Debris flow susceptibility mapping in mountainous area based on multi-source data fusion and CNN model - taking Nujiang Prefecture, China as an example

• Published in: International journal of digital earth Vol. 15; no. 1; pp. 1966 - 1988
• Main Authors: Xu, Fanshu, Wang, Baoyun
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 31.12.2022; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Artificial neural networks; Canyons; China; Convolution; convolutional neural networks; Data integration; Debris flow; Detritus; Digital Elevation Models; disaster prediction; Evaluation; Feature extraction; Flow mapping; Hydrologic data; landscapes; Lithology; Machine learning; mass movement; Mountain regions; Mountainous areas; mountainous valleys; Mountains; Neural networks; Precipitation; Remote sensing; Soil types; Susceptibility; Valleys; China
• ISSN: 1753-8947; 1753-8955; 1753-8955
• DOI: 10.1080/17538947.2022.2142304

Efforts to evaluate the susceptibility of debris flows in large areas, especially in mountainous regions, are often hampered by the alpine and canyon terrain. This paper proposes a convolution neural network (CNN) model named dense residual shuffle net (DRSNet). It is successfully applied to Nujiang Prefecture in Yunnan Province of China, a typical alpine area with frequent debris flows. DRSNet uses digital elevation model, remote sensing, lithology, soil type and precipitation data as input. First, dense connection and residual structure were used to extract the shallow features of various data. Next, channel shuffle, fuse block and fully connection were applied to strengthen the correlation between different shallow features and give inner danger scores. Finally, precipitation as the activation factor was introduced giving the valleys susceptibility. To verify the feasibility of DRSNet, comparative tests were conducted on 7 CNN models and 3 other machine learning (ML) methods. Experimental results show that DRSNet can achieve 78.6% accuracy in debris flow valley classification, which is at least 7.4% higher than common CNN models and 15.2% higher than other ML methods. This article provides new ideas for debris flow susceptibility evaluation.