weather
Pangu-Weather
Huawei Cloud first-generation AI weather model; commercial use forbidden.
Levelmodel
Classweather
Parametersnot in the notes
Contextnot in the notes
Released5 Jul 2023
Opennessopen weights restricted
Runs onsingle datacentre GPU
Statusactive
Benchmark Results
maintainer-run
WeatherBench 2 2domain
Z500 day 10, deterministic, Pangu-Weather (oper.) vs Analysismaintainer-run
799.8
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
Z500 day 10, deterministic, Pangu-Weather vs ERA5maintainer-run
778.2
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
Z500 day 5, deterministic, Pangu-Weather (oper.) vs Analysismaintainer-run
304.4
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
Z500 day 5, deterministic, Pangu-Weather vs ERA5maintainer-run
294.3
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
Z500 day 3, deterministic, Pangu-Weather (oper.) vs Analysismaintainer-run
138.4
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
Z500 day 3, deterministic, Pangu-Weather vs ERA5maintainer-run
133.8
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
Z500 day 1, deterministic, Pangu-Weather (oper.) vs Analysismaintainer-run
45
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
Z500 day 1, deterministic, Pangu-Weather vs ERA5maintainer-run
44.3
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
T850 day 10, deterministic, Pangu-Weather (oper.) vs Analysismaintainer-run
3.573
024
Score in RMSE K. Lower is better.
year 2022, 240x121 grid
T850 day 5, deterministic, Pangu-Weather (oper.) vs Analysismaintainer-run
1.766
024
Score in RMSE K. Lower is better.
year 2022, 240x121 grid
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Identity
- Developer
- Huawei (Huawei Cloud)
- Family
- not in the notes
- Released
- 5 Jul 2023 sourcesannouncement page
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- other 3D high-resolution neural network; 0.25 deg (721x1440)
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- sensor
- Output
- sensor
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights restricted
- Licence
- Creative Commons Attribution-NonCommercial-ShareAlike 4.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- single datacentre GPU
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperHuawei (Huawei Cloud)big tech, China
Huawei (Huawei Cloud)big tech, ChinaModelPangu-WeatherHuawei (Huawei Cloud), weather
Pangu-WeatherHuawei (Huawei Cloud), weatherUse CasesWeather ForecastingAgricultureUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
Badan Meteorologi, Klimatologi, dan Geofisika (BMKG)Contract signed, 5 Feb 2026Badan Meteorologi, Klimatologi, dan Geofisika (BMKG)In production, 23 Sep 2025Deployments of these use cases; none names this model.
Badan Meteorologi, Klimatologi, dan Geofisika (BMKG)Contract signed, 5 Feb 2026Badan Meteorologi, Klimatologi, dan Geofisika (BMKG)In production, 23 Sep 2025Deployments of these use cases; none names this model.Organisations 1
Sources
- GitHub - 198808xc/Pangu-Weather: An official implementation of Pangu-Weather github.com https://github.com/198808xc/Pangu-Weather
- China bets on AI weather forecasting as extreme weather intensifies news.tuoitre.vn https://news.tuoitre.vn/china-bets-on-ai-weather-forecasting-as-extreme-weather-intensifies-103260812213327362.htm
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Pangu-Weather", https://aurion.semai.id/models/huawei-pangu-weather/, records of October 2026.