GraphCast: ML weather model beats the world’s best physics-based 10-day forecast on 90% of targets
Result confirmed
Importance: major (4 of 5)The takeaway
GraphCast (Science, Nov 2023), a graph neural network trained on ECMWF reanalysis data, produced 10-day global forecasts in under a minute on one TPU.
Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Peer-reviewed
- Importance
- Major (4 of 5)
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- Beat HRES on 90.3% of 1,380 targets (89.9% statistically significant)
- 0.25° resolution; a 10-day forecast in under a minute on a single TPU v4
- Basis of NOAA’s operational AIGFS (Dec 2025), which uses ~99.7% less compute
What happened
DeepMind showed that a learned simulator could beat physics-based weather prediction on standard skill scores.
Why it matters
It triggered the rapid move of AI weather models into operational forecasting worldwide.
Sources
3 sources from 3 sites. Numbers match the chips in the text.
3 sources: 3 primary
Primary
- Learning skillful medium-range global weather forecasting (Science)science.org, paper
- DeepMind: GraphCastdeepmind.google, official
- NOAA deploys new generation of AI-driven global weather modelsnoaa.gov, official
Changes
- Filed