Deep-Learning-Based Marine Aquaculture Zone Extractions From Dual-Polarimetric SAR Imagery

doi:10.1109/JSTARS.2024.3384511

IOCAS-IR > 海洋环流与波动重点实验室

	Deep-Learning-Based Marine Aquaculture Zone Extractions From Dual-Polarimetric SAR Imagery
	Chen, Wantai 1,2; Li, Xiaofeng 1,3
	2024
发表期刊	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
ISSN	1939-1404
卷号	17 页码:8043-8057
通讯作者	Li, Xiaofeng(xiaofeng.li@ieee.org)
摘要	Efficient monitoring of marine aquaculture zones (MAZs) is crucial for facilitating coastal resource management. To achieve this, we developed a specialized deep convolutional neural network tailored for extracting MAZs from synthetic aperture radar (SAR) imagery, integrating prior analytical knowledge of MAZ imaging features. A total of 47 Sentinel-1 dual-polarized (VV and VH) SAR images spanning 2016-2023 in China's Subei Sandbanks along the Yellow Sea coast were collected due to appropriate tidal level and acquired time. We first comprehensively analyzed of normalized radar cross section (NRCS) values for MAZs under varying tidal levels and aquaculture facility structures. Rising tide-induced submergence resulted in a significant mean NRCS reduction of 7.01 dB (VV) and 4.54 dB (VH), causing MAZ signals to resemble seawater. In addition, during low tide, volume scattering from the net screen on the aquaculture rafts increased VH-polarized image recognizability, with a smaller NRCS overlap (64%) between MAZs and tidal flats compared to VV-polarized images. Hence, VH-polarized images taken during low tide with intact aquaculture facilities were selected for dataset construction due to their reliability in characterizing MAZs. Building upon the classical U-Net framework, we introduced four modifications informed by our imaging characteristics analysis to enhance the model's performance. Testing experiments demonstrated an impressive F1-score of 94.77%, highlighting the effectiveness of incorporating prior knowledge into refining deep learning models. Applying the model to SAR images from 2016 to 2023 revealed concentrated MAZs in the relatively flat southeastern Subei Sandbanks, with a noticeable scale decline post-2021 resulting in a 67.65% reduction over the years.
关键词	Aquaculture Radar polarimetry Imaging Tides Monitoring Task analysis Radar imaging Deep convolution neural networks (DCNNs) imaging characteristics marine aquaculture zones (MAZs) Sentinel-1 synthetic aperture radar (SAR)
DOI	10.1109/JSTARS.2024.3384511
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:001205792300012
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS关键词	TIDAL FLATS ; GREEN ; AREA
引用统计
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/185599
专题	海洋环流与波动重点实验室
通讯作者	Li, Xiaofeng
作者单位	1.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China 2.Univ Chinese Acad Sci, Coll Marine Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Ocean Mega Sci, Qingdao 266071, Peoples R China
第一作者单位	海洋环流与波动重点实验室
通讯作者单位	海洋环流与波动重点实验室
推荐引用方式 GB/T 7714	Chen, Wantai,Li, Xiaofeng. Deep-Learning-Based Marine Aquaculture Zone Extractions From Dual-Polarimetric SAR Imagery[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2024,17:8043-8057.
APA	Chen, Wantai,&Li, Xiaofeng.(2024).Deep-Learning-Based Marine Aquaculture Zone Extractions From Dual-Polarimetric SAR Imagery.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,17,8043-8057.
MLA	Chen, Wantai,et al."Deep-Learning-Based Marine Aquaculture Zone Extractions From Dual-Polarimetric SAR Imagery".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 17(2024):8043-8057.