Comparing Methods for Segmenting Supra-Glacial Lakes and Surface Features in the Mount Everest Region of the Himalayas Using Chinese GaoFen-3 SAR Images

Fang Chen

doi:10.3390/rs13132429

Abstract

Glaciers and numerous glacial lakes that are produced by glacier melting are key indicators of climate change. Often overlooked, supra-glacial lakes develop in the melting area in the low-lying part of a glacier and appear to be highly variable in their size, shape, and location. The lifespan of these lakes is thought to be quite transient, since the lakes may be completely filled by water and burst out within several weeks. Changes in supra-glacial lake outlines and other surface features such as supra-glacial rivers and crevasses on the glaciers are useful indicators for the direct monitoring of glacier changes. Synthetic aperture radar (SAR) is not affected by weather and climate, and is an effective tool for study of glaciated areas. The development of the Chinese GaoFen-3 (GF-3) SAR, which has high spatial and temporal resolution and high-precision observation performance, has made it possible to obtain dynamic information about glaciers in more detail. In this paper, the classical Canny operator, the variational B-spline level-set method, and U-Net-based deep-learning model were applied and compared to extract glacial lake outlines and other surface features using different modes and Chinese GF-3 SAR imagery in the Mount Everest Region of the Himalayas. Particularly, the U-Net-based deep-learning method, which was independent of auxiliary data and had a high degree of automation, was used for the first time in this context. The experimental results showed that the U-Net-based deep-learning model worked best in the segmentation of supra-glacial lakes in terms of accuracy (Precision = 98.45% and Recall = 95.82%) and segmentation efficiency, and was good at detecting small, elongated, and ice-covered supra-glacial lakes. We also found that it was useful for accurately identifying the location of supra-glacial streams and ice crevasses on glaciers, and quantifying their width. Finally, based on the time series of the mapping results, the spatial characteristics and temporal evolution of these features over the glaciers were comprehensively analyzed. Overall, this study presents a novel approach to improve the detection accuracy of glacier elements that could be leveraged for dynamic monitoring in future research.

Highlights

Apart from the fact that it is routinely not affected by cloud cover, as shown in the yellow rectangle in Figure 4, it can detect some supra-glacial lakes that appear confused by the boundary in the optical images
In the Landsat-8 OLI image, these mixed pixels of glacial lakes exhibited mixed reflectance, as shown in the red rectangle in Figure 4a; while in the Synthetic aperture radar (SAR) imagery, the presence of an obviously low backscattering signal for all the lakes ensured that the SAR intensity data could extract both the clean and dirty supra-glacial lakes within an ablation zone
Based on the derived supra-glacial outlines andexisted other important closely related to the long-term melting lake of glaciers; they on the flatlinear glacierfeatures surface such as supra-glacial streams and ice crevasses, we study the characteristics with gentle changes in slope on both sides of the river (Figure 9)

Summary

Introduction

Most TP glaciers have experienced accelerated thinning and melting. This has been accompanied by the formation and evolution of a large number of glacial lakes, and may induce secondary glacial lake outburst flood (GLOF)-related disasters [3]. Background image is from GF-3 UFS imagery on 10 September 2020. (b) Other lake inventory data used for comparison, from Chen et al in 2017 and Wang et al in 2018. The white glacial lake inventory data used for comparison, from Chen et al in 2017 and Wang et al in 2018. Lines denote the boundary of the glacier terminus. The white lines denote the boundary of the glacier terminus. According to the analysis above, we could conclude that glacial lake outlines and other linear features found from GF-3 SAR images using the U-Net-based deep-learning method were more accurate, and distinct than found in other glacial lake

Objectives

Methods

Results

Discussion

Conclusion