Explainability, uncertainty & physics★ Highlight
On Some Limitations of Current Machine Learning Weather Prediction Models
Why it matters. Influential ECMWF critique showing leading ML models miss mesoscale features and physical consistency; important caveat for evaluating ML skill.
In one sentence. Shows Pangu-Weather, FourCastNet and GraphCast fail to reproduce sub-synoptic and mesoscale phenomena, lacking physical consistency versus physics-based models.
Abstract
Abstract Machine Learning (ML) is having a profound impact in the domain of Weather and Climate Prediction. A recent development in this area has been the emergence of fully data‐driven ML prediction models which routinely claim superior performance to that of traditional physics‐based models. We examine some aspects of the forecasts produced by three of the leading current ML models, Pangu‐Weather, FourCastNet and GraphCast, with a focus on their fidelity and physical consistency. The main conclusion is that these ML models are not able to properly reproduce sub‐synoptic and mesoscale weather phenomena and lack the fidelity and physical consistency of physics‐based models and this has impacts on the interpretation of their forecasts and their perceived skill. Balancing forecast skill and physical realism will be an important consideration for future ML models.
Labels
- Topic
- Explainability, uncertainty & physics
- Type
- Evaluation or intercomparison of existing models
- Method
- Graph neural network, Transformer / ViT, CNN / U-Net
- Time scale
- 6 h–3 days, 3–15 days
- Domain
- Global
- Data
- ERA5 / reanalysis
- Status
- Research
- Identifiers
- DOI:10.1029/2023gl107377 OpenAlex:W4399668152
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.