A Machine-Learning based Method for Glacier Lakes Extraction in Qinghai Tibet Plateau

• Main Authors: Chen, Hong, Chang, Sheng, Tong, Liqiang, Guo, Zhaocheng, Tu, Jienan, He, Peng
• Format: Conference Proceeding
• Language: English
• Subjects: Feature extraction; Glacier lake; Lakes; Machine learning; Product design; Qinghai Tibet Plateau; Quality assessment; random forest; Reliability; Task analysis
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS46834.2022.9884925

Glacier lake is one important component of the ecosystem of the Qinghai Tibet Plateau. The changes of glacier lakes are extremely sensitive to climate and environmental changes, and also closely related to water resources changes and geological disasters. In this study, the typical area of glacial lakes development in Qinghai Tibet Plateau was selected. To extract glacier lakes in this area, a machine-learning based method (MLB) was proposed with Landsat-8 and NASADEM dataset. Considering the spectral features and topographic features, a total of 14 parameters were taken as the inputs of the proposed MLB. Compared with the threshold segmentation method (TS), the MLB performed superior. The kappa coefficient (KC) and overall accuracy (OA) of the MLB method are 0.8602 and 99.49, respectively. While, those values of TS are 0.6123 and 98.88, respectively. The TS may fail under certain conditions, especially in the cloud shadow. The results reveals that the accuracy of glacial lake extraction in the high-altitude area may be improved with the MLB. There is a potential for automated glacial lake mapping with the MLB in rugged mountain areas at a large scale.