|国家科技期刊平台
| 注册
首页|期刊导航|大气和海洋科学快报（英文版）|Intelligent identification of oceanic eddies in remote sensing data via Dual-Pyramid UNet

Intelligent identification of oceanic eddies in remote sensing data via Dual-Pyramid UNet

Nan Zhao Baoxiang Huang Xinmin Zhang Linyao Ge Ge Chen

大气和海洋科学快报（英文版）2023，Vol.16Issue(4)：29-36,8.
✕
大气和海洋科学快报（英文版）2023，Vol.16Issue(4)：29-36,8.DOI:10.1016/j.aosl.2023.100335

Intelligent identification of oceanic eddies in remote sensing data via Dual-Pyramid UNet

Intelligent identification of oceanic eddies in remote sensing data via Dual-Pyramid UNet

Nan Zhao 1Baoxiang Huang 2Xinmin Zhang 1Linyao Ge 3Ge Chen4

作者信息

  • 1. School of Computer Science and Technology,Qingdao University,Qingdao,China
  • 2. School of Computer Science and Technology,Qingdao University,Qingdao,China||Laboratory for Regional Oceanography and Numerical Modeling,Laoshan Laboratory,Qingdao,China
  • 3. School of Marine Technology,Institute for Advanced Ocean Study,Ocean University of China,Qingdao,China
  • 4. Laboratory for Regional Oceanography and Numerical Modeling,Laoshan Laboratory,Qingdao,China||School of Marine Technology,Institute for Advanced Ocean Study,Ocean University of China,Qingdao,China
  • 折叠

摘要

Abstract

海洋涡旋是大洋中重要的组成部分,对海洋能量和物质的输送至关重要.海洋涡旋的检测和表征无论是对于海洋气象学,海洋声学还是海洋生物学等领域都具有重要的研究价值.本文基于UNet架构,并结合金字塔分割注意力(PSA)模块和空洞空间卷积池化金字塔(ASPP)构造了Dual-Pyramid UNet模型,以平面异常和海表面温度数据中进行海洋涡旋的识别.实验在北大西洋和南大西洋两个涡旋活跃区域进行并选用多个评价指标对识别结果进行评价以证明模型的优异性能.

关键词

海洋涡旋识别/深度学习/金字塔分割注意/空洞空间卷积池化金字塔/U型网络架构

Key words

Oceanic eddy identification/Deep learning/Pyramid split attention/Atrous spatial pyramid pooling/UNet network

引用本文复制引用

Nan Zhao,Baoxiang Huang,Xinmin Zhang,Linyao Ge,Ge Chen..Intelligent identification of oceanic eddies in remote sensing data via Dual-Pyramid UNet[J].大气和海洋科学快报（英文版）,2023,16(4):29-36,8.

基金项目

This research was financially supported by the International Re-search Center of Big Data for Sustainable Development Goals[grant number CBAS2022GSP01],the National Natural Science Foundation of China[grant numbers 42276203 and 42030406],the Natural Science Foundation of Shandong Province[grant number ZR2021MD001],and the Laoshan Laboratory[grant number LSKJ202204302]. （）

大气和海洋科学快报（英文版）

OACSCD

1674-2834

访问量0
|
下载量0
段落导航相关论文