Deep Learning and Foundation Models for Weather Prediction: A Survey

Shi, Jimeng; Shirali, Azam; Jin, Bowen; Zhou, Sizhe; Hu, Wei; Rangaraj, Rahuul; Wang, Zhaonan; Wu, Yanzhao; Bobadilla, Leonardo; Lall, Upmanu; Wang, Shaowen; Han, Jiawei; Narasimhan, Giri

doi:10.24963/ijcai.2026/890

Deep Learning and Foundation Models for Weather Prediction: A Survey

Jimeng Shi, Azam Shirali, Bowen Jin, Sizhe Zhou, Wei Hu, Rahuul Rangaraj, Zhaonan Wang, Yanzhao Wu, Leonardo Bobadilla, Upmanu Lall, Shaowen Wang, Jiawei Han, Giri Narasimhan

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Survey Track. Pages 8023-8031.

https://doi.org/10.24963/ijcai.2026/890

Keywords

Multidisciplinary Topics and Applications: Other
Multidisciplinary Topics and Applications: Life sciences
Multidisciplinary Topics and Applications: Energy, environment and sustainability
Machine Learning: Applications

Abstract

Numerical weather prediction (NWP) models remain the cornerstone of atmospheric sciences. Yet, deep learning (DL) is challenging this paradigm by its ability to capture intricate spatio-temporal patterns and deliver ultra-fast predictions. Analogous to the foundation models (e.g., ChatGPT) in natural language processing, foundation models in the weather/climate domain have also been developed. This paper reviews DL and foundation models for weather prediction by highlighting their strengths and limitations. In particular, we carefully examine them from the perspective of their training paradigms: deterministic predictive learning, probabilistic generative learning, and pre-training & fine-tuning. For each paradigm, we summarize the underlying model architectures, training methods, and respective features. To facilitate further study, we provide a curated repository featuring categorized papers, open-source code, and benchmark datasets. Finally, we discuss and suggest potential research directions across new tasks and models in weather data storage and management, and operational deployment, further inspiring innovations in this rapidly evolving field. GitHub: https://github.com/JimengShi/DL-Foundation-Models-Weather.

Jimeng Shi, Azam Shirali, Bowen Jin, Sizhe Zhou, Wei Hu, Rahuul Rangaraj, Zhaonan Wang, Yanzhao Wu, Leonardo Bobadilla, Upmanu Lall, Shaowen Wang, Jiawei Han, and Giri Narasimhan. 2026. Deep Learning and Foundation Models for Weather Prediction: A Survey. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8023–8031. https://doi.org/10.24963/ijcai.2026/890

@inproceedings{ijcai2026p890,
  title     = {Deep Learning and Foundation Models for Weather Prediction: A Survey},
  author    = {Shi, Jimeng and Shirali, Azam and Jin, Bowen and Zhou, Sizhe and Hu, Wei and Rangaraj, Rahuul and Wang, Zhaonan and Wu, Yanzhao and Bobadilla, Leonardo and Lall, Upmanu and Wang, Shaowen and Han, Jiawei and Narasimhan, Giri},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8023--8031},
  year      = {2026},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2026/890},
  url       = {https://doi.org/10.24963/ijcai.2026/890},
}

TY  - CPAPER
TI  - Deep Learning and Foundation Models for Weather Prediction: A Survey
AU  - Shi, Jimeng
AU  - Shirali, Azam
AU  - Jin, Bowen
AU  - Zhou, Sizhe
AU  - Hu, Wei
AU  - Rangaraj, Rahuul
AU  - Wang, Zhaonan
AU  - Wu, Yanzhao
AU  - Bobadilla, Leonardo
AU  - Lall, Upmanu
AU  - Wang, Shaowen
AU  - Han, Jiawei
AU  - Narasimhan, Giri
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8023
EP  - 8031
DO  - 10.24963/ijcai.2026/890
UR  - https://doi.org/10.24963/ijcai.2026/890
ER  -