AI for atmosphere-ocean sciences: advancements, challenges and ways forward
文献类型：期刊论文
| 作者 | Luo, Jing-Jia33; Xia, Jiangjiang34; Pan, Baoxiang1; Ham, Yoo-Geun2; Li, Xiaofeng3; Wei, Shangguan24; Xue, Wei18,19,23; Wang, Yaqiang20,21,22; Mu, Bin25; Hong, Youngjoon26 |
| 刊名 | NATIONAL SCIENCE REVIEW
 |
| 出版日期 | 2026-03-01 |
| 卷号 | 13期号:5页码:27 |
| 关键词 | AI application and challenge atmosphere-ocean sciences explainable AI AI-MIP AI agent |
| ISSN号 | 2095-5138 |
| DOI | 10.1093/nsr/nwag063 |
| 通讯作者 | Luo, Jing-Jia(jjluo@nuist.edu.cn) ; Xia, Jiangjiang(xiajj@tea.ac.cn) ; Pan, Baoxiang(panbaoxiang@lasg.iap.ac.cn) ; Ham, Yoo-Geun(yoogeun@snu.ac.kr) ; Li, Xiaofeng(lixf@qdio.ac.cn) ; Wei, Shangguan(shgwei@mail.sysu.edu.cn) ; Xue, Wei(xuewei@tsinghua.edu.cn) ; Wang, Yaqiang(yqwang@cma.gov.cn) ; Mu, Bin(binmu@tongji.edu.cn) ; Hong, Youngjoon(hongyj@snu.ac.kr) ; Li, Hao(lihao_lh@fudan.edu.cn) ; Zhong, Xiaohui(zhong_xiaohui@fudan.edu.cn) ; Dai, Kan(daikan@cma.gov.cn) ; Bai, Lei(baisanshi@gmail.com) ; Ling, Fenghua(lingfenghua@pjlab.org.cn) |
| 英文摘要 | 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. This review explores how AI is transforming atmosphere-ocean sciences, from improved forecasts to trustworthy hybrid systems. It outlines a paradigm shift toward autonomous AI agents that could one day drive scientific discovery. |
| WOS关键词 | EXPLAINABLE ARTIFICIAL-INTELLIGENCE ; APPLYING NEURAL-NETWORK ; GOVERNING EQUATIONS ; PREDICTION ; MODELS ; FORECASTS ; SATELLITE ; WEATHER ; V1.0 |
| 资助项目 | State Key Laboratory of Climate System Prediction and Risk Management[CPRM-2025-NUIST-012] ; Ministry of Science and ICT ; Jing-Jin-Ji Regional Integrated Environmental Improvement-National Science and Technology[2025ZD1201900] ; National Natural Science Foundation of China[42088101] ; National Natural Science Foundation of China[U2242210] ; National Natural Science Foundation of China[U2342219] ; National Natural Science Foundation of China[42505033] ; National Natural Science Foundation of China[42505031] ; National Research Foundation[RS-2024-00440482] ; National Research Foundation[RS-2024-00440063] |
| WOS研究方向 | Science & Technology - Other Topics |
| 语种 | 英语 |
| WOS记录号 | WOS:001734708000001 |
| 出版者 | OXFORD UNIV PRESS |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/204982]  |
| 专题 | 中国科学院海洋研究所 |
| 通讯作者 | Luo, Jing-Jia; Xia, Jiangjiang; Pan, Baoxiang; Ham, Yoo-Geun; Li, Xiaofeng; Wei, Shangguan; Xue, Wei; Wang, Yaqiang; Mu, Bin; Hong, Youngjoon; Li, Hao; Zhong, Xiaohui; Dai, Kan; Bai, Lei; Ling, Fenghua |
| 作者单位 | 1.Chinese Acad Sci, Inst Atmospher Phys, Natl Key Lab Earth Syst Numer Modeling & Applicat, Beijing 100029, Peoples R China 2.Seoul Natl Univ, Dept Environm Management, Seoul 08826, South Korea 3.Chinese Acad Sci, Inst Oceanol, Qingdao 266071, Peoples R China 4.Lanzhou Univ, Coll Atmospher Sci, Key Lab Semiarid Climate Change, Minist Educ, Lanzhou 730000, Peoples R China 5.Lanzhou Univ, Inst Meteorol Artificial Intelligence Res, Lanzhou 730000, Peoples R China 6.Seoul Natl Univ, Environm Planning Inst, Seoul 08826, South Korea 7.Columbia Univ, Learning Earth AI & Phys LEAP NSF Sci & Technol Ct, New York, NY 10027 USA 8.Tsinghua Univ, Dept Earth Syst Sci, Beijing 100084, Peoples R China 9.Korea Inst Sci & Technol, Ctr Climate & Carbon Cycle Res, Seoul 02792, South Korea 10.Korea Adv Inst Sci & Technol, Sch Comp, Daejeon 34141, South Korea |
| 推荐引用方式 GB/T 7714 | Luo, Jing-Jia,Xia, Jiangjiang,Pan, Baoxiang,et al. AI for atmosphere-ocean sciences: advancements, challenges and ways forward[J]. NATIONAL SCIENCE REVIEW,2026,13(5):27. |
| APA | Luo, Jing-Jia.,Xia, Jiangjiang.,Pan, Baoxiang.,Ham, Yoo-Geun.,Li, Xiaofeng.,...&Zhao, Mengchu.(2026).AI for atmosphere-ocean sciences: advancements, challenges and ways forward.NATIONAL SCIENCE REVIEW,13(5),27. |
| MLA | Luo, Jing-Jia,et al."AI for atmosphere-ocean sciences: advancements, challenges and ways forward".NATIONAL SCIENCE REVIEW 13.5(2026):27. |
入库方式： OAI收割
来源：海洋研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。