RESEARCH BRIEFINGS

21 October 2026

An innovative artificial-intelligence application enhances weather forecasting in the difficult subseasonal range, providing accurate forecasts of precipitation, temperature and pressure 3–5 weeks in advance. The tool refines both physics- and AI-based weather models and improves the early prediction of extremes of heat, cold, rainfall and flooding.

This is a summary of: Guan, H. et al . Advancing subseasonal forecasting with machine learning. Nature 658 , 951–957 (2026 ).

doi: https://doi.org/10.1038/d41586-026-03077-0

‘Expert opinion’ is published under a CC BY 4.0 licence and Figure 1 is published under a CC BY-NC-ND 4.0 licence.

References

Cohen, J. et al. WIREs Clim. Change 10 , e00567 (2018).

Article Google Scholar

Nathaniel, J. et al. Adv. Neural Inf. Process. Syst. 37 , 43715–43729 (2024).

Article Google Scholar

Hwang, J., Orenstein, P., Cohen, J., Pfeiffer, K. & Mackey, L. In Proc. 25th ACM SIGKDD Int. Conf.…