Real-time wave model error correction via coupled neural networks and WAM under extreme weather
文献类型：期刊论文
| 作者 | Liu, Aiyue1,2; Li, Xiaofeng1; Shen, Dongliang1 |
| 刊名 | OCEAN MODELLING
 |
| 出版日期 | 2025-12-01 |
| 卷号 | 198页码:11 |
| 关键词 | Ai correction Ocean wave numerical model Cfosat satellite AI-numerical model coupling |
| ISSN号 | 1463-5003 |
| DOI | 10.1016/j.ocemod.2025.102600 |
| 通讯作者 | Shen, Dongliang(shendl@qdio.ac.cn) |
| 英文摘要 | Accurate forecasts of wave parameters, especially significant wave height, are essential for maritime operations, yet predicting wave heights during extreme weather remains difficult due to rapid error growth in numerical models. This study presents a real-time error correction framework that couples a spatiotemporal attention-based neural network with the WAM wave model. The correction network is trained using CFOSAT satellite observations and dynamically coupled with WAM via a Fortran-Python interface. Applied to 114 typhoon events in the Northwest Pacific, the system reduces significant wave height (SWH) root mean square error (RMSE) by 24.6 % and increases the structural similarity index (SSIM) by 26.3 %, compared to WAM predictions made with default tuning parameters. Validation across 32 tropical cyclones with diverse intensities in the Gulf of Mexico shows strong generalization, achieving up to a 47 % reduction in RMSE and enhancing wave spectral accuracy by >30 %. These results highlight the robustness and scalability of this hybrid AI-physics framework, demonstrating its practical value for real-time wave forecasting during extreme weather events. |
| WOS关键词 | FORECASTING SYSTEM ; NUMERICAL-MODELS ; PERFORMANCE ; UNCERTAINTY ; VALIDATION ; FRAMEWORK ; HEIGHTS |
| 资助项目 | National Natural Science Foundation of China[42376175] ; National Natural Science Foundation of China[42090044] ; Postdoctoral Fellowship Program of CPSF[GZC20232706] ; Qingdao Science and Technology for People's Livelihood Demonstration Special Project[25-1-5-cspz-18-nsh] |
| WOS研究方向 | Meteorology & Atmospheric Sciences ; Oceanography |
| 语种 | 英语 |
| WOS记录号 | WOS:001543479400001 |
| 出版者 | ELSEVIER SCI LTD |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/202812]  |
| 专题 | 海洋研究所_海洋环流与波动重点实验室 |
| 通讯作者 | Shen, Dongliang |
| 作者单位 | 1.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Observat & Forecasting, Key Lab Ocean Circulat & Waves, 88 Haijun Rd, Qingdao 266400, Shandong, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Aiyue,Li, Xiaofeng,Shen, Dongliang. Real-time wave model error correction via coupled neural networks and WAM under extreme weather[J]. OCEAN MODELLING,2025,198:11. |
| APA | Liu, Aiyue,Li, Xiaofeng,&Shen, Dongliang.(2025).Real-time wave model error correction via coupled neural networks and WAM under extreme weather.OCEAN MODELLING,198,11. |
| MLA | Liu, Aiyue,et al."Real-time wave model error correction via coupled neural networks and WAM under extreme weather".OCEAN MODELLING 198(2025):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。