Enhancing Retrievals of Air-Sea Heat Fluxes From AMSR2 Microwave Observations Based on Deep Learning
文献类型：期刊论文
| 作者 | Wang, Mengjiao1,2,3; Wang, Haoyu2,3; Li, Xiaofeng2,3 |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2025 |
| 卷号 | 63页码:17 |
| 关键词 | Atmospheric modeling Atmospheric measurements Sea measurements Heating systems Satellites Electromagnetic heating Satellite broadcasting Microwave radiometry Microwave measurement Accuracy Air-sea heat fluxes deep learning (DL) in situ measurements remote sensing |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2025.3586604 |
| 通讯作者 | Li, Xiaofeng(xiaofeng.li@ieee.org) |
| 英文摘要 | Air-sea heat fluxes play a crucial role in understanding global climate variability. Using the bulk aerodynamic algorithm, we can derive sensible heat flux (SHF) and latent heat flux (LHF) from the satellite sea surface temperature ( T-s ) and wind speed (WS), as well as the air temperature ( T-a ) and specific humidity ( Q(a) ). However, traditional retrievals of T-a and Q(a) tend to be unreliable. To address this issue, we introduced the Matrices-Points Fusion Network (MPFNet), a deep learning (DL) model designed to integrate spatial and point information. This model employs the Fourier Neural Operator (FNO) and Residual Network (ResNet) techniques to enhance retrieval capabilities. The model was pretrained with ECMWF ERA5 reanalysis-based data, followed by transfer learning (TL) with satellite and in situ matchup data for fine-tuning. Validation against independent in situ data showed significant improvements compared to the mainstream products in the community, with root mean square errors (RMSEs) for T-a and Q(a) reduced to 0.59 (degrees) C and 0.87 g/kg, representing 27%-41% and 16%-33% improvements, respectively. SHF and LHF RMSE values were 6.54 and 29.32 W/m(2), reflecting improvements of 32%-36% and 17%-31%, respectively. Using this fine-tuned MPFNet model with satellite data as input, a global daily gridded dataset of T-a , Q(a) , SHF, and LHF over 11.5 years was generated at a 0.25 degrees resolution. The analysis showed that previous products tended to underestimate T-a and Q(a) while overestimating SHF and LHF. |
| WOS关键词 | SURFACE SPECIFIC-HUMIDITY ; SENSIBLE HEAT ; WATER-VAPOR ; LATENT ; TEMPERATURE ; OCEAN ; SSM/I ; ACCURACY ; MODEL ; LAYER |
| 资助项目 | National Natural Science Foundation of China[42221005] ; National Natural Science Foundation of China[42090044] ; Qingdao Science and Technology for People's Livelihood Demonstration Special Project[25-1-5-cspz-18-nsh] ; National Science Foundation of China[42206202] |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001530269200034 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/202577]  |
| 专题 | 海洋研究所_海洋环流与波动重点实验室 |
| 通讯作者 | Li, Xiaofeng |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Oceanog, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China 3.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Observat & Forecasting, Qingdao 266071, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Mengjiao,Wang, Haoyu,Li, Xiaofeng. Enhancing Retrievals of Air-Sea Heat Fluxes From AMSR2 Microwave Observations Based on Deep Learning[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:17. |
| APA | Wang, Mengjiao,Wang, Haoyu,&Li, Xiaofeng.(2025).Enhancing Retrievals of Air-Sea Heat Fluxes From AMSR2 Microwave Observations Based on Deep Learning.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,17. |
| MLA | Wang, Mengjiao,et al."Enhancing Retrievals of Air-Sea Heat Fluxes From AMSR2 Microwave Observations Based on Deep Learning".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):17. |
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。