EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

AI for atmosphere–ocean sciences: advancements, challenges and ways forward

Jing-Jia Luo, Jiangjiang Xia, Baoxiang Pan, Yoo-Geun Ham, Xiaofeng Li iD, Wei Shangguan, Wei Xue, Yaqiang Wang, Bin Mu, Youngjoon Hong, Hao Li, Xiaohui Zhong und 33 weitere

National Science Review · 16.02.2026 · 13 (5)

DOI: 10.1093/nsr/nwag063 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift National Science Review, online erschienen am 29.01.2026. Verfasst von Jing-Jia Luo und 44 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Climate System Prediction and Risk Management (CPRM)/Jiangsu Key Laboratory of Intelligent Weather Forecasting and Applicatio…. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 278 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jing-Jin-Ji Regional Integrated Environmental Improvement-National Science and Technology, State Key Laboratory of Climate System Prediction and Risk Management.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) is rapidly transforming Earth science, offering unprecedented capabilities to tackle the most pressing challenges in the field. This work explores significant advances and emerging challenges across the AI for atmosphere–ocean sciences, while outlining critical ways forward. We review deep-learning methods and their application in weather and climate forecasting, which outperforms dynamical models in accuracy and computational efficiency. The role of AI in detecting complex phenomena, enhancing data assimilation and reconstruction, bias correction and downscaling coarse model outputs is also examined. However, the ‘black-box’ nature of complex AI models necessitates a focus on explainable AI to build trust and extract mechanistic insight. The most promising path forward is identified as the development of hybrid physics–AI modeling, which integrates the data-driven power of AI with the foundational constraints of physical laws to ensure generalizability and causal consistency. A new framework for AI-based model intercomparison is essential for rigorous benchmark performance. Finally, we contextualize these technical developments by discussing the usefulness and applicability of AI to society, including the improvement of multi-hazard early-warning systems and green energy production. We conclude by envisioning the future of AI agents for Earth science—autonomous, goal-oriented systems capable of designing and running experiments, generating and testing hypotheses, and learning dynamics from multisource data. This synthesis underscores that AI is not merely a tool, but a paradigm shift, which will significantly improve how we understand and adapt to a changing climate.

Schlagwörter

Stichwörter der Autor:innen

AI agentAI application and challengeAI-MIPatmosphere–ocean sciencesexplainable AI

Autor:innen und Institutionen

  • State Key Laboratory of Climate System Prediction and Risk Management (CPRM)/Jiangsu Key Laboratory of Intelligent Weather Forecasting and Applications Based on Big Data/ICAR/CIC-FEMD/KLME/ILCEC, School of Artificial In…
  • Temperate East Asia Research Center on Global Change, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China.
  • National Key Laboratory of Earth System Numerical Modeling and Application, Institute of Atmospheric Physics, Chinese Academy of Science, Beijing 100029, China.
  • Department of Environmental Management, Seoul National University, Seoul 08826, Republic of Korea.
  • Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, China.
  • School of Atmospheric Sciences, Sun Yat-sen University, Guangzhou 510275, China.

ORCID-Profile: Xiaofeng Li

Förderung

  • National Natural Science Foundation of China
  • Jing-Jin-Ji Regional Integrated Environmental Improvement-National Science and Technology
  • State Key Laboratory of Climate System Prediction and Risk Management
  • National Research Foundation
  • Ministry of Science and ICT

Zitieren

APA

Luo, J. J., Xia, J., Pan, B., Ham, Y. G., Li, X., Shangguan, W., Xue, W., Wang, Y., Mu, B., Hong, Y., Li, H., Zhong, X., Dai, K., Bai, L., Ling, F., Boers, N., Bretherton, C., Chen, B., Cho, D., …, & Zhao, M. (2026). AI for atmosphere–ocean sciences: advancements, challenges and ways forward. National Science Review, 13(5). https://doi.org/10.1093/nsr/nwag063

Vancouver

Luo JJ, Xia J, Pan B, Ham YG, Li X, Shangguan W, et al. AI for atmosphere–ocean sciences: advancements, challenges and ways forward. National Science Review. 2026;13(5). doi:10.1093/nsr/nwag063

BibTeX
@article{Luo2026,
  author = {Luo, Jing-Jia and Xia, Jiangjiang and Pan, Baoxiang and Ham, Yoo-Geun and Li, Xiaofeng and Shangguan, Wei and Xue, Wei and Wang, Yaqiang and Mu, Bin and Hong, Youngjoon and Li, Hao and Zhong, Xiaohui and Dai, Kan and Bai, Lei and Ling, Fenghua and Boers, Niklas and Bretherton, Christopher and Chen, Bin and Cho, Dongjin and Gentine, Pierre and Guo, Zijie and Huang, Xiaomeng and Kang, Daehyun and Kim, Hyunwoo J and Kim, Jeong-Hwan and Lei, Lili and Meng, Fan and Oh, Seol-Hee and Qin, Bo and Shen, Zixiong and Sun, Qiming and Tang, Yuheng and Tong, Xuan and Wan, Bingcheng and Wang, Lina and Wang, Ya and Wang, Yiming and Wu, Jiye and Xiao, Yi and Yao, Lina and Yang, Song and Yuan, Chaoxia and Yuan, Shijin and Yu, Tingzhao and Zhao, Mengchu},
  title = {AI for atmosphere–ocean sciences: advancements, challenges and ways forward},
  journal = {National Science Review},
  year = {2026},
  volume = {13},
  number = {5},
  doi = {10.1093/nsr/nwag063}
}
Kostenlos starten →