Search

The Shishapangma region, situated in the middle of the Himalayas, is rich in glacial lakes and glaciers. Hence, glacial lake outburst floods (GLOFs) have become a top priority because of the severe threat posed by GLOFs to the downstream settlements. This study presents a comprehensive analysis of GLOF hazards using multi-source remote sensing datasets and designs a flood model considering the different breaching depths and release volumes for the Galong Co region. Based on high-resolution optical images, we derived the expanding lake area and volume of glacial lakes. We monitored deformation velocity and long-term deformation time series around the lake dam with Small BAseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR). The glacier thinning trend was obtained from the difference in the Digital Elevation Model (DEM). We identified potential avalanche sources by combining topographic slope and measurable deformation. We then carried out flood modeling under three different scenarios using the hydrodynamic model HEC-RAS for Galong Co, which is formed upstream of Nyalam. The results show that the Nyalam region is exposed to high-intensity GLOFs in all scenarios. The larger breaching depth and release volumes caused a greater flow depth and peak discharge. Overall, the multiple remote sensing approaches can be applied to other glacial lakes, and the modeling can be used as a basis for GLOF mitigation. [ABSTRACT FROM AUTHOR]

The efficiency and accuracy of grid-based computational fluid dynamics methods are strongly dependent on the chosen cell size. The computational time increases exponentially with decreasing cell size. Therefore, a grid coarsing technology without apparent precision loss is essential for various numerical modeling methods. In this article, a physical adaption neural network (PANN) is proposed to optimize coarse grid representation from a fine grid. A new convolutional neural network is constructed to achieve a significant reduction in computational cost while maintaining a relatively accurate solution. An application to numerical modeling of dynamic processes in landslides is firstly carried out, and better results are obtained compared to the baseline method. More applications in various flood scenarios in mountainous areas are then analyzed. It is demonstrated that the proposed PANN downscaling method outperforms other currently widely used downscaling methods. The code is publicly available and can be applied broadly. Computing by PANN is hundreds of times more efficient, meaning that it is significant for the numerical modeling of various complicated Earth-surface flows and their applications. [ABSTRACT FROM AUTHOR]

Unlike conventional natural (RGB) images, the inherent large scale and complex structures of remote sensing images pose major challenges such as spatial object distribution diversity and spectral information extraction when existing models are directly applied for image classification. In this study, we develop an attention-based pyramid network for segmentation and classification of remote sensing datasets. Attention mechanisms are used to develop the following modules: (i) a novel and robust attention-based multi-scale fusion method effectively fuses useful spatial or spectral information at different and same scales; ( i i ) a region pyramid attention mechanism using region-based attention addresses the target geometric size diversity in large-scale remote sensing images; and ( i i i ) cross-scale attention in our adaptive atrous spatial pyramid pooling network adapts to varied contents in a feature-embedded space. Different forms of feature fusion pyramid frameworks are established by combining these attention-based modules. First, a novel segmentation framework, called the heavy-weight spatial feature fusion pyramid network (FFPNet), is proposed to address the spatial problem of high-resolution remote sensing images. Second, an end-to-end spatial-spectral FFPNet is presented for classifying hyperspectral images. Experiments conducted on ISPRS Vaihingen and ISPRS Potsdam high-resolution datasets demonstrate the competitive segmentation accuracy achieved by the proposed heavy-weight spatial FFPNet. Furthermore, experiments on the Indian Pines and the University of Pavia hyperspectral datasets indicate that the proposed spatial-spectral FFPNet outperforms the current state-of-the-art methods in hyperspectral image classification. [ABSTRACT FROM AUTHOR]