Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China

ABSTRACT: To enhance the prediction accuracy of landslides in in Longyan City, China, this study developed a methodology for geologic hazard susceptibility assessment based on a coupled model composed of a Geographic Information System (GIS) with integrated spatial data, a frequency ratio (FR) model...

Full description

Saved in:
Bibliographic Details
Main Authors: Zong-yue Lu, Gen-yuan Liu, Xi-dong Zhao, Kang Sun, Yan-si Chen, Zhi-hong Song, Kai Xue, Ming-shan Yang
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-04-01
Series:China Geology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2096519225000692
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849709876083687424
author Zong-yue Lu
Gen-yuan Liu
Xi-dong Zhao
Kang Sun
Yan-si Chen
Zhi-hong Song
Kai Xue
Ming-shan Yang
author_facet Zong-yue Lu
Gen-yuan Liu
Xi-dong Zhao
Kang Sun
Yan-si Chen
Zhi-hong Song
Kai Xue
Ming-shan Yang
author_sort Zong-yue Lu
collection DOAJ
description ABSTRACT: To enhance the prediction accuracy of landslides in in Longyan City, China, this study developed a methodology for geologic hazard susceptibility assessment based on a coupled model composed of a Geographic Information System (GIS) with integrated spatial data, a frequency ratio (FR) model, and a random forest (RF) model (also referred to as the coupled FR-RF model). The coupled FR-RF model was constructed based on the analysis of nine influential factors, including distance from roads, normalized difference vegetation index (NDVI), and slope. The performance of the coupled FR-RF model was assessed using metrics such as Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves, yielding Area Under the Curve (AUC) values of 0.93 and 0.95, which indicate high predictive accuracy and reliability for geological hazard forecasting. Based on the model predictions, five susceptibility levels were determined in the study area, providing crucial spatial information for geologic hazard prevention and control. The contributions of various influential factors to landslide susceptibility were determined using SHapley Additive exPlanations (SHAP) analysis and the Gini index, enhancing the model interpretability and transparency. Additionally, this study discussed the limitations of the coupled FR-RF model and the prospects for its improvement using new technologies. This study provides an innovative method and theoretical support for geologic hazard prediction and management, holding promising prospects for application.
format Article
id doaj-art-6e63935635bb40deb19d73dddeee1a32
institution DOAJ
issn 2589-9430
language English
publishDate 2025-04-01
publisher KeAi Communications Co., Ltd.
record_format Article
series China Geology
spelling doaj-art-6e63935635bb40deb19d73dddeee1a322025-08-20T03:15:06ZengKeAi Communications Co., Ltd.China Geology2589-94302025-04-018228129410.31035/cg2024123Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast ChinaZong-yue Lu0Gen-yuan Liu1Xi-dong Zhao2Kang Sun3Yan-si Chen4Zhi-hong Song5Kai Xue6Ming-shan Yang7Center for Geophysical Survey, China Geological Survey, Langfang 065000, China; Technology Innovation Center for Earth Near Surface Detection, China Geological Survey, Langfang 065000, ChinaCenter for Geophysical Survey, China Geological Survey, Langfang 065000, China; Technology Innovation Center for Earth Near Surface Detection, China Geological Survey, Langfang 065000, China; Corresponding authorHarbin Center for Integrated Natural Resources Survey, China Geological Survey, Harbin 150086, China; Observation and Research Station of Earth Critical Zone in Black Soil, Harbin, Ministry of Natural Resources 150086, China; Corresponding authorCenter for Geophysical Survey, China Geological Survey, Langfang 065000, China; Technology Innovation Center for Earth Near Surface Detection, China Geological Survey, Langfang 065000, ChinaCenter for Geophysical Survey, China Geological Survey, Langfang 065000, China; Technology Innovation Center for Earth Near Surface Detection, China Geological Survey, Langfang 065000, ChinaCenter for Geophysical Survey, China Geological Survey, Langfang 065000, China; Technology Innovation Center for Earth Near Surface Detection, China Geological Survey, Langfang 065000, ChinaCenter for Geophysical Survey, China Geological Survey, Langfang 065000, China; Technology Innovation Center for Earth Near Surface Detection, China Geological Survey, Langfang 065000, ChinaCenter for Geophysical Survey, China Geological Survey, Langfang 065000, China; Technology Innovation Center for Earth Near Surface Detection, China Geological Survey, Langfang 065000, ChinaABSTRACT: To enhance the prediction accuracy of landslides in in Longyan City, China, this study developed a methodology for geologic hazard susceptibility assessment based on a coupled model composed of a Geographic Information System (GIS) with integrated spatial data, a frequency ratio (FR) model, and a random forest (RF) model (also referred to as the coupled FR-RF model). The coupled FR-RF model was constructed based on the analysis of nine influential factors, including distance from roads, normalized difference vegetation index (NDVI), and slope. The performance of the coupled FR-RF model was assessed using metrics such as Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves, yielding Area Under the Curve (AUC) values of 0.93 and 0.95, which indicate high predictive accuracy and reliability for geological hazard forecasting. Based on the model predictions, five susceptibility levels were determined in the study area, providing crucial spatial information for geologic hazard prevention and control. The contributions of various influential factors to landslide susceptibility were determined using SHapley Additive exPlanations (SHAP) analysis and the Gini index, enhancing the model interpretability and transparency. Additionally, this study discussed the limitations of the coupled FR-RF model and the prospects for its improvement using new technologies. This study provides an innovative method and theoretical support for geologic hazard prediction and management, holding promising prospects for application.http://www.sciencedirect.com/science/article/pii/S2096519225000692Machine learningLandslide susceptibility assessmentGeographic Information System (GIS)Coupled FR-RF modelRandom forestInterpretability
spellingShingle Zong-yue Lu
Gen-yuan Liu
Xi-dong Zhao
Kang Sun
Yan-si Chen
Zhi-hong Song
Kai Xue
Ming-shan Yang
Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China
China Geology
Machine learning
Landslide susceptibility assessment
Geographic Information System (GIS)
Coupled FR-RF model
Random forest
Interpretability
title Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China
title_full Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China
title_fullStr Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China
title_full_unstemmed Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China
title_short Landslide susceptibility assessment based on an interpretable coupled FR-RF model: A case study of Longyan City, Fujian Province, Southeast China
title_sort landslide susceptibility assessment based on an interpretable coupled fr rf model a case study of longyan city fujian province southeast china
topic Machine learning
Landslide susceptibility assessment
Geographic Information System (GIS)
Coupled FR-RF model
Random forest
Interpretability
url http://www.sciencedirect.com/science/article/pii/S2096519225000692
work_keys_str_mv AT zongyuelu landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina
AT genyuanliu landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina
AT xidongzhao landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina
AT kangsun landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina
AT yansichen landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina
AT zhihongsong landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina
AT kaixue landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina
AT mingshanyang landslidesusceptibilityassessmentbasedonaninterpretablecoupledfrrfmodelacasestudyoflongyancityfujianprovincesoutheastchina