Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques

<p>Landslides threaten communities worldwide, resulting in financial, environmental, and human losses. Although some studies have employed machine learning (ML) algorithms and multi-criteria analysis (MCA) for landslide susceptibility mapping (LSM), comparative evaluations of these methods rem...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Zuleide Ferreira (20832508) (author)
مؤلفون آخرون: Bruna Almeida (12461880) (author), Ana Cristina Costa (3313470) (author), Manoel do Couto Fernandes (20832511) (author), Pedro Cabral (4253539) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852022298660306944
author Zuleide Ferreira (20832508)
author2 Bruna Almeida (12461880)
Ana Cristina Costa (3313470)
Manoel do Couto Fernandes (20832511)
Pedro Cabral (4253539)
author2_role author
author
author
author
author_facet Zuleide Ferreira (20832508)
Bruna Almeida (12461880)
Ana Cristina Costa (3313470)
Manoel do Couto Fernandes (20832511)
Pedro Cabral (4253539)
author_role author
dc.creator.none.fl_str_mv Zuleide Ferreira (20832508)
Bruna Almeida (12461880)
Ana Cristina Costa (3313470)
Manoel do Couto Fernandes (20832511)
Pedro Cabral (4253539)
dc.date.none.fl_str_mv 2025-03-05T16:00:08Z
dc.identifier.none.fl_str_mv 10.6084/m9.figshare.28541272.v1
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Insights_into_landslide_susceptibility_a_comparative_evaluation_of_multi-criteria_analysis_and_machine_learning_techniques/28541272
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Neuroscience
Biotechnology
Sociology
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Geospatial modelling
landslide-prone areas
hazard mapping
disaster risk reduction
climate change
dc.title.none.fl_str_mv Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <p>Landslides threaten communities worldwide, resulting in financial, environmental, and human losses. Although some studies have employed machine learning (ML) algorithms and multi-criteria analysis (MCA) for landslide susceptibility mapping (LSM), comparative evaluations of these methods remain scarce, particularly regarding predictor importance, performance metrics, and hyperparameter optimization. This research addresses these gaps by comparing logistic regression (LR), random forest (RF), support vector machines (SVM), and MCA, focusing on landslide susceptibility in Petrópolis, Brazil. The ML models used 29 influencing factors, encompassing geographic, geological, climatic, and anthropogenic variables, where feature importance analysis and hyperparameter tuning were applied to identify the most significant predictors. RF achieved the highest performance, with an accuracy of 0.94, ROC AUC of 0.98, and F1 score of 0.94. SVM and LR also performed well, with ROC AUCs of 0.96 and 0.95 and F1 scores of 0.92 and 0.89, respectively. Conversely, MCA showed lower results, with an accuracy of 0.41, ROC AUC of 0.41, and F1 score of 0.55. We attribute RF’s robustness to its adaptability to diverse variable types, reduced overfitting risk, and high predictive accuracy. These findings underscore RF’s strength in LSM and highlight ML’s potential to support urban planning and mitigate risks in landslide-prone areas.</p> <p></p><p>Effective landslide susceptibility analysis is essential for anticipating and mitigating risks.</p><p>MCA failed to identify non-landslide areas, highlighting its limitations.</p><p>ML overcomes traditional MCA in landslide susceptibility mapping.</p><p>RF achieved the highest prediction accuracy for landslide susceptibility, outperforming other methods.</p><p>ML-based landslide susceptibility mapping ranks susceptibility factors more effectively.</p><p></p> <p>Effective landslide susceptibility analysis is essential for anticipating and mitigating risks.</p> <p>MCA failed to identify non-landslide areas, highlighting its limitations.</p> <p>ML overcomes traditional MCA in landslide susceptibility mapping.</p> <p>RF achieved the highest prediction accuracy for landslide susceptibility, outperforming other methods.</p> <p>ML-based landslide susceptibility mapping ranks susceptibility factors more effectively.</p>
eu_rights_str_mv openAccess
id Manara_eec9cd12f8e9cc1cb5f770542fe8ce21
identifier_str_mv 10.6084/m9.figshare.28541272.v1
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28541272
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniquesZuleide Ferreira (20832508)Bruna Almeida (12461880)Ana Cristina Costa (3313470)Manoel do Couto Fernandes (20832511)Pedro Cabral (4253539)NeuroscienceBiotechnologySociologySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedGeospatial modellinglandslide-prone areashazard mappingdisaster risk reductionclimate change<p>Landslides threaten communities worldwide, resulting in financial, environmental, and human losses. Although some studies have employed machine learning (ML) algorithms and multi-criteria analysis (MCA) for landslide susceptibility mapping (LSM), comparative evaluations of these methods remain scarce, particularly regarding predictor importance, performance metrics, and hyperparameter optimization. This research addresses these gaps by comparing logistic regression (LR), random forest (RF), support vector machines (SVM), and MCA, focusing on landslide susceptibility in Petrópolis, Brazil. The ML models used 29 influencing factors, encompassing geographic, geological, climatic, and anthropogenic variables, where feature importance analysis and hyperparameter tuning were applied to identify the most significant predictors. RF achieved the highest performance, with an accuracy of 0.94, ROC AUC of 0.98, and F1 score of 0.94. SVM and LR also performed well, with ROC AUCs of 0.96 and 0.95 and F1 scores of 0.92 and 0.89, respectively. Conversely, MCA showed lower results, with an accuracy of 0.41, ROC AUC of 0.41, and F1 score of 0.55. We attribute RF’s robustness to its adaptability to diverse variable types, reduced overfitting risk, and high predictive accuracy. These findings underscore RF’s strength in LSM and highlight ML’s potential to support urban planning and mitigate risks in landslide-prone areas.</p> <p></p><p>Effective landslide susceptibility analysis is essential for anticipating and mitigating risks.</p><p>MCA failed to identify non-landslide areas, highlighting its limitations.</p><p>ML overcomes traditional MCA in landslide susceptibility mapping.</p><p>RF achieved the highest prediction accuracy for landslide susceptibility, outperforming other methods.</p><p>ML-based landslide susceptibility mapping ranks susceptibility factors more effectively.</p><p></p> <p>Effective landslide susceptibility analysis is essential for anticipating and mitigating risks.</p> <p>MCA failed to identify non-landslide areas, highlighting its limitations.</p> <p>ML overcomes traditional MCA in landslide susceptibility mapping.</p> <p>RF achieved the highest prediction accuracy for landslide susceptibility, outperforming other methods.</p> <p>ML-based landslide susceptibility mapping ranks susceptibility factors more effectively.</p>2025-03-05T16:00:08ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.6084/m9.figshare.28541272.v1https://figshare.com/articles/dataset/Insights_into_landslide_susceptibility_a_comparative_evaluation_of_multi-criteria_analysis_and_machine_learning_techniques/28541272CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/285412722025-03-05T16:00:08Z
spellingShingle Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
Zuleide Ferreira (20832508)
Neuroscience
Biotechnology
Sociology
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Geospatial modelling
landslide-prone areas
hazard mapping
disaster risk reduction
climate change
status_str publishedVersion
title Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
title_full Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
title_fullStr Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
title_full_unstemmed Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
title_short Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
title_sort Insights into landslide susceptibility: a comparative evaluation of multi-criteria analysis and machine learning techniques
topic Neuroscience
Biotechnology
Sociology
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Geospatial modelling
landslide-prone areas
hazard mapping
disaster risk reduction
climate change