A faster view of the weather.
GraphCast produced skillful medium-range global weather forecasts using a learned model.
Original sources ↓ · Revision history ↓
Demonstrated · source published 2023-11-14
The human problem
Weather forecasting demands substantial computation.
The prior constraint
Numerical models simulate atmospheric physics.
AI’s actual role
A graph neural network learned weather evolution from historical data.
The documented result
The reported evaluation beat the operational comparison on more than 90% of 1,380 targets.
Why it may matter
Faster forecasts could help forecasters explore conditions sooner.
Limitations
Retrospective benchmark skill does not establish local warning quality.
Unresolved questions
Evaluate extremes and operational integration.
Source history & evidence assessment
- Maturity
- Demonstrated
- Claim confidence
- unassessed
- Event date
- Not recorded
- Source published
- 2023-11-14
- Captured
- Not recorded
- Last source review
- 2026-09-05
- Editorial method
- Original source check
- Place / relevance
- London, United Kingdom · institution-location
Legacy source check; no named human reviewer is recorded in this projection.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Original sources
Learning skillful medium-range global weather forecasting ↗ · paper
Institutions: Google DeepMind
Explore the underlying question
Related developments
Editorial connections between distinct settings and results; these links do not imply replication.
Revision & correction history
No corrections recorded.