CRAUnet++: A New Convolutional Neural Network for Land Surface Water Extraction from Sentinel-2 Imagery by Combining RWI with Improved Unet++
-
Published:2024-09-12
Issue:18
Volume:16
Page:3391
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Li Nan12, Xu Xiaohua34, Huang Shifeng12, Sun Yayong12ORCID, Ma Jianwei12, Zhu He12, Hu Mengcheng12ORCID
Affiliation:
1. State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100038, China 2. Research Center on Flood & Drought Disaster Prevention and Reduction of the Ministry of Water Resources, Beijing 100038, China 3. Jiangxi Provincial Institute of Water Science, Nanchang 330000, China 4. Jiangxi Provincial Technology Innovation Center for Ecological Water Engineering in Poyang Lake Basin, Nanchang 330000, China
Abstract
Accurately mapping the surface water bodies through remote sensing technology is of great significance for water resources management, flood monitoring, and drought monitoring. At present, many scholars at home and abroad carry out research on deep learning image recognition algorithms based on convolutional neural networks, and a variety of variant-based convolutional neural networks are proposed to be applied to extract water bodies from remote sensing images. However, due to the low depth of convolutional layers employed and underutilization of water spectral feature information, most of the water body extraction methods based on convolutional neural networks (CNNs) for remote sensing images are limited in accuracy. In this study, we propose a novel surface water automatic extraction method based on the convolutional neural network (CRAUnet++) for Sentinel-2 images. The proposed method includes three parts: (1) substituting the feature extractor of the original Unet++ with ResNet34 to enhance the network’s complexity by increasing its depth; (2) Embedding the Spatial and Channel ‘Squeeze and Excitation’ (SCSE) module into the up-sampling stage of the network to suppress background features and amplify water body features; (3) adding the vegetation red edge-based water index (RWI) into the input data to maximize the utilization of water body spectral information of Sentinel-2 images without increasing the data processing time. To verify the performance and accuracy of the proposed algorithm, the ablation experiment under four different strategies and comparison experiment with different algorithms of RWI, FCN, SegNet, Unet, and DeepLab v3+ were conducted on Sentinel-2 images of the Poyang Lake. The experimental result shows that the precision, recall, F1, and IoU of CRAUnet++ are 95.99%, 96.41%, 96.19%, and 92.67%, respectively. CRAUnet++ has a good performance in extracting various types of water bodies and suppressing noises because it introduces SCSE attention mechanisms and combines surface water spectral features from RWI, exceeding that of the other five algorithms. The result demonstrates that CRAUnet++ has high validity and reliability in extracting surface water bodies based on Sentinel-2 images.
Funder
the Key Research and Development Program of Jiangxi Province the Youth Innovation Talents Promotion Plan of the Research Center of Flood and Drought Disaster Reduction of the Ministry of Water Resources, IWHR
Reference61 articles.
1. Performance of Landsat-8 and Sentinel-2 Surface Reflectance Products for River Remote Sensing Retrievals of Chlorophyll-a and Turbidity;Kuhn;Remote Sens. Environ.,2019 2. Wang, R., Zhang, C., Chen, C., Hao, H., Li, W., and Jiao, L. (2024). A Multi-Modality Fusion and Gated Multi-Filter U-Net for Water Area Segmentation in Remote Sensing. Remote Sens., 16. 3. Liu, J., and Wang, Y. (2022). Water Body Extraction in Remote Sensing Imagery Using Domain Adaptation-Based Network Embedding Selective Self-Attention and Multi-Scale Feature Fusion. Remote Sens., 14. 4. Li, J., Ma, R., Cao, Z., Xue, K., Xiong, J., Hu, M., and Feng, X. (2022). Satellite Detection of Surface Water Extent: A Review of Methodology. Water, 14. 5. Remote sensing applications for reservoir water level monitoring, sustainable water surface management, and environmental risks in Quang Nam province, Vietnam;Quang;J. Water Clim. Chang.,2021
|
|