Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniques

Data-driven landslide susceptibility assessment (LSA) remains unconvincing owing to the disconnection from the modelling to physical cognition of landslide causation. Most models are mere good fits to certain datasets and can produce unexpected bias in their prediction, misleading high-risk area zon...

Full description

Saved in:
Bibliographic Details
Main Authors: Miao Yu, Li Chen, Xuanmei Fan, Peifeng Ma, Shaojie Zhao, Zhongwang Wu, Fan Yang, Longwei Xu, Monan Shan, Xiao Xie, Haowei Zeng, Zhengjia Zhang
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/10.1080/17538947.2025.2509857
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224272526966784
author Miao Yu
Li Chen
Xuanmei Fan
Peifeng Ma
Shaojie Zhao
Zhongwang Wu
Fan Yang
Longwei Xu
Monan Shan
Xiao Xie
Haowei Zeng
Zhengjia Zhang
author_facet Miao Yu
Li Chen
Xuanmei Fan
Peifeng Ma
Shaojie Zhao
Zhongwang Wu
Fan Yang
Longwei Xu
Monan Shan
Xiao Xie
Haowei Zeng
Zhengjia Zhang
author_sort Miao Yu
collection DOAJ
description Data-driven landslide susceptibility assessment (LSA) remains unconvincing owing to the disconnection from the modelling to physical cognition of landslide causation. Most models are mere good fits to certain datasets and can produce unexpected bias in their prediction, misleading high-risk area zoning. To validate data-driven LSA, this study delved into the innate interactions between input landslide features and predictions by model explanation and compared feature permutation results with landslide statistical priors. Furthermore, multi-temporal interferometric synthetic aperture radar (MT-InSAR) derived ground deformation was applied in an alpha pixel fusion and growth method for LSA enhancement. This study took Hong Kong as the research area, employed extreme gradient boosting (XGBoost) for LSA, and utilized Shapley additive explanations (SHAP) method for model explanation. The mean Shapley values – indicating feature importance – for slope, stream power index (SPI) and land use are 1.31, 1.12, and 0.67, respectively. This aligns with the landslide feature permutation derived from prior statistics, verifying the model prediction reliability. The applied InSAR enhancement results in a 13% increase of ‘(very) high’ landslide susceptibility areas. Additionally, LSA results and ground deformation map were cross-validated in the virtual geographic environment. This study improves the reliability of data-driven LSA through model explanation and InSAR enhancement.
format Article
id doaj-art-25d8fda33dde478e954f4099bb366c92
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-25d8fda33dde478e954f4099bb366c922025-08-25T11:31:38ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2509857Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniquesMiao Yu0Li Chen1Xuanmei Fan2Peifeng Ma3Shaojie Zhao4Zhongwang Wu5Fan Yang6Longwei Xu7Monan Shan8Xiao Xie9Haowei Zeng10Zhengjia Zhang11Department of Space Information, Space Engineering University, Beijing, People’s Republic of ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu, People’s Republic of ChinaState Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu, People’s Republic of ChinaInstitute of Space and Earth Information Science, The Chinese University of Hong Kong, Hong Kong, People’s Republic of ChinaDepartment of Space Information, Space Engineering University, Beijing, People’s Republic of ChinaDepartment of Space Information, Space Engineering University, Beijing, People’s Republic of ChinaDepartment of Space Information, Space Engineering University, Beijing, People’s Republic of ChinaDepartment of Space Information, Space Engineering University, Beijing, People’s Republic of ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai, People’s Republic of ChinaInstitute of Applied Ecology, Chinese Academy of Sciences, Beijing, People’s Republic of ChinaGeomatics Center, Chengdu Institute of Survey & Investigation, Chengdu, People’s Republic of ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan, People’s Republic of ChinaData-driven landslide susceptibility assessment (LSA) remains unconvincing owing to the disconnection from the modelling to physical cognition of landslide causation. Most models are mere good fits to certain datasets and can produce unexpected bias in their prediction, misleading high-risk area zoning. To validate data-driven LSA, this study delved into the innate interactions between input landslide features and predictions by model explanation and compared feature permutation results with landslide statistical priors. Furthermore, multi-temporal interferometric synthetic aperture radar (MT-InSAR) derived ground deformation was applied in an alpha pixel fusion and growth method for LSA enhancement. This study took Hong Kong as the research area, employed extreme gradient boosting (XGBoost) for LSA, and utilized Shapley additive explanations (SHAP) method for model explanation. The mean Shapley values – indicating feature importance – for slope, stream power index (SPI) and land use are 1.31, 1.12, and 0.67, respectively. This aligns with the landslide feature permutation derived from prior statistics, verifying the model prediction reliability. The applied InSAR enhancement results in a 13% increase of ‘(very) high’ landslide susceptibility areas. Additionally, LSA results and ground deformation map were cross-validated in the virtual geographic environment. This study improves the reliability of data-driven LSA through model explanation and InSAR enhancement.https://www.tandfonline.com/doi/10.1080/17538947.2025.2509857Landslide susceptibilitymachine learningInSARmodel explanation
spellingShingle Miao Yu
Li Chen
Xuanmei Fan
Peifeng Ma
Shaojie Zhao
Zhongwang Wu
Fan Yang
Longwei Xu
Monan Shan
Xiao Xie
Haowei Zeng
Zhengjia Zhang
Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniques
International Journal of Digital Earth
Landslide susceptibility
machine learning
InSAR
model explanation
title Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniques
title_full Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniques
title_fullStr Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniques
title_full_unstemmed Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniques
title_short Validating and enhancing data-driven landslide susceptibility prediction by model explanation and MT-InSAR techniques
title_sort validating and enhancing data driven landslide susceptibility prediction by model explanation and mt insar techniques
topic Landslide susceptibility
machine learning
InSAR
model explanation
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2509857
work_keys_str_mv AT miaoyu validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT lichen validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT xuanmeifan validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT peifengma validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT shaojiezhao validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT zhongwangwu validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT fanyang validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT longweixu validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT monanshan validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT xiaoxie validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT haoweizeng validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques
AT zhengjiazhang validatingandenhancingdatadrivenlandslidesusceptibilitypredictionbymodelexplanationandmtinsartechniques