Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods

Landslide susceptibility assessment (LSA) aims to determine the spatial probability of landslides, reducing the loss caused by future landslides. In order to assess the impact of various negative sample collection strategies on the prediction accuracy of the landslide susceptibility assessment (LSA)...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiani Wang, Yunqi Wang, Manyi Li, Zihan Qi, Cheng Li, Haimei Qi, Xiaoming Zhang
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Ecological Indicators
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1470160X24014055
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850118408925872128
author Jiani Wang
Yunqi Wang
Manyi Li
Zihan Qi
Cheng Li
Haimei Qi
Xiaoming Zhang
author_facet Jiani Wang
Yunqi Wang
Manyi Li
Zihan Qi
Cheng Li
Haimei Qi
Xiaoming Zhang
author_sort Jiani Wang
collection DOAJ
description Landslide susceptibility assessment (LSA) aims to determine the spatial probability of landslides, reducing the loss caused by future landslides. In order to assess the impact of various negative sample collection strategies on the prediction accuracy of the landslide susceptibility assessment (LSA) model, and to investigate the effectiveness of landslide susceptibility zoning methods. Taking Fengjie County, Chongqing City, China as the study area, this study proposes three negative sample collection strategies based on slope unit, buffer zone, and information value, and combines them with C5.0 decision tree (DT) model respectively to construct an LSA model. Concurrently, the landslide susceptibility indexes (LSIs) were divided using the K-means clustering algorithm and contrasted with the natural breakpoint classification (NBC), quantile classification (QC), equal interval classification (EIC), and geometric interval classification (GIC) methods. The results show that: (1) Rainfall, elevation, and water system are the primary conditioning factors of landslide development in the study area. (2) The accuracy of the negative sample collection strategy based on the slope units on the model training subset and the test subset reached 97.78 % and 92.99 %, respectively, and the AUC values were 0.978 and 0.930, indicating high model accuracy. (3) The zoning effect based on the K-means clustering algorithm was the best, and the predicted very-high and high susceptibility areas were 805.73 km2 and 567.66 km2, respectively, accounting for 19.59 % and 13.80 % of Fengjie County. The very-high and high susceptibility areas had maximum FR values of 3.963 and 1.432, respectively, when compared to other zoning methods. This study can provide a more objective and scientific method for LSA, and the findings can offer more precise decision assistance for risk management and geological disaster prevention.
format Article
id doaj-art-503ff4794cad43bbb8404f5fdb572e75
institution OA Journals
issn 1470-160X
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Ecological Indicators
spelling doaj-art-503ff4794cad43bbb8404f5fdb572e752025-08-20T02:35:53ZengElsevierEcological Indicators1470-160X2024-12-0116911294810.1016/j.ecolind.2024.112948Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methodsJiani Wang0Yunqi Wang1Manyi Li2Zihan Qi3Cheng Li4Haimei Qi5Xiaoming Zhang6School of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China; Three-gorges Reservoir Area (Chongqing) Forest Ecosystem Research Station, Chongqing 400700, ChinaSchool of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China; Three-gorges Reservoir Area (Chongqing) Forest Ecosystem Research Station, Chongqing 400700, China; Corresponding author at: School of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China.Observation and Research Station of Ecological Restoration for Chongqing Typical Mining Areas, Ministry of Natural Resources, Chongqing Institute of Geology and Mineral Resources, Chongqing 401120, ChinaSchool of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China; Three-gorges Reservoir Area (Chongqing) Forest Ecosystem Research Station, Chongqing 400700, ChinaObservation and Research Station of Ecological Restoration for Chongqing Typical Mining Areas, Ministry of Natural Resources, Chongqing Institute of Geology and Mineral Resources, Chongqing 401120, ChinaSchool of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China; Three-gorges Reservoir Area (Chongqing) Forest Ecosystem Research Station, Chongqing 400700, ChinaChina Institute of Water Resources and Hydropower Research, Beijing 100048, ChinaLandslide susceptibility assessment (LSA) aims to determine the spatial probability of landslides, reducing the loss caused by future landslides. In order to assess the impact of various negative sample collection strategies on the prediction accuracy of the landslide susceptibility assessment (LSA) model, and to investigate the effectiveness of landslide susceptibility zoning methods. Taking Fengjie County, Chongqing City, China as the study area, this study proposes three negative sample collection strategies based on slope unit, buffer zone, and information value, and combines them with C5.0 decision tree (DT) model respectively to construct an LSA model. Concurrently, the landslide susceptibility indexes (LSIs) were divided using the K-means clustering algorithm and contrasted with the natural breakpoint classification (NBC), quantile classification (QC), equal interval classification (EIC), and geometric interval classification (GIC) methods. The results show that: (1) Rainfall, elevation, and water system are the primary conditioning factors of landslide development in the study area. (2) The accuracy of the negative sample collection strategy based on the slope units on the model training subset and the test subset reached 97.78 % and 92.99 %, respectively, and the AUC values were 0.978 and 0.930, indicating high model accuracy. (3) The zoning effect based on the K-means clustering algorithm was the best, and the predicted very-high and high susceptibility areas were 805.73 km2 and 567.66 km2, respectively, accounting for 19.59 % and 13.80 % of Fengjie County. The very-high and high susceptibility areas had maximum FR values of 3.963 and 1.432, respectively, when compared to other zoning methods. This study can provide a more objective and scientific method for LSA, and the findings can offer more precise decision assistance for risk management and geological disaster prevention.http://www.sciencedirect.com/science/article/pii/S1470160X24014055Landslide susceptibility assessmentNegative sample collection strategyC5.0 decision treeK-means clustering algorithmLandslide susceptibility zoning
spellingShingle Jiani Wang
Yunqi Wang
Manyi Li
Zihan Qi
Cheng Li
Haimei Qi
Xiaoming Zhang
Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods
Ecological Indicators
Landslide susceptibility assessment
Negative sample collection strategy
C5.0 decision tree
K-means clustering algorithm
Landslide susceptibility zoning
title Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods
title_full Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods
title_fullStr Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods
title_full_unstemmed Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods
title_short Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods
title_sort improved landslide susceptibility assessment a new negative sample collection strategy and a comparative analysis of zoning methods
topic Landslide susceptibility assessment
Negative sample collection strategy
C5.0 decision tree
K-means clustering algorithm
Landslide susceptibility zoning
url http://www.sciencedirect.com/science/article/pii/S1470160X24014055
work_keys_str_mv AT jianiwang improvedlandslidesusceptibilityassessmentanewnegativesamplecollectionstrategyandacomparativeanalysisofzoningmethods
AT yunqiwang improvedlandslidesusceptibilityassessmentanewnegativesamplecollectionstrategyandacomparativeanalysisofzoningmethods
AT manyili improvedlandslidesusceptibilityassessmentanewnegativesamplecollectionstrategyandacomparativeanalysisofzoningmethods
AT zihanqi improvedlandslidesusceptibilityassessmentanewnegativesamplecollectionstrategyandacomparativeanalysisofzoningmethods
AT chengli improvedlandslidesusceptibilityassessmentanewnegativesamplecollectionstrategyandacomparativeanalysisofzoningmethods
AT haimeiqi improvedlandslidesusceptibilityassessmentanewnegativesamplecollectionstrategyandacomparativeanalysisofzoningmethods
AT xiaomingzhang improvedlandslidesusceptibilityassessmentanewnegativesamplecollectionstrategyandacomparativeanalysisofzoningmethods