Projection of ENSO using observation-informed deep learning
文献类型：期刊论文
| 作者 | Zhu, Yuchao2,3,4; Zhang, Rong-Hua5; Wang, Fan2,3,4; Cai, Wenju1,6,7; Li, Delei1; Guan, Shoude6,7; Li, Yuanlong2,3,4 |
| 刊名 | NATURE COMMUNICATIONS
 |
| 出版日期 | 2025-08-19 |
| 卷号 | 16期号:1页码:12 |
| DOI | 10.1038/s41467-025-63157-z |
| 通讯作者 | Zhang, Rong-Hua(rzhang@nuist.edu.cn) ; Wang, Fan(fwang@qdio.ac.cn) |
| 英文摘要 | The El Ni & ntilde;o-Southern Oscillation (ENSO) profoundly impacts global climate, but its sea surface temperature (SST) variability projected by climate models remains uncertain, with a substantial inter-model spread in 21st-century projections. Model-observation discrepancies in ENSO physics contribute to this uncertainty, necessitating observational constraints to refine projections. However, methods to achieve this constraint remain unclear. Here, we show that deep learning informed by the observed response of ENSO SST variability to tropical Pacific warming patterns reduces projection uncertainty by 54% under a high-emission scenario. Specifically, artificial neural networks (ANNs), trained on climate model simulations and observations, successfully capture the real-world ENSO response. Interpretability analyses reveal that replicating observed ENSO physics by ANNs is critical, identifying warming in the far-eastern and central equatorial Pacific as key to ENSO change. A model-as-truth approach further confirms the robustness of ANN-generated projections. By conditioning future ENSO SST variability projection on the ANN-inferred ENSO response to tropical Pacific warming, uncertainty is reduced from a range of 0.59 degrees C to 0.27 degrees C. Our results highlight the prospect of integrating machine learning with observations to reduce uncertainty in climate projections. |
| WOS关键词 | SEA-SURFACE TEMPERATURE ; EARTH SYSTEM MODEL ; NINO-SOUTHERN-OSCILLATION ; EL-NINO ; EQUATORIAL PACIFIC ; EMERGENT CONSTRAINTS ; OCEAN ; VARIABILITY ; TRENDS |
| 资助项目 | National Key Research and Development Program of China[2022YFF0801404] ; National Natural Science Foundation of China[42276008] ; National Natural Science Foundation of China[42030410] ; Taishan Scholars Program[tsqn202408274] ; Taishan Scholars Program[LSKJ202202402] ; Jiangsu Innovation Research Group[202346] |
| WOS研究方向 | Science & Technology - Other Topics |
| 语种 | 英语 |
| WOS记录号 | WOS:001554401700029 |
| 出版者 | NATURE PORTFOLIO |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/203203]  |
| 专题 | 海洋研究所_海洋环流与波动重点实验室 |
| 通讯作者 | Zhang, Rong-Hua; Wang, Fan |
| 作者单位 | 1.Laoshan Lab, Qingdao, Peoples R China 2.Chinese Acad Sci, Inst Oceanol, Lab Ocean Circulat & Waves, Qingdao, Peoples R China 3.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Observat & Forecasting, Qingdao, Peoples R China 4.Qingdao Marine Sci & Technol Ctr, Lab Ocean Dynam & Climate, Qingdao, Peoples R China 5.Nanjing Univ Informat Sci & Technol, Sch Marine Sci, State Key Lab Climate Syst Predict & Risk Manageme, Nanjing, Peoples R China 6.Ocean Univ China, Frontiers Sci Ctr Deep Ocean Multispheres & Earth, Qingdao, Peoples R China 7.Ocean Univ China, Key Lab Phys Oceanog, Qingdao, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhu, Yuchao,Zhang, Rong-Hua,Wang, Fan,et al. Projection of ENSO using observation-informed deep learning[J]. NATURE COMMUNICATIONS,2025,16(1):12. |
| APA | Zhu, Yuchao.,Zhang, Rong-Hua.,Wang, Fan.,Cai, Wenju.,Li, Delei.,...&Li, Yuanlong.(2025).Projection of ENSO using observation-informed deep learning.NATURE COMMUNICATIONS,16(1),12. |
| MLA | Zhu, Yuchao,et al."Projection of ENSO using observation-informed deep learning".NATURE COMMUNICATIONS 16.1(2025):12. |
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。