Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning Optimization

The present study examines the application of four machine learning models—Multi-Layer Perceptron, Naive Bayes, Credal Decision Trees, and Random Forests—to assess landslide susceptibility using Mei County, China, as a case study. Aerial photographs and field survey data were integrated into a GIS s...

Full description

Saved in:
Bibliographic Details
Main Authors: Chuanwei Zhang, Dingshuai Liu, Paraskevas Tsangaratos, Ioanna Ilia, Sijin Ma, Wei Chen
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/6325
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160991741935616
author Chuanwei Zhang
Dingshuai Liu
Paraskevas Tsangaratos
Ioanna Ilia
Sijin Ma
Wei Chen
author_facet Chuanwei Zhang
Dingshuai Liu
Paraskevas Tsangaratos
Ioanna Ilia
Sijin Ma
Wei Chen
author_sort Chuanwei Zhang
collection DOAJ
description The present study examines the application of four machine learning models—Multi-Layer Perceptron, Naive Bayes, Credal Decision Trees, and Random Forests—to assess landslide susceptibility using Mei County, China, as a case study. Aerial photographs and field survey data were integrated into a GIS system to develop a landslide inventory map. Additionally, 16 landslide conditioning factors were collected and processed, including elevation, Normalized Difference Vegetation Index, precipitation, terrain, land use, lithology, slope, aspect, stream power index, topographic wetness index, sediment transport index, plan curvature, profile curvature, and distance to roads. From the landslide inventory, 87 landslides were identified, along with an equal number of randomly selected non-landslide locations. These data points, combined with the conditioning factors, formed a spatial dataset for our landslide analysis. To implement the proposed methodological approach, the dataset was divided into two subsets: 70% formed the training subset and 30% formed the testing subset. A correlation analysis was conducted to examine the relationship between the conditioning factors and landslide occurrence, and the certainty factor method was applied to assess their influence. Beyond model comparison, the central focus of this research is the optimization of machine learning parameters to enhance prediction reliability and spatial accuracy. The results show that the Random Forests and Multi-Layer Perceptron models provided superior predictive capability, offering detailed and actionable landslide susceptibility maps. Specifically, the area under the receiver operating characteristic curve and other statistical indicators were calculated to assess the models’ predictive accuracy. By producing high-resolution susceptibility maps tailored to local geomorphological conditions, this work supports more informed land-use planning, infrastructure development, and early warning systems in landslide-prone areas. The findings also contribute to the growing body of research on artificial intelligence-driven natural hazard assessment, offering a replicable framework for integrating machine learning in geospatial risk analysis and environmental decision-making.
format Article
id doaj-art-e46b500b7b614f8b8b5ae1c2f042086b
institution OA Journals
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e46b500b7b614f8b8b5ae1c2f042086b2025-08-20T02:23:00ZengMDPI AGApplied Sciences2076-34172025-06-011511632510.3390/app15116325Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning OptimizationChuanwei Zhang0Dingshuai Liu1Paraskevas Tsangaratos2Ioanna Ilia3Sijin Ma4Wei Chen5Kunming Coal Design and Research Institute Co., Ltd., Kunming 650000, ChinaYunnan Xiaolongtan Mining Bureau Co., Ltd., Kaiyuan 661600, ChinaLaboratory of Engineering Geology and Hydrogeology, Department of Geological Sciences, School of Mining and Metallurgical Engineering, National Technical University of Athens, 15780 Zografou, GreeceLaboratory of Engineering Geology and Hydrogeology, Department of Geological Sciences, School of Mining and Metallurgical Engineering, National Technical University of Athens, 15780 Zografou, GreeceCollege of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaCollege of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, ChinaThe present study examines the application of four machine learning models—Multi-Layer Perceptron, Naive Bayes, Credal Decision Trees, and Random Forests—to assess landslide susceptibility using Mei County, China, as a case study. Aerial photographs and field survey data were integrated into a GIS system to develop a landslide inventory map. Additionally, 16 landslide conditioning factors were collected and processed, including elevation, Normalized Difference Vegetation Index, precipitation, terrain, land use, lithology, slope, aspect, stream power index, topographic wetness index, sediment transport index, plan curvature, profile curvature, and distance to roads. From the landslide inventory, 87 landslides were identified, along with an equal number of randomly selected non-landslide locations. These data points, combined with the conditioning factors, formed a spatial dataset for our landslide analysis. To implement the proposed methodological approach, the dataset was divided into two subsets: 70% formed the training subset and 30% formed the testing subset. A correlation analysis was conducted to examine the relationship between the conditioning factors and landslide occurrence, and the certainty factor method was applied to assess their influence. Beyond model comparison, the central focus of this research is the optimization of machine learning parameters to enhance prediction reliability and spatial accuracy. The results show that the Random Forests and Multi-Layer Perceptron models provided superior predictive capability, offering detailed and actionable landslide susceptibility maps. Specifically, the area under the receiver operating characteristic curve and other statistical indicators were calculated to assess the models’ predictive accuracy. By producing high-resolution susceptibility maps tailored to local geomorphological conditions, this work supports more informed land-use planning, infrastructure development, and early warning systems in landslide-prone areas. The findings also contribute to the growing body of research on artificial intelligence-driven natural hazard assessment, offering a replicable framework for integrating machine learning in geospatial risk analysis and environmental decision-making.https://www.mdpi.com/2076-3417/15/11/6325landslide susceptibility mappingmachine learning optimizationGIS-based analysisRandom ForestsMei CountyChina
spellingShingle Chuanwei Zhang
Dingshuai Liu
Paraskevas Tsangaratos
Ioanna Ilia
Sijin Ma
Wei Chen
Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning Optimization
Applied Sciences
landslide susceptibility mapping
machine learning optimization
GIS-based analysis
Random Forests
Mei County
China
title Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning Optimization
title_full Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning Optimization
title_fullStr Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning Optimization
title_full_unstemmed Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning Optimization
title_short Enhancing Predictive Accuracy of Landslide Susceptibility via Machine Learning Optimization
title_sort enhancing predictive accuracy of landslide susceptibility via machine learning optimization
topic landslide susceptibility mapping
machine learning optimization
GIS-based analysis
Random Forests
Mei County
China
url https://www.mdpi.com/2076-3417/15/11/6325
work_keys_str_mv AT chuanweizhang enhancingpredictiveaccuracyoflandslidesusceptibilityviamachinelearningoptimization
AT dingshuailiu enhancingpredictiveaccuracyoflandslidesusceptibilityviamachinelearningoptimization
AT paraskevastsangaratos enhancingpredictiveaccuracyoflandslidesusceptibilityviamachinelearningoptimization
AT ioannailia enhancingpredictiveaccuracyoflandslidesusceptibilityviamachinelearningoptimization
AT sijinma enhancingpredictiveaccuracyoflandslidesusceptibilityviamachinelearningoptimization
AT weichen enhancingpredictiveaccuracyoflandslidesusceptibilityviamachinelearningoptimization