Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches

Shallow landslides are one of the most common natural hazards in Brazil and worldwide. Susceptibility maps are powerful tools to analyze the spatial probability of shallow landslide occurrences. The outputs of susceptibility maps strongly depend on the type of landslide inventory used. The aim of th...

Full description

Saved in:
Bibliographic Details
Main Authors: Helen Cristina Dias, Daniel Hölbling, Carlos Henrique Grohmann
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Geosciences
Subjects:
Online Access:https://www.mdpi.com/2076-3263/15/3/77
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849341613195657216
author Helen Cristina Dias
Daniel Hölbling
Carlos Henrique Grohmann
author_facet Helen Cristina Dias
Daniel Hölbling
Carlos Henrique Grohmann
author_sort Helen Cristina Dias
collection DOAJ
description Shallow landslides are one of the most common natural hazards in Brazil and worldwide. Susceptibility maps are powerful tools to analyze the spatial probability of shallow landslide occurrences. The outputs of susceptibility maps strongly depend on the type of landslide inventory used. The aim of this study is to examine the influence of different inventories on shallow landslide susceptibility modeling using the different methods LR, SVM, and XGBoost. Three different shallow landslide inventories were compiled following a single extreme rainfall event in the Ribeira Valley, São Paulo, Brazil. The results indicate that inventories generated through different landslide detection methods and imagery produce diverse susceptibility maps, as evidenced by the calculated Cohen’s Kappa coefficient values (0.33–0.79). The agreement among the models varied depending on the specific model: LR exhibited the highest agreement (0.79), whereas SVM (0.36) and XGBoost (0.33) showed lower numbers. Conversely, the accuracy numbers suggest that XGBoost achieved the highest success rate in terms of AUC (85–78%), followed by SVM (82–76%), and LR (80–71%). Inventories obtained through different detection methods, using distinct datasets, can directly influence the susceptibility assessment, leading to varying classifications of the same area. These findings demonstrate the importance of well-established landslide mapping criteria.
format Article
id doaj-art-68b551a79d1248e9ab9e60e6102e66e6
institution Kabale University
issn 2076-3263
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Geosciences
spelling doaj-art-68b551a79d1248e9ab9e60e6102e66e62025-08-20T03:43:36ZengMDPI AGGeosciences2076-32632025-02-011537710.3390/geosciences15030077Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical ApproachesHelen Cristina Dias0Daniel Hölbling1Carlos Henrique Grohmann2Institute of Energy and Environment, Universidade de São Paulo (IEE-USP), Av. Prof. Luciano Gualberto 1289, Cidade Universitária, São Paulo 05508-900, BrazilDepartment of Geoinformatics, Z_GIS, University of Salzburg, Schillerstraße 30, 5020 Salzburg, AustriaInstitute of Energy and Environment, Universidade de São Paulo (IEE-USP), Av. Prof. Luciano Gualberto 1289, Cidade Universitária, São Paulo 05508-900, BrazilShallow landslides are one of the most common natural hazards in Brazil and worldwide. Susceptibility maps are powerful tools to analyze the spatial probability of shallow landslide occurrences. The outputs of susceptibility maps strongly depend on the type of landslide inventory used. The aim of this study is to examine the influence of different inventories on shallow landslide susceptibility modeling using the different methods LR, SVM, and XGBoost. Three different shallow landslide inventories were compiled following a single extreme rainfall event in the Ribeira Valley, São Paulo, Brazil. The results indicate that inventories generated through different landslide detection methods and imagery produce diverse susceptibility maps, as evidenced by the calculated Cohen’s Kappa coefficient values (0.33–0.79). The agreement among the models varied depending on the specific model: LR exhibited the highest agreement (0.79), whereas SVM (0.36) and XGBoost (0.33) showed lower numbers. Conversely, the accuracy numbers suggest that XGBoost achieved the highest success rate in terms of AUC (85–78%), followed by SVM (82–76%), and LR (80–71%). Inventories obtained through different detection methods, using distinct datasets, can directly influence the susceptibility assessment, leading to varying classifications of the same area. These findings demonstrate the importance of well-established landslide mapping criteria.https://www.mdpi.com/2076-3263/15/3/77morphologyspatial agreementOBIAsatellite imagerymass movementBrazil
spellingShingle Helen Cristina Dias
Daniel Hölbling
Carlos Henrique Grohmann
Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches
Geosciences
morphology
spatial agreement
OBIA
satellite imagery
mass movement
Brazil
title Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches
title_full Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches
title_fullStr Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches
title_full_unstemmed Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches
title_short Examining the Influence of Different Inventories on Shallow Landslide Susceptibility Modeling: An Assessment Using Machine Learning and Statistical Approaches
title_sort examining the influence of different inventories on shallow landslide susceptibility modeling an assessment using machine learning and statistical approaches
topic morphology
spatial agreement
OBIA
satellite imagery
mass movement
Brazil
url https://www.mdpi.com/2076-3263/15/3/77
work_keys_str_mv AT helencristinadias examiningtheinfluenceofdifferentinventoriesonshallowlandslidesusceptibilitymodelinganassessmentusingmachinelearningandstatisticalapproaches
AT danielholbling examiningtheinfluenceofdifferentinventoriesonshallowlandslidesusceptibilitymodelinganassessmentusingmachinelearningandstatisticalapproaches
AT carloshenriquegrohmann examiningtheinfluenceofdifferentinventoriesonshallowlandslidesusceptibilitymodelinganassessmentusingmachinelearningandstatisticalapproaches