Abstract
Remote sensing monitoring of glacial lakes is an indispensable tool for identifying and preventing glacial lake disasters. At present, the existing extraction methods of glacial lakes based on Landsat remote sensing image have achieved remarkable results, but the algorithms used lack the ability to analyze glacial lake spectral and shape and texture features, and require manual design parameters to fine tune the automation of the algorithm. As a result, it cannot mine the depth features of glacier lakes in remote sensing images accurately enough. To address these challenges, this study designed a self-attention mechanism module U-net network that enhances the propagation of features, reduces information loss, strengthens the weight of glacial lake areas, restrains the weight of irrelevant features, reduces the influence of low image contrast on the model, and deals with the variety of pixel categories in glacial lakes. These features improve the performance of the model. Based on Landsat-8 images, we first extracted glacial lakes in large-scale alpine areas using a U-net network model. To make it a self-attention U-net network, we introduced the attention mechanism into the step connection part of the U-net network to adjust feature weight, focus on learning glacial lake features, and strengthen the network to extract the glacial lake features. Finally, we selected the combination of bands 3, 5, and 6 and all bands of Landsat-8 images sing the self-attention U-net network to extract glacial lakes in the study area and compared and analyzed the extraction results. The experimental results and analyses revealed that the proposed method can effectively segment glacial lakes from Landsat-8 remote sensing images. Its effectiveness was proven by different evaluation indices. Compared with a standard U-net network, the true positive for the combination of 3, 5, and 6 bands increased by 15.95% and for all bands by 5.79%. The area under curve for the whole study area reached 85.03% for all bands. The improved U-net network can, thus, meet the real time needs of glacial lake disaster information acquisition.
Highlights
G LACIAL lakes are natural bodies of water formed by modern glacial meltwater as the main supply source of stagnant water in moraine ridge depressions [1]
U-net and self-attention U-net network models were used to extract a large-scale glacial lake in the Alatau mountains based on a Landsat-8 remote sensing image
The 3, 5, and 6 bands of Landsat-8 image are sensitive to the water body, while the glacial lake is a special kind of water body, so it is necessary to extract glacial lake with the combination of 3, 5, and 6 bands
Summary
G LACIAL lakes are natural bodies of water formed by modern glacial meltwater as the main supply source of stagnant water in moraine ridge depressions [1]. Glacial lakes are the incubators of alpine glacial disasters and are important in the study of mountain disasters [2]. Many glacial lake collapse events have occurred in recent years, resulting in significant losses in life and property [3]. The real-time monitoring of glacial lakes is, essential. Glacial lakes are a special kind of lake with diverse features found at high altitudes. The geographic information contained in optical remote sensing images is complex, and the sensors of optical remote sensing satellites have multiband data, which are affected by different topographies and carry complex semantic information [4]. Glacial lakes can appear similar to some ground features (such as mountain shadows and melting glaciers), so it is difficult to extract the large-scale remote sensing data on glacial lakes accurately
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
