AI tool improves subseasonal weather forecasts up to a month ahead
A new machine‑learning approach described in a Nature paper by Guan H. et al.
Key points
- Guan H. et al. present a machine‑learning tool for subseasonal weather forecasting in Nature 658, 951–957 (2026).
- The paper is licensed under CC BY 4.0, with figures under CC BY‑NC‑ND 4.0.
The authors trained a model on historical atmospheric observations and report improved forecast skill compared with traditional dynamical methods for lead times from two weeks to a month. The paper references earlier work from 2018, 2019, 2023, and 2024, showing a growing research thread that applies deep learning to climate prediction. The article is released under a CC BY 4.0 licence, with figures under CC BY‑NC‑ND 4.0, allowing broad reuse while protecting the original visuals. Better subseasonal forecasts could help agriculture, water‑resource planning, and disaster preparedness by giving decision‑makers more reliable information a few weeks in advance.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Demis Hassabis says he expects AGI within two to three years, down from his three-to-five-year prediction earlier in 2026, and discusses AI's science potential · 2 src
- What Is Distributed AI Training? Data, Tensor, Pipeline, and Expert Parallelism · 1 src
- Claude designs protein minibinders against scorpion neurotoxins · 3 src
- Mass General Brigham's AI predicts cancer survival from a selfie, study suggests · 2 src
- Interactive site visualizes Artificial Analysis scores versus model size · 1 src
Comments
via GitHub Discussions