Learning skillful medium-range global weather forecasting
8/10 importance · solved · weather forecasting · 2023 · validator confidence 92% · research
The problem
Producing accurate 10-day global weather forecasts, traditionally requiring heavy compute rather than learning from historical weather data.
Why it matters
Medium-range forecasts are critical to decision-making across many social and economic domains.
What the AI did
GraphCast, a machine learning method trained directly on reanalysis data, predicts hundreds of weather variables for 10 days at 0.25° resolution in under 1 minute.
Results
Outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets; supports severe event prediction.
Impact
Match or beat operational forecasting systems on most verification targets at far greater speed.
How important is this problem?
8/10 — major — millions of lives, an industry or a field
Abstract states global medium-range forecasting is critical to decision-making across many social and economic domains; outperforms operational systems on 90% of 1380 targets.
stated — the source itself gives scale or impact evidence for this rating.
Scale stated in source: global, 10-day, 0.25° resolution; 1380 verification targets
Ratings use a published rubric and are AI-assisted, not measured or peer-reviewed. Method
Sources & verification
- Primary source
- https://doi.org/10.1126/science.adi2336
- Model / method
- GraphCast
- Organization
- not stated in source
- Validator notes
- glm-5.3: ok (confidence 92) | Peer-reviewed in Science; concrete outperformance metrics stated in abstract.
- Keywords
- weather forecasting, machine learning, GraphCast, reanalysis data, tropical cyclones, extreme events
A second-stage review judged this entry against the primary source; status “verified”. “Verified” means the evidence supported the claim — it does not mean the underlying result was independently reproduced.
Related
-
Accurate medium-range global weather forecasting with 3D neural networks
Numerical weather prediction is accurate but computationally expensive, while prior AI forecasting methods were much faster but significantly less accurate. The paper aims to make AI-based medium-range global weather forecasting accurate.
Climate & Environment · 2023 · partially solved · 8/10 importance
-
FuXi: a cascade machine learning forecasting system for 15-day global weather forecast
Medium-range weather forecasts accumulate errors beyond 10 days, so ML models still lag the ECMWF ensemble for 15-day forecasts.
Climate & Environment · 2023 · partially solved · 8/10 importance
-
Skilful nowcasting of extreme precipitation with NowcastNet
Extreme precipitation is a considerable contributor to meteorological disasters, and existing nowcasting methods suffer blur, dissipation, intensity or location errors; physics-based methods miss chaotic dynamics while data-driven methods violate physical laws…
Climate & Environment · 2023 · partially solved · 8/10 importance
-
Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects
Renewable energy generation is variable and uncertain, making accurate forecasting difficult, which complicates efficient grid operation and energy management.
Climate & Environment · 2023 · ai assisted · 8/10 importance
-
Automatic detection of methane emissions in multispectral satellite imagery using a vision transformer
Detecting methane point-source emissions from satellites was limited by trade-offs between coverage, resolution and detection accuracy.
Climate & Environment · 2024 · solved · 8/10 importance