Predicting glacial lake outburst susceptibility on the southern Tibetan Plateau with historical events and machine learning methods

Huan Liu, Zhewei Wang, Hong Wen (), Nisong Pei, Zuqi Xia, Rui Bian, Song Ma and Ling Tao
Additional contact information
Huan Liu: Sichuan Anxin Kechuang Technology Co. Ltd
Zhewei Wang: China Railway Eryuan Engineering Group CO., LTD
Hong Wen: Xihua University
Nisong Pei: Chengdu University of Information Technology
Zuqi Xia: Xihua University
Rui Bian: Sichuan Anxin Kechuang Technology Co. Ltd
Song Ma: Sichuan Academy of Safety Science and Technology
Ling Tao: Xihua University

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2025, vol. 121, issue 15, No 16, 17677-17705

Abstract: Abstract Glacial Lake Outburst Floods (GLOFs) have inflicted varying degrees of damage on the ecological environment, infrastructure, and human life in the alpine regions. Consequently, effectively predicting GLOFs has emerged as a critical research focus for disaster prevention and mitigation. This study focuses on the southern Tibetan Plateau and systematically examines the distribution characteristics of glaciers and glacial lakes, which are key contributors to GLOFs, and reviews historical GLOF events and their developmental patterns using remote sensing imagery, geographic information systems (GIS) and machine learning techniques. Based on historical GLOF data, a susceptibility evaluation system was developed by integrating Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) algorithms. This system quantitatively assesses the susceptibility of each glacial lake within the study area. The findings indicate that the majority of historical GLOF events occurred between June and September, with triggering factors including icefalls, moraine dam destabilization, and heavy precipitation. Climate warming, particularly during the 1960s and from 1990 to 2020, has significantly influenced the frequency of GLOF events, revealing substantial spatial heterogeneity, glacial dependence, and climate sensitivity of GLOFs. The evaluation results show that approximately 17.4% of the glacial lakes are situated in high and very high susceptibility classes, with the highest susceptibility observed in the central and eastern sub-regions. The MLP model demonstrated slightly higher accuracy than the SVM model, with AUC (Area Under the Receiver Operating Characteristic Curve) values of 0.96 and 0.90, respectively. This study offers a novel methodology and technical support for assessing the risk of glacial lake outbursts in the Tibetan Plateau and similar alpine mountain regions, providing a scientific basis for the development of disaster prevention and mitigation strategies.

Keywords: Glacial lake outburst flood; Spatial pattern; Susceptibility evaluation; Machine learning method; Tibetan plateau (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-025-07486-8 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:121:y:2025:i:15:d:10.1007_s11069-025-07486-8

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-025-07486-8

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().