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
AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility

文献类型：期刊论文

作者Jiang, Jiawei1,5; Mo, Huier10; Zhang, Lin1,9; Wan, Liying10; Zhang, Xiangguang6,7,8; Drevillon, Marie4; Xu, Boya6; Wang, Jun3; Xin, Jinyuan2; Ma, Yining2
刊名INTERNATIONAL JOURNAL OF DIGITAL EARTH
出版日期2025-12-31
卷号18期号:2页码:20
关键词Three-dimensional ocean structures remote sensing data spatiotemporal resolution multiscale residual attention mechanism data-driven forecasting marine environment prediction
ISSN号1753-8947
DOI10.1080/17538947.2025.2595786
通讯作者Zhang, Lin(zl_hjs123@163.com) ; Zhang, Xiangguang(zxg@qdio.ac.cn)
英文摘要Accurate prediction of three-dimensional (3D) ocean structures is essential for understanding oceanic processes. While AI-based ocean models demonstrate superior forecasting performance, they typically depend on numerically simulated 3D background structures as input, leading to operational limitations and significant computational expenses. This study explores a method for directly forecasting high-spatiotemporal resolution 3D ocean temperature structures using multisource remote sensing data in '2D-to-3D' mode, comparing it with predictions from 3D numerical simulation background structure profiles in '3D-to-3D' mode. We propose a multiscale residual spatiotemporal window attention model (MSWO) for 1/12 degrees resolution forecasting. Extensive experiments are conducted using the world-leading ocean prediction intercomparison and validation task team (IV-TT) Class4 intercomparison framework to evaluate the model's performance. Benchmarked against mainstream forecasting systems, MSWO achieves comparable accuracy to operational models in 2D-to-3D mode and superior accuracy in 3D-to-3D mode. Furthermore, the MSWO model outperforms other data-driven artificial intelligence models in terms of training cost and accuracy. This study demonstrates the feasibility of deriving high-spatiotemporal-resolution 3D ocean forecasts from satellite remote sensing.
WOS关键词SYSTEM
资助项目the CAS (Chinese Academy of Sciences) Program[DSS-WXGZ-2022] ; National Natural Science Foundation of China[42176030] ; National Key Research and Development Program of China[2021YFC2100900]
WOS研究方向Physical Geography ; Remote Sensing
语种英语
WOS记录号WOS:001634651600001
出版者TAYLOR & FRANCIS LTD
源URL[http://ir.qdio.ac.cn/handle/337002/204369]  
专题海洋研究所_海洋环流与波动重点实验室
通讯作者Zhang, Lin; Zhang, Xiangguang
作者单位1.Laoshan Lab, Qingdao 266237, Peoples R China
2.Chinese Acad Sci, Inst Atmospher Phys, Beijing, Peoples R China
3.Natl Univ Def Technol, Changsha, Peoples R China
4.Mercator Ocean Int, Toulouse, France
5.Shandong Univ, Inst Marine Sci & Technol, Qingdao, Peoples R China
6.Univ Chinese Acad Sci, Beijing, Peoples R China
7.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China
8.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Observat & Forecasting, Qingdao 266071, Peoples R China
9.Navy Submarine Acad, Qingdao, Peoples R China
10.Natl Marine Environm Forecasting Ctr, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Jiang, Jiawei,Mo, Huier,Zhang, Lin,et al. AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility[J]. INTERNATIONAL JOURNAL OF DIGITAL EARTH,2025,18(2):20.
APA Jiang, Jiawei.,Mo, Huier.,Zhang, Lin.,Wan, Liying.,Zhang, Xiangguang.,...&Ma, Yining.(2025).AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility.INTERNATIONAL JOURNAL OF DIGITAL EARTH,18(2),20.
MLA Jiang, Jiawei,et al."AI performs on high-resolution three-dimensional ocean temperature forecasting: remote sensing data-driven becomes a new possibility".INTERNATIONAL JOURNAL OF DIGITAL EARTH 18.2(2025):20.

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。