Debris flow susceptibility mapping in mountainous area based on multi-source data fusion and CNN model – taking Nujiang Prefecture, China as an example
Authors:
Open Access
- 14 November 2022
- journal article
- research article
- Published by Taylor & Francis in International Journal of Digital Earth
- Vol. 15 (1) , 1966-1988
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (61966040)
This publication has 46 references indexed in Scilit:
- Assessment of flood hazard areas at a regional scale using an index-based approach and Analytical Hierarchy Process: Application in Rhodope–Evros region, GreeceScience of The Total Environment, 2015
- Assessing debris flow susceptibility in Heshigten Banner, Inner Mongolia, China, using principal component analysis and an improved fuzzy C-means algorithmBulletin of Engineering Geology and the Environment, 2015
- Debris Flow Characteristics and Risk Degree Assessment in Changyuan Gully, Huairou District, BeijingProcedia Earth and Planetary Science, 2011
- Initiation conditions for debris flows generated by runoff at Chalk Cliffs, central ColoradoGeomorphology, 2008
- Characteristics of the Nujiang River runoff for a long term and its response to climate changeChinese Science Bulletin, 2007
- A mass‐conserving fast algorithm to parameterize gravitational transport and deposition using digital elevation modelsWater Resources Research, 2007
- Calibration of numerical models for small debris flows in Yosemite Valley, California, USANatural Hazards and Earth System Sciences, 2005
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Debris FlowAnnual Review of Fluid Mechanics, 1981
- Quantitative analysis of watershed geomorphologyEOS, Transactions American Geophysical Union, 1957