Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang Prefecture

In large-scale debris flow susceptibility assessments, there is often excessive manual intervention, low efficiency, and inadequate model accuracy. To address these issues, this paper integrates multiple data sources and proposes a Multi-channel and Multi-scale Residual Network (MMRNet) for automati...

Full description

Saved in:
Bibliographic Details
Main Authors: Cunxi Liu, Baoyun Wang
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:All Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/27669645.2023.2292311
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846136226303705088
author Cunxi Liu
Baoyun Wang
author_facet Cunxi Liu
Baoyun Wang
author_sort Cunxi Liu
collection DOAJ
description In large-scale debris flow susceptibility assessments, there is often excessive manual intervention, low efficiency, and inadequate model accuracy. To address these issues, this paper integrates multiple data sources and proposes a Multi-channel and Multi-scale Residual Network (MMRNet) for automatic extraction of gully features. Firstly, MMRNet employs a multi-scale feature fusion module to capture both local and global features of gullies, enhancing the model’s feature representation capabilities. It then uses an improved residual structure to fuse shallow features, compress features, and improve assessment efficiency. Additionally, channel rearrangement techniques are used to enhance feature flow. Finally, susceptibility prediction is made based on the similarity between the gully under evaluation and gullies where debris flows have occurred. The natural breakpoint method is used to classify susceptibility results into five levels. Experimental results show that the very high susceptibility zones for debris flows are mainly concentrated in areas with abundant river systems along the Nujiang River, covering 61.68% of the entire study area, with a debris flow proportion of 98.78%. The MMRNet model achieves an accuracy (ACC) of 81.6% and an area under the curve (AUC) of 0.8320, indicating that this model is a high-performance method for debris flow susceptibility assessment.
format Article
id doaj-art-137c20c9f3854926b2ee7c3c792efe3c
institution Kabale University
issn 2766-9645
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series All Earth
spelling doaj-art-137c20c9f3854926b2ee7c3c792efe3c2024-12-09T07:46:39ZengTaylor & Francis GroupAll Earth2766-96452024-12-0136111810.1080/27669645.2023.2292311Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang PrefectureCunxi Liu0Baoyun Wang1School of Mathematics, Yunnan Normal University, Kunming, Yunnan, People’s Republic of ChinaSchool of Mathematics, Yunnan Normal University, Kunming, Yunnan, People’s Republic of ChinaIn large-scale debris flow susceptibility assessments, there is often excessive manual intervention, low efficiency, and inadequate model accuracy. To address these issues, this paper integrates multiple data sources and proposes a Multi-channel and Multi-scale Residual Network (MMRNet) for automatic extraction of gully features. Firstly, MMRNet employs a multi-scale feature fusion module to capture both local and global features of gullies, enhancing the model’s feature representation capabilities. It then uses an improved residual structure to fuse shallow features, compress features, and improve assessment efficiency. Additionally, channel rearrangement techniques are used to enhance feature flow. Finally, susceptibility prediction is made based on the similarity between the gully under evaluation and gullies where debris flows have occurred. The natural breakpoint method is used to classify susceptibility results into five levels. Experimental results show that the very high susceptibility zones for debris flows are mainly concentrated in areas with abundant river systems along the Nujiang River, covering 61.68% of the entire study area, with a debris flow proportion of 98.78%. The MMRNet model achieves an accuracy (ACC) of 81.6% and an area under the curve (AUC) of 0.8320, indicating that this model is a high-performance method for debris flow susceptibility assessment.https://www.tandfonline.com/doi/10.1080/27669645.2023.2292311Debris flowconvolutional neural networkmulti-scale featuresdeep learningmachine learning
spellingShingle Cunxi Liu
Baoyun Wang
Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang Prefecture
All Earth
Debris flow
convolutional neural network
multi-scale features
deep learning
machine learning
title Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang Prefecture
title_full Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang Prefecture
title_fullStr Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang Prefecture
title_full_unstemmed Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang Prefecture
title_short Gully-type debris flow susceptibility assessment based on a multi-channel multi-scale residual network fusing multi-source data: a case study of Nujiang Prefecture
title_sort gully type debris flow susceptibility assessment based on a multi channel multi scale residual network fusing multi source data a case study of nujiang prefecture
topic Debris flow
convolutional neural network
multi-scale features
deep learning
machine learning
url https://www.tandfonline.com/doi/10.1080/27669645.2023.2292311
work_keys_str_mv AT cunxiliu gullytypedebrisflowsusceptibilityassessmentbasedonamultichannelmultiscaleresidualnetworkfusingmultisourcedataacasestudyofnujiangprefecture
AT baoyunwang gullytypedebrisflowsusceptibilityassessmentbasedonamultichannelmultiscaleresidualnetworkfusingmultisourcedataacasestudyofnujiangprefecture