ENSO-Related Precursor Pathways of Interannual Thermal Anomalies Identified Using a Transformer-Based Deep Learning Model in the Tropical Pacific
文献类型：期刊论文
| 作者 | Zhou, Lu2,3; Zhang, Rong-Hua1,3,4
|
| 刊名 | GEOPHYSICAL RESEARCH LETTERS
 |
| 出版日期 | 2024-06-01 |
| 卷号 | 51期号:12页码:11 |
| 关键词 | ENSO predictions thermal precursors multivariate three-dimensional (3D) predictions transformer-based model explainable artificial intelligence (XAI) |
| ISSN号 | 0094-8276 |
| DOI | 10.1029/2023GL107347 |
| 通讯作者 | Zhang, Rong-Hua(rzhang@nuist.edu.cn) |
| 英文摘要 | Recent studies have demonstrated great values of deep-learning (DL) methods for improving El Ni & ntilde;o-Southern Oscillation (ENSO) predictions. However, the black-box nature of DL makes it challenging to physically interpret mechanisms responsible for successful ENSO predictions. Here, we demonstrate an interpretable method by performing perturbation experiments to predictors and quantifying input-output relationships in predictions by using a transformer-based model; ENSO-related thermal precursors serving as initial conditions during multi-month time intervals (TIs) are identified in the equatorial-northern Pacific, acting to precondition input predictors to provide for long-lead ENSO predictability. Results reveal the existence of upper-ocean temperature anomaly pathways and consistent phase propagations of thermal precursors around the tropical Pacific. It is illustrated that three-dimensional thermal fields and their basinwide evolution during long TIs act to enhance long-lead prediction skills of ENSO. These physically explainable results indicate that neural networks can adequately represent predictable precursors in the input predictors for successful ENSO predictions. Deep learning (DL) methods have emerged as a powerful tool for improving El Ni & ntilde;o-Southern Oscillation (ENSO) predictions. But DL-based modeling looks like "black boxes" without effectively telling why good predictions can be made. In this study, we conduct interpretable analyses to uncover the key physical processes responsible for successful ENSO predictions using a DL-based prediction model. Results identify ENSO-related thermal precursors in the equatorial-northern Pacific region, which precondition ENSO evolution months ahead of time. Specifically, interannual thermal precursors are illustrated to have consistent and coherent phase propagations in the tropical Pacific basin: eastward along the equator, westward across the off-equatorial tropical North Pacific, and apparent meridional phase connections both in the western and eastern boundaries. From the prediction perspective, the demonstrated existence of upper-ocean temperature anomaly pathways acts to enhance long-lead ENSO predictability in the purely data-driven DL framework. These physically explainable results indicate that the neural networks, despite their absence of explicit physical constraints, are capable of representing predictable precursors whose information is included in the input predictors, being able to make convincing and successful ENSO predictions. A deep learning (DL) model is used to conduct El Ni & ntilde;o-Southern Oscillation (ENSO) predictability studies for physical interpretability DL model experiments are made to identify ENSO-related thermal precursors along a counterclockwise pathway encircling the tropical Pacific The existence of upper-ocean thermal anomaly pathways is demonstrated to enhance long-lead ENSO predictability |
| WOS关键词 | OCEAN RECHARGE PARADIGM ; EL-NINO ; COUPLED MODEL ; ANALYSIS SYSTEM ; ROSSBY WAVES ; PART I ; VARIABILITY ; PREDICTIONS ; REANALYSIS ; PHASE |
| 资助项目 | Laoshan Laboratory[42030410] ; Laoshan Laboratory[LSKJ202202402] ; National Natural Science Foundation of China[XDB40000000] ; Strategic Priority Research Program of CAS ; Startup Foundation for Introducing Talent of NUIST |
| WOS研究方向 | Geology |
| 语种 | 英语 |
| WOS记录号 | WOS:001248646500001 |
| 出版者 | AMER GEOPHYSICAL UNION |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/186494]  |
| 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 |
| 作者单位 | 1.Laoshan Lab, Qingdao, Peoples R China 2.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Nanjing Univ Informat Sci & Technol, Sch Marine Sci, Nanjing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhou, Lu,Zhang, Rong-Hua. ENSO-Related Precursor Pathways of Interannual Thermal Anomalies Identified Using a Transformer-Based Deep Learning Model in the Tropical Pacific[J]. GEOPHYSICAL RESEARCH LETTERS,2024,51(12):11. |
| APA | Zhou, Lu,&Zhang, Rong-Hua.(2024).ENSO-Related Precursor Pathways of Interannual Thermal Anomalies Identified Using a Transformer-Based Deep Learning Model in the Tropical Pacific.GEOPHYSICAL RESEARCH LETTERS,51(12),11. |
| MLA | Zhou, Lu,et al."ENSO-Related Precursor Pathways of Interannual Thermal Anomalies Identified Using a Transformer-Based Deep Learning Model in the Tropical Pacific".GEOPHYSICAL RESEARCH LETTERS 51.12(2024):11. |
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。