Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China

Reliable landslide susceptibility maps are essential for geohazard risk management. However, the selection of models and methods in the landslide susceptibility modeling (LSM) process is subjective and can lead to uncertainties in susceptibility outcomes. This paper introduces a framework for LSM an...

Full description

Saved in:
Bibliographic Details
Main Authors: Liang Liu, Jiqiu Deng
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Geomatics, Natural Hazards & Risk
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19475705.2024.2344804
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846126527609044992
author Liang Liu
Jiqiu Deng
author_facet Liang Liu
Jiqiu Deng
author_sort Liang Liu
collection DOAJ
description Reliable landslide susceptibility maps are essential for geohazard risk management. However, the selection of models and methods in the landslide susceptibility modeling (LSM) process is subjective and can lead to uncertainties in susceptibility outcomes. This paper introduces a framework for LSM and uncertainty analysis that leverages multiple models in key steps. The framework dynamically operates and combines models at each LSM step to generate susceptibility evaluation results from various method combinations. The uncertainty of different model combinations is then analyzed by comparing these results. The framework’s effectiveness is validated using Baoji City as a case study, examining the impact of different attribute interval numbers (AIN), non-landslide negative sample selection methods, and prediction models on susceptibility prediction outcomes. The results of each group show that the highest AUC value is 0.963 (AIN = 12, buffer-controlled sampling, Random forest) is about 0.26 higher than the lowest (no AIN, low-slope controlled sampling, Support vector machine). The findings suggest that the combinations involving larger AIN values, buffer-controlled sampling, XGBoost, or Random forest model yield relatively high AUC accuracy and relatively low uncertainty in the susceptibility index.
format Article
id doaj-art-c2beb0a83d8a49199e7a78248638de04
institution Kabale University
issn 1947-5705
1947-5713
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Geomatics, Natural Hazards & Risk
spelling doaj-art-c2beb0a83d8a49199e7a78248638de042024-12-12T18:11:16ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132024-12-0115110.1080/19475705.2024.2344804Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, ChinaLiang Liu0Jiqiu Deng1Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring (Central South University), Ministry of Education, Changsha, ChinaKey Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring (Central South University), Ministry of Education, Changsha, ChinaReliable landslide susceptibility maps are essential for geohazard risk management. However, the selection of models and methods in the landslide susceptibility modeling (LSM) process is subjective and can lead to uncertainties in susceptibility outcomes. This paper introduces a framework for LSM and uncertainty analysis that leverages multiple models in key steps. The framework dynamically operates and combines models at each LSM step to generate susceptibility evaluation results from various method combinations. The uncertainty of different model combinations is then analyzed by comparing these results. The framework’s effectiveness is validated using Baoji City as a case study, examining the impact of different attribute interval numbers (AIN), non-landslide negative sample selection methods, and prediction models on susceptibility prediction outcomes. The results of each group show that the highest AUC value is 0.963 (AIN = 12, buffer-controlled sampling, Random forest) is about 0.26 higher than the lowest (no AIN, low-slope controlled sampling, Support vector machine). The findings suggest that the combinations involving larger AIN values, buffer-controlled sampling, XGBoost, or Random forest model yield relatively high AUC accuracy and relatively low uncertainty in the susceptibility index.https://www.tandfonline.com/doi/10.1080/19475705.2024.2344804Landslide susceptibility mappinguncertainty analysismachine learningnon-landslide sampleattribute interval number
spellingShingle Liang Liu
Jiqiu Deng
Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China
Geomatics, Natural Hazards & Risk
Landslide susceptibility mapping
uncertainty analysis
machine learning
non-landslide sample
attribute interval number
title Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China
title_full Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China
title_fullStr Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China
title_full_unstemmed Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China
title_short Multi-model combination in key steps for landslide susceptibility modeling and uncertainty analysis: a case study in Baoji City, China
title_sort multi model combination in key steps for landslide susceptibility modeling and uncertainty analysis a case study in baoji city china
topic Landslide susceptibility mapping
uncertainty analysis
machine learning
non-landslide sample
attribute interval number
url https://www.tandfonline.com/doi/10.1080/19475705.2024.2344804
work_keys_str_mv AT liangliu multimodelcombinationinkeystepsforlandslidesusceptibilitymodelinganduncertaintyanalysisacasestudyinbaojicitychina
AT jiqiudeng multimodelcombinationinkeystepsforlandslidesusceptibilitymodelinganduncertaintyanalysisacasestudyinbaojicitychina