Toward the development of deep learning analyses for snow avalanche releases in mountain regions

Authors

Yunzhi Chen, Xi'an University of Science and Technology
Wei Chen, Xi'an University of Science and Technology
Omid Rahmati, AREEO
Fatemeh Falah, Lorestan University
Dominik Kulakowski, Clark University
Saro Lee, Korea Institute of Geoscience and Mineral Resources
Fatemeh Rezaie, Korea Institute of Geoscience and Mineral Resources
Mahdi Panahi, Kangwon National University
Aref Bahmani, Natural Resources and Watershed Management Organization
Hamid Darabi, Oulun Yliopisto
Ali Torabi Haghighi, Oulun Yliopisto
Huiyuan Bian, Xi'an University of Science and Technology

Document Type

Article

Abstract

Snow avalanches impose a considerable threat to infrastructure and human safety in snow bound mountain areas. Nevertheless, the spatial prediction of snow avalanches has received little research attention in many vulnerable parts of the world, particularly in developing countries. The present study investigates the applicability of a stand alone convolutional neural network (CNN) model, as a deep learning approach, along with two metaheuristic algorithms including grey wolf optimization (CNN-GWO) and imperialist competitive algorithm (CNN-ICA) in snow avalanche modelling in the Darvan watershed, Iran. The analysis was based on thirteen potential drivers of avalanche occurrence and an inventory map of previously documented avalanche occurrences. The efficiency of models’ performance was evaluated by Area Under the Receiver Operating Characteristic curve (AUC) and the Root Mean Square Error (RMSE). The CNN-ICA model yielded the highest accuracy in both training (AUC= 0.982, RMSE = 0.067) and validation (AUC= 0.972, RMSE = 0.125) steps, followed by the CNN-GWO model (AUC of 0.975 for training, RMSE of 0.18 for training, AUC of 0.968 for validation, RMSE of 0.157 for validation). However, the standalone CNN model showed lower goodness-of-fit (AUC= 0.864, RMSE = 0.22) and predictive performance (AUC= 0.811, RMSE = 0.330). The approach utilized in this study is broadly applicable for identifying areas where avalanche hazard is likely to be high and where mitigation measures or corresponding land use planning should be prioritized.

Publication Title

Geocarto International

Publication Date

2021

ISSN

1010-6049

DOI

10.1080/10106049.2021.1986578

Keywords

artificial intelligence, GIS, natural disasters, Snow avalanche

Repository Citation

Chen, Yunzhi; Chen, Wei; Rahmati, Omid; Falah, Fatemeh; Kulakowski, Dominik; Lee, Saro; Rezaie, Fatemeh; Panahi, Mahdi; Bahmani, Aref; Darabi, Hamid; Torabi Haghighi, Ali; and Bian, Huiyuan, "Toward the development of deep learning analyses for snow avalanche releases in mountain regions" (2021). Geography. 264.
https://commons.clarku.edu/faculty_geography/264

Copyright Conditions

The available download is the accepted version of this work.