Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor Engineering

Current research lacks an in-depth exploration of ensemble learning and factor engineering applications in regard to landslide susceptibility modeling. In the Three Gorges Reservoir area of China, a region prone to frequent landslides that endanger lives and infrastructure, this study advances lands...

Full description

Saved in:
Bibliographic Details
Main Authors: Lizhou Zhang, Siqiao Ye, Deping He, Linfeng Wang, Weiping Li, Bijing Jin, Taorui Zeng
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/6192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129658401521664
author Lizhou Zhang
Siqiao Ye
Deping He
Linfeng Wang
Weiping Li
Bijing Jin
Taorui Zeng
author_facet Lizhou Zhang
Siqiao Ye
Deping He
Linfeng Wang
Weiping Li
Bijing Jin
Taorui Zeng
author_sort Lizhou Zhang
collection DOAJ
description Current research lacks an in-depth exploration of ensemble learning and factor engineering applications in regard to landslide susceptibility modeling. In the Three Gorges Reservoir area of China, a region prone to frequent landslides that endanger lives and infrastructure, this study advances landslide susceptibility prediction by integrating ensemble learning with systematic factor engineering. Four homogeneous ensemble models (random forest, XGBoost, LightGBM, and CatBoost) and two heterogeneous ensembles (bagging and stacking) were implemented to evaluate 14 influencing factors. The key results demonstrate the Digital Elevation Model (DEM) as the dominant factor, while the stacking ensemble achieved superior performance (AUC = 0.876), outperforming single models by 4.4%. Iterative factor elimination and hyperparameter tuning increased the high-susceptibility zones in the stacking predictions to 42.54% and enhanced XGBoost’s low-susceptibility classification accuracy from 12.96% to 13.57%. The optimized models were used to generate a high-resolution landslide susceptibility map, identifying 23.8% of the northern and central regions as high-susceptibility areas, compared to only 9.3% as eastern and southern low-susceptibility zones. This methodology improved the prediction accuracy by 12–18% in comparison to a single model, providing actionable insights for landslide risk mitigation.
format Article
id doaj-art-cdd92bf34323465a9edbff02522ee2c4
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-cdd92bf34323465a9edbff02522ee2c42025-08-20T02:32:54ZengMDPI AGApplied Sciences2076-34172025-05-011511619210.3390/app15116192Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor EngineeringLizhou Zhang0Siqiao Ye1Deping He2Linfeng Wang3Weiping Li4Bijing Jin5Taorui Zeng6College of River and Ocean Engineering, Chongqing Jiaotong University, Chongqing 400047, ChinaCollege of River and Ocean Engineering, Chongqing Jiaotong University, Chongqing 400047, ChinaChongqing Institute of Surveying and Mapping Science and Technology, Chongqing 401121, ChinaCollege of River and Ocean Engineering, Chongqing Jiaotong University, Chongqing 400047, ChinaChongqing Institute of Surveying and Mapping Science and Technology, Chongqing 401121, ChinaFaculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaInstitute of Future Civil Engineering Science and Technology, Chongqing Jiaotong University, Chongqing 400047, ChinaCurrent research lacks an in-depth exploration of ensemble learning and factor engineering applications in regard to landslide susceptibility modeling. In the Three Gorges Reservoir area of China, a region prone to frequent landslides that endanger lives and infrastructure, this study advances landslide susceptibility prediction by integrating ensemble learning with systematic factor engineering. Four homogeneous ensemble models (random forest, XGBoost, LightGBM, and CatBoost) and two heterogeneous ensembles (bagging and stacking) were implemented to evaluate 14 influencing factors. The key results demonstrate the Digital Elevation Model (DEM) as the dominant factor, while the stacking ensemble achieved superior performance (AUC = 0.876), outperforming single models by 4.4%. Iterative factor elimination and hyperparameter tuning increased the high-susceptibility zones in the stacking predictions to 42.54% and enhanced XGBoost’s low-susceptibility classification accuracy from 12.96% to 13.57%. The optimized models were used to generate a high-resolution landslide susceptibility map, identifying 23.8% of the northern and central regions as high-susceptibility areas, compared to only 9.3% as eastern and southern low-susceptibility zones. This methodology improved the prediction accuracy by 12–18% in comparison to a single model, providing actionable insights for landslide risk mitigation.https://www.mdpi.com/2076-3417/15/11/6192landslide susceptibilityensemble learningfactor engineeringrandom forestXGBoostLightGBM
spellingShingle Lizhou Zhang
Siqiao Ye
Deping He
Linfeng Wang
Weiping Li
Bijing Jin
Taorui Zeng
Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor Engineering
Applied Sciences
landslide susceptibility
ensemble learning
factor engineering
random forest
XGBoost
LightGBM
title Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor Engineering
title_full Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor Engineering
title_fullStr Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor Engineering
title_full_unstemmed Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor Engineering
title_short Examination of Landslide Susceptibility Modeling Using Ensemble Learning and Factor Engineering
title_sort examination of landslide susceptibility modeling using ensemble learning and factor engineering
topic landslide susceptibility
ensemble learning
factor engineering
random forest
XGBoost
LightGBM
url https://www.mdpi.com/2076-3417/15/11/6192
work_keys_str_mv AT lizhouzhang examinationoflandslidesusceptibilitymodelingusingensemblelearningandfactorengineering
AT siqiaoye examinationoflandslidesusceptibilitymodelingusingensemblelearningandfactorengineering
AT depinghe examinationoflandslidesusceptibilitymodelingusingensemblelearningandfactorengineering
AT linfengwang examinationoflandslidesusceptibilitymodelingusingensemblelearningandfactorengineering
AT weipingli examinationoflandslidesusceptibilitymodelingusingensemblelearningandfactorengineering
AT bijingjin examinationoflandslidesusceptibilitymodelingusingensemblelearningandfactorengineering
AT taoruizeng examinationoflandslidesusceptibilitymodelingusingensemblelearningandfactorengineering