Integration of geospatial foundation models in unsupervised change detection workflows for landslide identification

This study investigates the integration of Geospatial Foundation Models (GFMs) into an unsupervised change detection workflow for landslide identification. As climate change increases landslide frequency, rapid and automated detection systems are essential for a timely response. However, the high co...

Full description

Saved in:
Bibliographic Details
Main Authors: Julia Anna Leonardi, Valerio Marsocci, Vasil Yordanov, Maria Antonia Brovelli
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2547292
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224283824324608
author Julia Anna Leonardi
Valerio Marsocci
Vasil Yordanov
Maria Antonia Brovelli
author_facet Julia Anna Leonardi
Valerio Marsocci
Vasil Yordanov
Maria Antonia Brovelli
author_sort Julia Anna Leonardi
collection DOAJ
description This study investigates the integration of Geospatial Foundation Models (GFMs) into an unsupervised change detection workflow for landslide identification. As climate change increases landslide frequency, rapid and automated detection systems are essential for a timely response. However, the high cost of annotating satellite datasets has driven interest toward unsupervised methods that could operate effectively with limited data. This work addresses two key gaps: (1) the absence of a dedicated dataset for unsupervised landslide change detection, and (2) limited investigation of GFMs as feature extractors in unsupervised frameworks. To address these, we introduce the Global Landslide Dataset for Change Detection (GLaD4CD), comprising 174 Sentinel-2 bi-temporal image pairs of global landslide events, and propose LandslideMetric-CD, an unsupervised model based on Metric-CD by Bandara and Patel [2023. “Deep Metric Learning for Unsupervised Remote Sensing Change Detection.” arXiv:2303.09536 [cs]], adapted to incorporate the SSL4EO DINO GFM. While domain-guided approaches like band-specific thresholding achieve higher F1 scores (48.41% for Band 04), LandslideMetric-CD (F1 = 31.68%) outperforms fully automatic differential thresholding using the full spectral range (F1 = 19.33%) and RGB-based deep learning methods (F1 = 19.66% for Change Detection based on image Reconstruction Loss (CDRL) [Noh et al. 2024. “Unsupervised Change Detection Based on Image Reconstruction Loss.” Remote Sensing Letters 15 (9): 919–929]). These findings underscore the importance of spectral band selection and demonstrate the potential of GFMs for automated, expert-independent landslide detection.
format Article
id doaj-art-433b8eaa8f9f4005b60c31b443496acb
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-433b8eaa8f9f4005b60c31b443496acb2025-08-25T11:31:45ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2547292Integration of geospatial foundation models in unsupervised change detection workflows for landslide identificationJulia Anna Leonardi0Valerio Marsocci1Vasil Yordanov2Maria Antonia Brovelli3Department of Civil and Environmental Engineering, Politecnico di Milano, Milan, ItalyESA, ESRIN, φ-lab, Frascati, ItalyDepartment of Civil and Environmental Engineering, Politecnico di Milano, Milan, ItalyDepartment of Civil and Environmental Engineering, Politecnico di Milano, Milan, ItalyThis study investigates the integration of Geospatial Foundation Models (GFMs) into an unsupervised change detection workflow for landslide identification. As climate change increases landslide frequency, rapid and automated detection systems are essential for a timely response. However, the high cost of annotating satellite datasets has driven interest toward unsupervised methods that could operate effectively with limited data. This work addresses two key gaps: (1) the absence of a dedicated dataset for unsupervised landslide change detection, and (2) limited investigation of GFMs as feature extractors in unsupervised frameworks. To address these, we introduce the Global Landslide Dataset for Change Detection (GLaD4CD), comprising 174 Sentinel-2 bi-temporal image pairs of global landslide events, and propose LandslideMetric-CD, an unsupervised model based on Metric-CD by Bandara and Patel [2023. “Deep Metric Learning for Unsupervised Remote Sensing Change Detection.” arXiv:2303.09536 [cs]], adapted to incorporate the SSL4EO DINO GFM. While domain-guided approaches like band-specific thresholding achieve higher F1 scores (48.41% for Band 04), LandslideMetric-CD (F1 = 31.68%) outperforms fully automatic differential thresholding using the full spectral range (F1 = 19.33%) and RGB-based deep learning methods (F1 = 19.66% for Change Detection based on image Reconstruction Loss (CDRL) [Noh et al. 2024. “Unsupervised Change Detection Based on Image Reconstruction Loss.” Remote Sensing Letters 15 (9): 919–929]). These findings underscore the importance of spectral band selection and demonstrate the potential of GFMs for automated, expert-independent landslide detection.https://www.tandfonline.com/doi/10.1080/17538947.2025.2547292Landslide detectionchange detectiongeospatial foundation modelsremote sensingdeep learning
spellingShingle Julia Anna Leonardi
Valerio Marsocci
Vasil Yordanov
Maria Antonia Brovelli
Integration of geospatial foundation models in unsupervised change detection workflows for landslide identification
International Journal of Digital Earth
Landslide detection
change detection
geospatial foundation models
remote sensing
deep learning
title Integration of geospatial foundation models in unsupervised change detection workflows for landslide identification
title_full Integration of geospatial foundation models in unsupervised change detection workflows for landslide identification
title_fullStr Integration of geospatial foundation models in unsupervised change detection workflows for landslide identification
title_full_unstemmed Integration of geospatial foundation models in unsupervised change detection workflows for landslide identification
title_short Integration of geospatial foundation models in unsupervised change detection workflows for landslide identification
title_sort integration of geospatial foundation models in unsupervised change detection workflows for landslide identification
topic Landslide detection
change detection
geospatial foundation models
remote sensing
deep learning
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2547292
work_keys_str_mv AT juliaannaleonardi integrationofgeospatialfoundationmodelsinunsupervisedchangedetectionworkflowsforlandslideidentification
AT valeriomarsocci integrationofgeospatialfoundationmodelsinunsupervisedchangedetectionworkflowsforlandslideidentification
AT vasilyordanov integrationofgeospatialfoundationmodelsinunsupervisedchangedetectionworkflowsforlandslideidentification
AT mariaantoniabrovelli integrationofgeospatialfoundationmodelsinunsupervisedchangedetectionworkflowsforlandslideidentification