文献类型：期刊文献

英文题名：Detection of three-dimensional structures of oceanic eddies using artificial intelligence

作者：Xu, Guangjun[1,2];Xie, Wenhong[3];Lin, Xiayan[4];Liu, Yu[2,4];Hang, Renlong[5];Sun, Wenjin[2,3];Liu, Dazhao[1];Dong, Changming[2,3]

机构：[1]Guangdong Ocean Univ, Sch Elect & Informat Engn, Zhanjiang 524088, Peoples R China;[2]Southern Marine Sci & Engn Guangdong Lab Zhuhai, Zhuhai 519000, Peoples R China;[3]Nanjing Univ Informat Sci & Technol, Ocean Modeling & Observat Lab, Nanjing 210044, Peoples R China;[4]Zhejiang Ocean Univ, Marine Sci & Technol Coll, Zhoushan 316022, Peoples R China;[5]Nanjing Univ Informat Sci & Technol, Engn Res Ctr Digital Forens, Minist Educ, Nanjing 210044, Peoples R China

年份：2024

卷号：190

外文期刊名：OCEAN MODELLING

收录：SCI-EXPANDED(收录号：WOS:001264088300001)、、EI(收录号：20242116128934)、Scopus(收录号：2-s2.0-85193573473)、WOS

基金：This research is supported by the project supported by Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) (SML2020SP007) , National Key Research and Development Program of China (2023YFC3008200) , Guangdong Basic and Applied Basic Research Foundation (2019A1515110840) , State Key Laboratory of Tropic Oceanography, South China Sea Institute of Oceanology, Chinese Academy of Science (LTO2319) , and Research Startup Foundation of Guangdong Ocean University (R20009) . Thanks to Dr. Kenny T.C. Lim Kam Sian and Dr. Brandon J. Bethel for their contributions to this manuscript.

语种：英文

外文关键词：Three-dimensional structure of oceanic eddy; Artificial intelligence oceanography; 3D-U -Res -Net

外文摘要：Oceanic mesoscale eddies play an important role in transports of heat, freshwater, mass in the ocean, therefore understanding three-dimensional structure of oceanic eddies is of significance to climate study and oceanic applications. However, detection of three-dimensional (3D) structures is a big challenge though many algorithms of sea surface 2D eddy detection are developed. In this study, we present a novel approach by using 3D U-Net residual architecture (3D-U-Res-Net) to identify 3D structure of oceanic eddies. The sensitivity tests to input variables are conducted to optimalize the input setting. Trained by 3D eddy data provided by a kinetic eddy detection method, the AI-based method can identify different kinds of eddy vertical structures and moreover can dig out more eddy information in deeper layers. This study has significant implications for the further application of the AI-based algorithm in oceanic study.