Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western Greece

Landslides are one of the most severe geohazards globally, causing extreme financial and social losses. While InSAR time-series analyses provide valuable insights into landslide detection, mapping, and monitoring, AI is also implemented in a variety of geohazards, including landslides. In the presen...

Full description

Saved in:
Bibliographic Details
Main Authors: Stavroula Alatza, Alexis Apostolakis, Constantinos Loupasakis, Charalampos Kontoes, Martha Kokkalidou, Nikolaos S. Bartsotas, Georgios Christopoulos
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/7/1161
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212420845305856
author Stavroula Alatza
Alexis Apostolakis
Constantinos Loupasakis
Charalampos Kontoes
Martha Kokkalidou
Nikolaos S. Bartsotas
Georgios Christopoulos
author_facet Stavroula Alatza
Alexis Apostolakis
Constantinos Loupasakis
Charalampos Kontoes
Martha Kokkalidou
Nikolaos S. Bartsotas
Georgios Christopoulos
author_sort Stavroula Alatza
collection DOAJ
description Landslides are one of the most severe geohazards globally, causing extreme financial and social losses. While InSAR time-series analyses provide valuable insights into landslide detection, mapping, and monitoring, AI is also implemented in a variety of geohazards, including landslides. In the present study, a machine learning (ML) landslide susceptibility map is proposed that integrates the geotectonic units of Greece and incorporates various sources of landslide data. Satellite data from Persistent Scatterer Interferometry analysis, validated by geotechnical experts, resulted in an extremely large dataset of more than 3000 landslides in an area of interest, including the most landslide-prone area in Greece. The gradient-boosted decision tree was employed in the landslide susceptibility mapping. The model was trained on three geotectonic units and five prefectures of Western Greece and performed well in predicting landslide events. Finally, a SHAP (SHapley Additive exPlanations) analysis verified that precipitation and geology, which are the main landslide-triggering and preparatory factors, respectively, in Greece, positively affected landslide characterization. The innovation of the proposed research lies in the uniqueness of this newly created dataset, comprising a remarkably large number of landslide and non-landslide locations in Western Greece. By adopting a strict machine learning methodology, the spatial autocorrelation effect, which is overlooked in similar studies, was reduced. Also, leveraging the unique features of the geological formations, the model was trained to incorporate differences in the landslide susceptibility of formations located in different geotectonic units with variant geotechnical characteristics. The proposed approach facilitates the generalization of the model and sets a strong base for the creation of a national-scale landslide susceptibility mapping and forecasting system.
format Article
id doaj-art-d1a7c631c8084fc88124bf0ce8e41129
institution OA Journals
issn 2072-4292
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d1a7c631c8084fc88124bf0ce8e411292025-08-20T02:09:21ZengMDPI AGRemote Sensing2072-42922025-03-01177116110.3390/rs17071161Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western GreeceStavroula Alatza0Alexis Apostolakis1Constantinos Loupasakis2Charalampos Kontoes3Martha Kokkalidou4Nikolaos S. Bartsotas5Georgios Christopoulos6Laboratory of Engineering Geology and Hydrogeology, School of Mining and Metallurgical Engineering, National Technical University of Athens, Zografou, 157 80 Athens, GreeceNational Observatory of Athens, Operational Unit BEYOND Centre for Earth Observation Research and Satellite Remote Sensing IAASARS/NOA, 152 36 Athens, GreeceLaboratory of Engineering Geology and Hydrogeology, School of Mining and Metallurgical Engineering, National Technical University of Athens, Zografou, 157 80 Athens, GreeceNational Observatory of Athens, Operational Unit BEYOND Centre for Earth Observation Research and Satellite Remote Sensing IAASARS/NOA, 152 36 Athens, GreeceNational Observatory of Athens, Operational Unit BEYOND Centre for Earth Observation Research and Satellite Remote Sensing IAASARS/NOA, 152 36 Athens, GreeceNational Observatory of Athens, Operational Unit BEYOND Centre for Earth Observation Research and Satellite Remote Sensing IAASARS/NOA, 152 36 Athens, GreeceNational Observatory of Athens, Operational Unit BEYOND Centre for Earth Observation Research and Satellite Remote Sensing IAASARS/NOA, 152 36 Athens, GreeceLandslides are one of the most severe geohazards globally, causing extreme financial and social losses. While InSAR time-series analyses provide valuable insights into landslide detection, mapping, and monitoring, AI is also implemented in a variety of geohazards, including landslides. In the present study, a machine learning (ML) landslide susceptibility map is proposed that integrates the geotectonic units of Greece and incorporates various sources of landslide data. Satellite data from Persistent Scatterer Interferometry analysis, validated by geotechnical experts, resulted in an extremely large dataset of more than 3000 landslides in an area of interest, including the most landslide-prone area in Greece. The gradient-boosted decision tree was employed in the landslide susceptibility mapping. The model was trained on three geotectonic units and five prefectures of Western Greece and performed well in predicting landslide events. Finally, a SHAP (SHapley Additive exPlanations) analysis verified that precipitation and geology, which are the main landslide-triggering and preparatory factors, respectively, in Greece, positively affected landslide characterization. The innovation of the proposed research lies in the uniqueness of this newly created dataset, comprising a remarkably large number of landslide and non-landslide locations in Western Greece. By adopting a strict machine learning methodology, the spatial autocorrelation effect, which is overlooked in similar studies, was reduced. Also, leveraging the unique features of the geological formations, the model was trained to incorporate differences in the landslide susceptibility of formations located in different geotectonic units with variant geotechnical characteristics. The proposed approach facilitates the generalization of the model and sets a strong base for the creation of a national-scale landslide susceptibility mapping and forecasting system.https://www.mdpi.com/2072-4292/17/7/1161SAR interferometrylandslide susceptibilityXGboostWestern GreeceSHAP analysisexplainable ML
spellingShingle Stavroula Alatza
Alexis Apostolakis
Constantinos Loupasakis
Charalampos Kontoes
Martha Kokkalidou
Nikolaos S. Bartsotas
Georgios Christopoulos
Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western Greece
Remote Sensing
SAR interferometry
landslide susceptibility
XGboost
Western Greece
SHAP analysis
explainable ML
title Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western Greece
title_full Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western Greece
title_fullStr Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western Greece
title_full_unstemmed Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western Greece
title_short Harnessing InSAR and Machine Learning for Geotectonic Unit-Specific Landslide Susceptibility Mapping: The Case of Western Greece
title_sort harnessing insar and machine learning for geotectonic unit specific landslide susceptibility mapping the case of western greece
topic SAR interferometry
landslide susceptibility
XGboost
Western Greece
SHAP analysis
explainable ML
url https://www.mdpi.com/2072-4292/17/7/1161
work_keys_str_mv AT stavroulaalatza harnessinginsarandmachinelearningforgeotectonicunitspecificlandslidesusceptibilitymappingthecaseofwesterngreece
AT alexisapostolakis harnessinginsarandmachinelearningforgeotectonicunitspecificlandslidesusceptibilitymappingthecaseofwesterngreece
AT constantinosloupasakis harnessinginsarandmachinelearningforgeotectonicunitspecificlandslidesusceptibilitymappingthecaseofwesterngreece
AT charalamposkontoes harnessinginsarandmachinelearningforgeotectonicunitspecificlandslidesusceptibilitymappingthecaseofwesterngreece
AT marthakokkalidou harnessinginsarandmachinelearningforgeotectonicunitspecificlandslidesusceptibilitymappingthecaseofwesterngreece
AT nikolaossbartsotas harnessinginsarandmachinelearningforgeotectonicunitspecificlandslidesusceptibilitymappingthecaseofwesterngreece
AT georgioschristopoulos harnessinginsarandmachinelearningforgeotectonicunitspecificlandslidesusceptibilitymappingthecaseofwesterngreece