Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 Imagery

Tidal creeks are vital geomorphological features of tidal flats, and their spatial and temporal variations contribute significantly to the preservation of ecological diversity and the spatial evolution of coastal wetlands. Traditional methods, such as manual annotation and machine learning, remain c...

Full description

Saved in:
Bibliographic Details
Main Authors: Bojie Chen, Qianran Zhang, Na Yang, Xiukun Wang, Xiaobo Zhang, Yilan Chen, Shengli Wang
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/4/676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718723759308800
author Bojie Chen
Qianran Zhang
Na Yang
Xiukun Wang
Xiaobo Zhang
Yilan Chen
Shengli Wang
author_facet Bojie Chen
Qianran Zhang
Na Yang
Xiukun Wang
Xiaobo Zhang
Yilan Chen
Shengli Wang
author_sort Bojie Chen
collection DOAJ
description Tidal creeks are vital geomorphological features of tidal flats, and their spatial and temporal variations contribute significantly to the preservation of ecological diversity and the spatial evolution of coastal wetlands. Traditional methods, such as manual annotation and machine learning, remain common for tidal creek extraction, but they are slow and inefficient. With increasing data volumes, accurately analyzing tidal creeks over large spatial and temporal scales has become a significant challenge. This study proposes a residual U-Net model that utilizes full-dimensional dynamic convolution to segment tidal creeks in the Yellow River Delta, employing Gaofen-2 satellite images with a resolution of 4 m. The model replaces the traditional convolutions in the residual blocks of the encoder with Omni-dimensional Dynamic Convolution (ODConv), mitigating the loss of fine details and improving segmentation for small targets. Adding coordinate attention (CA) to the Atrous Spatial Pyramid Pooling (ASPP) module improves target classification and localization in remote sensing images. Including dice coefficients in the focal loss function improves the model’s gradient and tackles class imbalance within the dataset. Furthermore, the inclusion of dice coefficients in the focal loss function improves the gradient of the model and tackles the dataset’s class inequality. The study results indicate that the model attains an F1 score and kappa coefficient exceeding 80% for both mud and salt marsh regions. Comparisons with several semantic segmentation models on the mud marsh tidal creek dataset show that ODU-Net significantly enhances tidal creek segmentation, resolves class imbalance issues, and delivers superior extraction accuracy and stability.
format Article
id doaj-art-5fb1f6b720804d78a75063e3568fe698
institution DOAJ
issn 2072-4292
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-5fb1f6b720804d78a75063e3568fe6982025-08-20T03:12:19ZengMDPI AGRemote Sensing2072-42922025-02-0117467610.3390/rs17040676Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 ImageryBojie Chen0Qianran Zhang1Na Yang2Xiukun Wang3Xiaobo Zhang4Yilan Chen5Shengli Wang6College of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaFirst Institute of Oceanography, Ministry of Natural Resources (MNR), Qingdao 266061, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaTidal creeks are vital geomorphological features of tidal flats, and their spatial and temporal variations contribute significantly to the preservation of ecological diversity and the spatial evolution of coastal wetlands. Traditional methods, such as manual annotation and machine learning, remain common for tidal creek extraction, but they are slow and inefficient. With increasing data volumes, accurately analyzing tidal creeks over large spatial and temporal scales has become a significant challenge. This study proposes a residual U-Net model that utilizes full-dimensional dynamic convolution to segment tidal creeks in the Yellow River Delta, employing Gaofen-2 satellite images with a resolution of 4 m. The model replaces the traditional convolutions in the residual blocks of the encoder with Omni-dimensional Dynamic Convolution (ODConv), mitigating the loss of fine details and improving segmentation for small targets. Adding coordinate attention (CA) to the Atrous Spatial Pyramid Pooling (ASPP) module improves target classification and localization in remote sensing images. Including dice coefficients in the focal loss function improves the model’s gradient and tackles class imbalance within the dataset. Furthermore, the inclusion of dice coefficients in the focal loss function improves the gradient of the model and tackles the dataset’s class inequality. The study results indicate that the model attains an F1 score and kappa coefficient exceeding 80% for both mud and salt marsh regions. Comparisons with several semantic segmentation models on the mud marsh tidal creek dataset show that ODU-Net significantly enhances tidal creek segmentation, resolves class imbalance issues, and delivers superior extraction accuracy and stability.https://www.mdpi.com/2072-4292/17/4/676tidal creek segmentationResBlockU-Netattention mechanismremote sensingcoastal wetlands
spellingShingle Bojie Chen
Qianran Zhang
Na Yang
Xiukun Wang
Xiaobo Zhang
Yilan Chen
Shengli Wang
Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 Imagery
Remote Sensing
tidal creek segmentation
ResBlock
U-Net
attention mechanism
remote sensing
coastal wetlands
title Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 Imagery
title_full Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 Imagery
title_fullStr Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 Imagery
title_full_unstemmed Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 Imagery
title_short Deep Learning Extraction of Tidal Creeks in the Yellow River Delta Using GF-2 Imagery
title_sort deep learning extraction of tidal creeks in the yellow river delta using gf 2 imagery
topic tidal creek segmentation
ResBlock
U-Net
attention mechanism
remote sensing
coastal wetlands
url https://www.mdpi.com/2072-4292/17/4/676
work_keys_str_mv AT bojiechen deeplearningextractionoftidalcreeksintheyellowriverdeltausinggf2imagery
AT qianranzhang deeplearningextractionoftidalcreeksintheyellowriverdeltausinggf2imagery
AT nayang deeplearningextractionoftidalcreeksintheyellowriverdeltausinggf2imagery
AT xiukunwang deeplearningextractionoftidalcreeksintheyellowriverdeltausinggf2imagery
AT xiaobozhang deeplearningextractionoftidalcreeksintheyellowriverdeltausinggf2imagery
AT yilanchen deeplearningextractionoftidalcreeksintheyellowriverdeltausinggf2imagery
AT shengliwang deeplearningextractionoftidalcreeksintheyellowriverdeltausinggf2imagery