weather
GraphCast (WeatherNext 1 Graph)
Message-passing GNN weather model; beat HRES on 90% of tested targets; code Apache-2.0.
Levelmodel
Classweather
Parametersnot in the notes
Contextnot in the notes
Released2023
Opennessopen weights restricted
Runs onsingle datacentre GPU
Statusactive
Benchmark Results
maintainer-run
WeatherBench 2 2domain
Z500 day 10, deterministic, GraphCast (oper.) vs Analysismaintainer-run
747.6
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
Z500 day 10, deterministic, GraphCast vs ERA5maintainer-run
731.9
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
Z500 day 5, deterministic, GraphCast vs ERA5maintainer-run
274.3
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
Z500 day 5, deterministic, GraphCast (oper.) vs Analysismaintainer-run
270.2
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
Z500 day 3, deterministic, GraphCast vs ERA5maintainer-run
124.2
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
Z500 day 3, deterministic, GraphCast (oper.) vs Analysismaintainer-run
120.6
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
Z500 day 1, deterministic, GraphCast vs ERA5maintainer-run
39.8
0450900
Score in RMSE m2/s2. Lower is better.
year 2020, 240x121 grid
Z500 day 1, deterministic, GraphCast (oper.) vs Analysismaintainer-run
38.3
0450900
Score in RMSE m2/s2. Lower is better.
year 2022, 240x121 grid
T850 day 10, deterministic, GraphCast (oper.) vs Analysismaintainer-run
3.364
024
Score in RMSE K. Lower is better.
year 2022, 240x121 grid
T850 day 5, deterministic, GraphCast (oper.) vs Analysismaintainer-run
1.555
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).
Lineage
successor
WeatherNext 2 (FGN) is a child (successor)high confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 4 models. Confidence and evidence are the notes' own.
Identity
- Developer
- Google DeepMind
- Family
- not in the notes
- Released
- 2023 sourcesnotesunverified
- 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
- GNN Graph neural network on multi-mesh; 0.25 deg, 37 levels; small 1 deg; operational 13 levels
- 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.
Industry Use Cases
No industry use case links this model.
Links
ModelGraphCast (WeatherNext 1 Graph)Google DeepMind, weather
GraphCast (WeatherNext 1 Graph)Google DeepMind, 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 - google-deepmind/weathernext github.com https://github.com/google-deepmind/graphcast
- developers.google.com/weathernext/guides/evals https://developers.google.com/weathernext/guides/evals
- WeatherBench 2 sites.research.google https://sites.research.google/gr/weatherbench/
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GraphCast (WeatherNext 1 Graph)", https://aurion.semai.id/models/google-deepmind-graphcast/, records of October 2026.