中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 海洋研究所
  3. 中国科学院海洋研究所
  4. 海洋环流与波动重点实验室
SWO: A Lightweight Window Spatiotemporal Attention Network Reconstructs Subsurface Temperature Structure

文献类型：期刊论文

作者Jiang, Jiawei2,3; Wang, Jun4,5; Liu, Yiping1; Feng, Liqiang8; Jiang, Qiufu2; Huang, Chao2; Xiang, Liang2; Zhang, Xiangguang2,6,7
刊名IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
出版日期2024
卷号17页码:19274-19287
关键词Spatiotemporal phenomena Oceans Computational modeling Image reconstruction Computer architecture Remote sensing Ocean temperature Lightweight satellite observations spatiotemporal attention mechanism Spatiotemporal Window Ocean (SWO) temperature structure reconstruction
ISSN号1939-1404
DOI10.1109/JSTARS.2024.3427845
通讯作者Zhang, Xiangguang(zxg@qdio.ac.cn)
英文摘要Satellite remote sensing enables the extensive, long-term observation of oceanic changes. To achieve transparent ocean observation, artificial intelligence is innovatively used to reconstruct the three-dimensional ocean structure from remote sensing data with spatiotemporal attention. However, high-resolution satellite imagery imposes high computational demands. This study proposes Spatiotemporal Window Ocean (SWO), which is an efficient network that uses a special calculation strategy and spatiotemporal window attention to reduce complexity. The model integrates multiple satellite data sources, including sea surface temperature, absolute dynamic topography, and sea surface salinity. Our experimental results demonstrate that SWO achieves lower computational costs and superior performance compared with recent commonly used spatiotemporal sequence models. Specifically, SWO requires a training time equivalent to 1/3 of SimVP, 1/4 of PredRNN, and 1/5 of SA-ConvLSTM while achieving a root mean square error index that is 13.8%, 20.3%, and 13.2% better, respectively. The computational advantages of SWO offer an important technical means for the high-resolution reconstruction of ocean phenomena in the future.
WOS关键词OCEAN MODEL
资助项目National Key Research and Development Program[2021YFC3101504] ; National Natural Science Foundation of China[42176030] ; High Level Innovative Talent Project of NUDT ; Technology Support Talent Program of the Chinese Academy of Sciences[E4KY31] ; Chinese Academy of Sciences pilot project[XDB42000000] ; Major Science and Technology Infrastructure Maintenance and Reconstruction Project of the Chinese Academy of Sciences[DSS WXGZ-2022]
WOS研究方向Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:001346124200001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://ir.qdio.ac.cn/handle/337002/199420]  
专题海洋研究所_海洋环流与波动重点实验室
通讯作者Zhang, Xiangguang
作者单位1.China Geol Survey, Yantai Ctr Coastal Zone Geol Survey, Yantai 100037, Peoples R China
2.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266003, Peoples R China
3.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
4.Natl Univ Def Technol, Coll Meteorol & Oceanog, Changsha 410073, Peoples R China
5.Hunan Key Lab Marine Detect Technol, Changsha 410073, Peoples R China
6.Qingdao Marine Sci & Technol Ctr, Lab Ocean Dynam & Climate, Qingdao 266237, Peoples R China
7.Univ Chinese Acad Sci, Coll Marine Sci, Qingdao 266101, Peoples R China
8.Chinese Acad Sci, Inst Oceanol, Ocean Big Data Ctr, Qingdao 266003, Peoples R China
推荐引用方式
GB/T 7714		 Jiang, Jiawei,Wang, Jun,Liu, Yiping,et al. SWO: A Lightweight Window Spatiotemporal Attention Network Reconstructs Subsurface Temperature Structure[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2024,17:19274-19287.
APA Jiang, Jiawei.,Wang, Jun.,Liu, Yiping.,Feng, Liqiang.,Jiang, Qiufu.,...&Zhang, Xiangguang.(2024).SWO: A Lightweight Window Spatiotemporal Attention Network Reconstructs Subsurface Temperature Structure.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,17,19274-19287.
MLA Jiang, Jiawei,et al."SWO: A Lightweight Window Spatiotemporal Attention Network Reconstructs Subsurface Temperature Structure".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 17(2024):19274-19287.

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。