Search

In recent years, high resolution (HR) remote sensing images have brought significant changes to land cover monitoring. Monitoring water resources, a vital and scarce commodity for human survival, is a crucial aspect of land cover monitoring and forms the foundation for water resource allocation in regions facing shortages. Hence, a universal method is necessary to address this problem and handle large-scale water resources monitoring. We explore the network structure via improving the interpretability to reduce the network layers and propose a lightweight pixel-wise semantic segmentation model, which achieves waterbody extraction from GF-1 remote sensing images with high accuracy and high speed. The proposed model structure addresses both semantic segmentation for large and small waterbodies, extracting fine-grained edge and contour information from high-resolution feature maps. Additionally, it efficiently extracts multi-scale high-level semantic information using residual convolutional blocks and dilated convolutional blocks. The multi-scale feature maps are fused, and binary classification is predicted through Support Vector Machines (SVM). Furthermore, the paper introduces a model training method with an adaptive learning rate, reducing the overall training time. To validate the model's performance, remote sensing images from GF-1 are utilized to construct a dataset. Experimental results, compared with five models, demonstrate that the proposed method achieves the highest accuracy and least training time. [ABSTRACT FROM AUTHOR]

The studies on snow depth comprise a crucial area of research in the Indian Himalayas, where the seasonal snow cover primarily drives the rivers and significant water resources. In this paper, the initial estimates of the line of sight displacement obtained using differential interferometric phase in VV and VH polarizations using Sentinel-1 bi-temporal dual polarimetric SAR data corresponding to snow covered and snow free land cover, are improved by applying bias corrections for the snow phase and for residual errors in displacement derived from the corrected snow phase. The bias for the snow phase is computed from the observed phase in VV and VH polarizations for the snow free area and the bias for the residual errors is computed by observing the stationary pixels identified in the snow free area using a digital elevation model. The snow depth is computed as a weighted sum of the corrected displacements in the VV and VH polarization, with the weights derived using the local incidence angle. The snow depth results based on the proposed approach was evaluated with respect to field measurements and a coefficient of determination of 0.628 was observed with an improvement of ~0.4 as compared to the displacement observed in the VV and VH channel using the conventional method. [ABSTRACT FROM AUTHOR]