Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks

Accurate assessment of landslide susceptibility is vital for risk prevention, yet existing methods often overlook remote but interconnected geographical features, leading to unreliable maps. To effectively address this issue, the complex mountainous terrain and geomorphological features involved in...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangqi Lei, Hanhu Liu, Zhe Chen, Shaoda Li, Hang Chen, Shuai Zeng, Xiao Wang, Wenqian Bai, Wei Li, Lorenzo Picco
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/10.1080/17538947.2025.2468913
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224356321820672
author Xiangqi Lei
Hanhu Liu
Zhe Chen
Shaoda Li
Hang Chen
Shuai Zeng
Xiao Wang
Wenqian Bai
Wei Li
Lorenzo Picco
author_facet Xiangqi Lei
Hanhu Liu
Zhe Chen
Shaoda Li
Hang Chen
Shuai Zeng
Xiao Wang
Wenqian Bai
Wei Li
Lorenzo Picco
author_sort Xiangqi Lei
collection DOAJ
description Accurate assessment of landslide susceptibility is vital for risk prevention, yet existing methods often overlook remote but interconnected geographical features, leading to unreliable maps. To effectively address this issue, the complex mountainous terrain and geomorphological features involved in landslide formation were fully considered in this work. This was attained by introducing geographical environmental correlations from the perspectives of mapping units and susceptibility assessment models to achieve comprehensive linkage between the landslides and the affected environments, thereby enhancing accuracy. Significantly, in this work, the SDGSAT-1 data were innovatively applied to the field of landslide research and the landslide susceptibility in Jiulong County, Ganzi, was evaluated based on optimal-scale slope units and Graph Neural Networks (GNN). The results showed that: (1) SDGSAT-1 offers significant benefits to landslide research. Our analysis compared LANDSAT with similar resolutions from multiple perspectives and found that SDGSAT-1 has substantial advantages. (2) The landslide susceptibility assessment method proposed in this work, based on optimal-scale slope units and GNN, demonstrated superior performance, with various evaluation metrics, such as AUC, Accuracy, and Precision far exceeding those of other machine learning models.
format Article
id doaj-art-497de70005c44caab021930aa8d96c5a
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-497de70005c44caab021930aa8d96c5a2025-08-25T11:24:53ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2468913Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural NetworksXiangqi Lei0Hanhu Liu1Zhe Chen2Shaoda Li3Hang Chen4Shuai Zeng5Xiao Wang6Wenqian Bai7Wei Li8Lorenzo Picco9College of Earth and Planetary Sciences, Chengdu University of Technology, Chengdu, People’s Republic of ChinaCollege of Geography and Planning, Chengdu University of Technology, Chengdu, People’s Republic of ChinaCollege of Mathematics and Physics, Chengdu University of Technology, Chengdu, People’s Republic of ChinaCollege of Earth and Planetary Sciences, Chengdu University of Technology, Chengdu, People’s Republic of ChinaCollege of Surveying, Mapping and Geoinformation, Sichuan Water Conservancy Vocational College, Chengdu, People’s Republic of ChinaSichuan Provincial Institute of Land Space Ecological Restoration and Geological Disaster Prevention and Control, Chengdu, People’s Republic of ChinaCollege of Architecture and Civil Engineering, Chengdu University, Chengdu, People’s Republic of ChinaCollege of Geography and Planning, Chengdu University of Technology, Chengdu, People’s Republic of ChinaCollege of Earth and Planetary Sciences, Chengdu University of Technology, Chengdu, People’s Republic of ChinaDepartment of Land and Agroforest Environment, University of Padova, Padova, ItalyAccurate assessment of landslide susceptibility is vital for risk prevention, yet existing methods often overlook remote but interconnected geographical features, leading to unreliable maps. To effectively address this issue, the complex mountainous terrain and geomorphological features involved in landslide formation were fully considered in this work. This was attained by introducing geographical environmental correlations from the perspectives of mapping units and susceptibility assessment models to achieve comprehensive linkage between the landslides and the affected environments, thereby enhancing accuracy. Significantly, in this work, the SDGSAT-1 data were innovatively applied to the field of landslide research and the landslide susceptibility in Jiulong County, Ganzi, was evaluated based on optimal-scale slope units and Graph Neural Networks (GNN). The results showed that: (1) SDGSAT-1 offers significant benefits to landslide research. Our analysis compared LANDSAT with similar resolutions from multiple perspectives and found that SDGSAT-1 has substantial advantages. (2) The landslide susceptibility assessment method proposed in this work, based on optimal-scale slope units and GNN, demonstrated superior performance, with various evaluation metrics, such as AUC, Accuracy, and Precision far exceeding those of other machine learning models.https://www.tandfonline.com/doi/10.1080/17538947.2025.2468913SDGSAT-1landslideslandslide susceptibility assessmentautomatic extraction of slope unitsGraph Neural Network
spellingShingle Xiangqi Lei
Hanhu Liu
Zhe Chen
Shaoda Li
Hang Chen
Shuai Zeng
Xiao Wang
Wenqian Bai
Wei Li
Lorenzo Picco
Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks
International Journal of Digital Earth
SDGSAT-1
landslides
landslide susceptibility assessment
automatic extraction of slope units
Graph Neural Network
title Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks
title_full Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks
title_fullStr Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks
title_full_unstemmed Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks
title_short Investigating the landslide susceptibility assessment methods for multi-scale slope units based on SDGSAT-1 and Graph Neural Networks
title_sort investigating the landslide susceptibility assessment methods for multi scale slope units based on sdgsat 1 and graph neural networks
topic SDGSAT-1
landslides
landslide susceptibility assessment
automatic extraction of slope units
Graph Neural Network
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2468913
work_keys_str_mv AT xiangqilei investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT hanhuliu investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT zhechen investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT shaodali investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT hangchen investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT shuaizeng investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT xiaowang investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT wenqianbai investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT weili investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks
AT lorenzopicco investigatingthelandslidesusceptibilityassessmentmethodsformultiscaleslopeunitsbasedonsdgsat1andgraphneuralnetworks