly 1.1GB each)
data
documented-not-released(ERA5 over 39 years, about 60TB, with the lite variant's 2007-2017 subset spelled out
code
partial(CPU, GPU and iterative inference scripts plus algorithm pseudocode

The repository declares no license file and GitHub's license endpoint returns 404, so it would be wrong to read the code as permissive. The only grant is the README's, and it puts the trained parameters under CC BY-NC-SA 4.0 and forbids commercial use, which caps the score at restricted whatever else was published.

Adoption

2 medium confidence
2.0

Weights are hosted on Google Drive and Baidu Netdisk with no download count, so 1,395 GitHub stars are the last-resort reach signal; the repository was last pushed in January 2024.

Capability

2 high confidence
2.0

One attribute, the temporal-scale span. Pseudocode is not an adaptation pathway, ERA5 and ECMWF HRES initial fields are one data system, and a deterministic forecast is a fixed target rather than a generated output.

Verified 2026-09-10