Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China

This study aims to evaluate the effectiveness of various individual machine learning and their ensemble techniques such as Stacking, Voting and Meta-learning in landslide susceptibility assessment taking Poyang, Jiangxi, China as an example. Multi-source geo-environmental data including field survey...

Full description

Saved in:
Bibliographic Details
Main Authors: Yong Song, Yingxu Song, Chengnan Wang, Linwei Wu, Weicheng Wu, Yuan Li, Sicheng Li, Aiqing Chen
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Geomatics, Natural Hazards & Risk
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19475705.2024.2354499
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846126479594749952
author Yong Song
Yingxu Song
Chengnan Wang
Linwei Wu
Weicheng Wu
Yuan Li
Sicheng Li
Aiqing Chen
author_facet Yong Song
Yingxu Song
Chengnan Wang
Linwei Wu
Weicheng Wu
Yuan Li
Sicheng Li
Aiqing Chen
author_sort Yong Song
collection DOAJ
description This study aims to evaluate the effectiveness of various individual machine learning and their ensemble techniques such as Stacking, Voting and Meta-learning in landslide susceptibility assessment taking Poyang, Jiangxi, China as an example. Multi-source geo-environmental data including field surveys, Sentinel-2A/B satellite images, Digital Elevation Models (DEM), and geological and hydrological data were utilized to construct and validate landslide susceptibility models. Results show that the Stacking Classifier outperformed other models, achieving the highest F1 Score of 0.846 and AUC (Area Under ROC Curve) of 0.923, demonstrating its strong predictivity, followed by the Voting Classifier with the F1 Score of 0.829 and AUC of 0.922. Among the individual models, the Multi-Layer Perceptron (MLP) performed best with the F1 Score of 0.828 and AUC of 0.904. Furthermore, the explainable Artificial Intelligence (XAI) technique was applied to better understand the mechanism of classifiers in predicting landslide susceptibility and it suggests a significant correlation between land use, distance to fault, and landslide occurrences. In conclusion, Stacking and Voting hybrid learning models show clear advantages over the individual ones for landslide risk zoning. The results of study may provide technical support for disaster mitigation efforts and future urban planning in areas prone to landslides in Poyang.
format Article
id doaj-art-1a3c2194745d44c89e4ee05321f62eaa
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-1a3c2194745d44c89e4ee05321f62eaa2024-12-12T18:11:17ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132024-12-0115110.1080/19475705.2024.2354499Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, ChinaYong Song0Yingxu Song1Chengnan Wang2Linwei Wu3Weicheng Wu4Yuan Li5Sicheng Li6Aiqing Chen7Geological and Environmental Research Institute of Jiangxi Province, Nanchang, Jiangxi, ChinaKey Laboratory of Digital Land and Resources and Faculty of Earth Sciences, East China University of Technology, Nanchang, Jiangxi, ChinaGeological and Environmental Research Institute of Jiangxi Province, Nanchang, Jiangxi, ChinaGeological and Environmental Research Institute of Jiangxi Province, Nanchang, Jiangxi, ChinaKey Laboratory of Digital Land and Resources and Faculty of Earth Sciences, East China University of Technology, Nanchang, Jiangxi, ChinaKey Laboratory of Digital Land and Resources and Faculty of Earth Sciences, East China University of Technology, Nanchang, Jiangxi, ChinaKey Laboratory of Digital Land and Resources and Faculty of Earth Sciences, East China University of Technology, Nanchang, Jiangxi, ChinaKey Laboratory of Digital Land and Resources and Faculty of Earth Sciences, East China University of Technology, Nanchang, Jiangxi, ChinaThis study aims to evaluate the effectiveness of various individual machine learning and their ensemble techniques such as Stacking, Voting and Meta-learning in landslide susceptibility assessment taking Poyang, Jiangxi, China as an example. Multi-source geo-environmental data including field surveys, Sentinel-2A/B satellite images, Digital Elevation Models (DEM), and geological and hydrological data were utilized to construct and validate landslide susceptibility models. Results show that the Stacking Classifier outperformed other models, achieving the highest F1 Score of 0.846 and AUC (Area Under ROC Curve) of 0.923, demonstrating its strong predictivity, followed by the Voting Classifier with the F1 Score of 0.829 and AUC of 0.922. Among the individual models, the Multi-Layer Perceptron (MLP) performed best with the F1 Score of 0.828 and AUC of 0.904. Furthermore, the explainable Artificial Intelligence (XAI) technique was applied to better understand the mechanism of classifiers in predicting landslide susceptibility and it suggests a significant correlation between land use, distance to fault, and landslide occurrences. In conclusion, Stacking and Voting hybrid learning models show clear advantages over the individual ones for landslide risk zoning. The results of study may provide technical support for disaster mitigation efforts and future urban planning in areas prone to landslides in Poyang.https://www.tandfonline.com/doi/10.1080/19475705.2024.2354499Landslide susceptibilitymodel stacking and votingmeta learningmachine learningexplainable artificial intelligence (XAI)
spellingShingle Yong Song
Yingxu Song
Chengnan Wang
Linwei Wu
Weicheng Wu
Yuan Li
Sicheng Li
Aiqing Chen
Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China
Geomatics, Natural Hazards & Risk
Landslide susceptibility
model stacking and voting
meta learning
machine learning
explainable artificial intelligence (XAI)
title Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China
title_full Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China
title_fullStr Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China
title_full_unstemmed Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China
title_short Landslide susceptibility assessment through multi-model stacking and meta-learning in Poyang County, China
title_sort landslide susceptibility assessment through multi model stacking and meta learning in poyang county china
topic Landslide susceptibility
model stacking and voting
meta learning
machine learning
explainable artificial intelligence (XAI)
url https://www.tandfonline.com/doi/10.1080/19475705.2024.2354499
work_keys_str_mv AT yongsong landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina
AT yingxusong landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina
AT chengnanwang landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina
AT linweiwu landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina
AT weichengwu landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina
AT yuanli landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina
AT sichengli landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina
AT aiqingchen landslidesusceptibilityassessmentthroughmultimodelstackingandmetalearninginpoyangcountychina