Copyright Notice:

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Publications of SPCL

Y. Yu, L. Huang, A. Calotoiu, T. Hoefler:

 Scaling Laws of Global Weather Models

(In Proceedings of the 43rd International Conference on Machine Learning, Jul. 2026, arXiv:2602.22962. )

Abstract

Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical scaling laws within this domain. We investigate the relationship between model performance (validation loss) and three key factors: model size ($), dataset size ($), and compute budget ($). Across a range of models, we find that Aurora exhibits the strongest data-scaling behavior: increasing the training dataset by 10x reduces validation loss by up to 3.2x. GraphCast demonstrates the highest parameter efficiency, yet suffers from limited hardware utilization. Our compute-optimal analysis indicates that, under fixed compute budgets, allocating resources to longer training durations yields greater performance gains than increasing model size. Furthermore, we analyze model shape and uncover scaling behaviors that differ fundamentally from those observed in language models: weather forecasting models consistently favor increased width over depth. These findings suggest that future weather models should prioritize wider architectures and larger effective training datasets to maximize predictive performance.

Documents

download article:
access preprint on arxiv:
 

BibTeX

@inproceedings{,
  author={Yuejiang Yu and Langwen Huang and Alexandru Calotoiu and Torsten Hoefler},
  title={{Scaling Laws of Global Weather Models}},
  year={2026},
  month={07},
  booktitle={Proceedings of the 43rd International Conference on Machine Learning},
  note={arXiv:2602.22962.},
  doi={10.48550/arXiv.2602.22962},
}