Detecting Ocean Eddies with a Lightweight and Efficient Convolutional Network

As a ubiquitous mesoscale phenomenon, ocean eddies significantly impact ocean energy and mass exchange. Detecting these eddies accurately and efficiently has become a research focus in ocean remote sensing. Many traditional detection methods, rooted in physical principles, often encounter challenges...

Full description

Saved in:
Bibliographic Details
Main Authors: Haochen Sun, Hongping Li, Ming Xu, Tianyu Xia, Hao Yu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/24/4808
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102879895552000
author Haochen Sun
Hongping Li
Ming Xu
Tianyu Xia
Hao Yu
author_facet Haochen Sun
Hongping Li
Ming Xu
Tianyu Xia
Hao Yu
author_sort Haochen Sun
collection DOAJ
description As a ubiquitous mesoscale phenomenon, ocean eddies significantly impact ocean energy and mass exchange. Detecting these eddies accurately and efficiently has become a research focus in ocean remote sensing. Many traditional detection methods, rooted in physical principles, often encounter challenges in practical applications due to their complex parameter settings, while effective, deep learning models can be limited by the high computational demands of their extensive parameters. Therefore, this paper proposes a new approach to eddy detection based on the altimeter data, the Ghost Attention Deeplab Network (GAD-Net), which is a lightweight and efficient semantic segmentation model designed to address these issues. The encoder of GAD-Net consists of a lightweight ECA+GhostNet and an Atrous Spatial Pyramid Pooling (ASPP) module. And the decoder integrates an Efficient Attention Network (EAN) module and an Efficient Ghost Feature Integration (EGFI) module. Experimental results show that GAD-Net outperforms other models in evaluation indices, with a lighter model size and lower computational complexity. It also outperforms other segmentation models in actual detection results in different sea areas. Furthermore, GAD-Net achieves detection results comparable to the Py-Eddy-Tracker (PET) method with a smaller eddy radius and a faster detection speed. The model and the constructed eddy dataset are publicly available.
format Article
id doaj-art-b746edf3cfe747428efe8c24d17f3365
institution Kabale University
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-b746edf3cfe747428efe8c24d17f33652024-12-27T14:51:23ZengMDPI AGRemote Sensing2072-42922024-12-011624480810.3390/rs16244808Detecting Ocean Eddies with a Lightweight and Efficient Convolutional NetworkHaochen Sun0Hongping Li1Ming Xu2Tianyu Xia3Hao Yu4College of Marine Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Marine Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Marine Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Marine Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaCollege of Marine Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, ChinaAs a ubiquitous mesoscale phenomenon, ocean eddies significantly impact ocean energy and mass exchange. Detecting these eddies accurately and efficiently has become a research focus in ocean remote sensing. Many traditional detection methods, rooted in physical principles, often encounter challenges in practical applications due to their complex parameter settings, while effective, deep learning models can be limited by the high computational demands of their extensive parameters. Therefore, this paper proposes a new approach to eddy detection based on the altimeter data, the Ghost Attention Deeplab Network (GAD-Net), which is a lightweight and efficient semantic segmentation model designed to address these issues. The encoder of GAD-Net consists of a lightweight ECA+GhostNet and an Atrous Spatial Pyramid Pooling (ASPP) module. And the decoder integrates an Efficient Attention Network (EAN) module and an Efficient Ghost Feature Integration (EGFI) module. Experimental results show that GAD-Net outperforms other models in evaluation indices, with a lighter model size and lower computational complexity. It also outperforms other segmentation models in actual detection results in different sea areas. Furthermore, GAD-Net achieves detection results comparable to the Py-Eddy-Tracker (PET) method with a smaller eddy radius and a faster detection speed. The model and the constructed eddy dataset are publicly available.https://www.mdpi.com/2072-4292/16/24/4808eddy detectiondeep learningsemantic segmentationlightweightghost attention deeplab network (GAD-Net)
spellingShingle Haochen Sun
Hongping Li
Ming Xu
Tianyu Xia
Hao Yu
Detecting Ocean Eddies with a Lightweight and Efficient Convolutional Network
Remote Sensing
eddy detection
deep learning
semantic segmentation
lightweight
ghost attention deeplab network (GAD-Net)
title Detecting Ocean Eddies with a Lightweight and Efficient Convolutional Network
title_full Detecting Ocean Eddies with a Lightweight and Efficient Convolutional Network
title_fullStr Detecting Ocean Eddies with a Lightweight and Efficient Convolutional Network
title_full_unstemmed Detecting Ocean Eddies with a Lightweight and Efficient Convolutional Network
title_short Detecting Ocean Eddies with a Lightweight and Efficient Convolutional Network
title_sort detecting ocean eddies with a lightweight and efficient convolutional network
topic eddy detection
deep learning
semantic segmentation
lightweight
ghost attention deeplab network (GAD-Net)
url https://www.mdpi.com/2072-4292/16/24/4808
work_keys_str_mv AT haochensun detectingoceaneddieswithalightweightandefficientconvolutionalnetwork
AT hongpingli detectingoceaneddieswithalightweightandefficientconvolutionalnetwork
AT mingxu detectingoceaneddieswithalightweightandefficientconvolutionalnetwork
AT tianyuxia detectingoceaneddieswithalightweightandefficientconvolutionalnetwork
AT haoyu detectingoceaneddieswithalightweightandefficientconvolutionalnetwork