Articles | Volume 32, issue 4
https://doi.org/10.5194/npg-32-397-2025
https://doi.org/10.5194/npg-32-397-2025
Research article
 | 
20 Oct 2025
Research article |  | 20 Oct 2025

Improving dynamical climate predictions with machine learning: insights from a twin experiment framework

Zikang He, Julien Brajard, Yiguo Wang, Xidong Wang, and Zheqi Shen

Viewed

Total article views: 5,425 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
4,228 933 264 5,425 226 286
  • HTML: 4,228
  • PDF: 933
  • XML: 264
  • Total: 5,425
  • BibTeX: 226
  • EndNote: 286
Views and downloads (calculated since 17 Feb 2025)
Cumulative views and downloads (calculated since 17 Feb 2025)

Viewed (geographical distribution)

Total article views: 5,425 (including HTML, PDF, and XML) Thereof 5,273 with geography defined and 152 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 19 Nov 2026
Download
Short summary
Climate prediction is challenging due to systematic errors in traditional climate models. We addressed this by training a machine learning model to correct these errors and then integrating it with the traditional climate model to form an AI-physics hybrid model. Our study demonstrates that the hybrid model outperforms the original climate model on both short-term and long-term predictions of the atmosphere and ocean.
Share