Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent Precipitation

Precipitation typically leads to the accumulation of soil moisture, which causes slope instability and triggers landslides. However, due to the lag nature of this process, landslides usually do not occur on the day of heavy rainfall. Therefore, it is essential to incorporate antecedent effective pre...

Full description

Saved in:
Bibliographic Details
Main Authors: Chuanmei Cheng, Ying Li, Dong Zhu, Yu Liu, Yongqiu Wu, Degen Lin, Hao Guo
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/6241
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331296152584192
author Chuanmei Cheng
Ying Li
Dong Zhu
Yu Liu
Yongqiu Wu
Degen Lin
Hao Guo
author_facet Chuanmei Cheng
Ying Li
Dong Zhu
Yu Liu
Yongqiu Wu
Degen Lin
Hao Guo
author_sort Chuanmei Cheng
collection DOAJ
description Precipitation typically leads to the accumulation of soil moisture, which causes slope instability and triggers landslides. However, due to the lag nature of this process, landslides usually do not occur on the day of heavy rainfall. Therefore, it is essential to incorporate antecedent effective precipitation as a factor in landslide prediction models that allow for the creation of more comprehensive landslide susceptibility maps. In this study, six machine learning models are compared, with antecedent effective precipitation included as a conditioning factor for model training. The optimal model is selected to simulate landslide susceptibility maps under four return periods (5, 10, 20, and 50 years). Additionally, the mean decreases in the Gini and SHAP values are employed to identify the most significant factors contributing to landslides. The results indicate the following: (1) Effective antecedent precipitation is the most influential factor in landslide occurrence, ranging from one to two times higher than other factors. (2) Most meteorological stations in the study area show antecedent effective precipitation that follows a lognormal distribution, mainly in coastal areas, with a secondary fit to the general extreme value distribution. The spatial distribution of antecedent effective precipitation is more prominent in the coastal and western mountainous regions, with lower values that then increase with longer return periods in central areas. (3) The XGBoost model achieves the best performance, with an area under the curve of 0.96 and an accuracy of 89.02%. (4) The landslide susceptibility maps for the four return periods reveal three high-risk zones: the southern coastal mountains, the western Zhejiang mountains, and the areas surrounding the hilly region of Shaoxing to Taizhou in central Zhejiang. This study provides dynamic decision-making support for the prevention and control of rainstorm-induced landslide risks.
format Article
id doaj-art-e6dc71009f0447df8fc8c649a0c13bac
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e6dc71009f0447df8fc8c649a0c13bac2025-08-20T03:46:38ZengMDPI AGApplied Sciences2076-34172025-06-011511624110.3390/app15116241Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent PrecipitationChuanmei Cheng0Ying Li1Dong Zhu2Yu Liu3Yongqiu Wu4Degen Lin5Hao Guo6College of Geography and Environmental Sciences, Zhejiang Normal University, Jinhua 321004, ChinaZhejiang Institute of Meteorological Sciences, Hangzhou 310051, ChinaThe 3rd Geological Brigade of Zhejiang Province, Jinhua 321000, ChinaCollege of Geography and Environmental Sciences, Zhejiang Normal University, Jinhua 321004, ChinaCollege of Geography and Environmental Sciences, Zhejiang Normal University, Jinhua 321004, ChinaBusiness School International Department, Wenzhou University, Wenzhou, 325035, ChinaCollege of Geography and Environmental Sciences, Zhejiang Normal University, Jinhua 321004, ChinaPrecipitation typically leads to the accumulation of soil moisture, which causes slope instability and triggers landslides. However, due to the lag nature of this process, landslides usually do not occur on the day of heavy rainfall. Therefore, it is essential to incorporate antecedent effective precipitation as a factor in landslide prediction models that allow for the creation of more comprehensive landslide susceptibility maps. In this study, six machine learning models are compared, with antecedent effective precipitation included as a conditioning factor for model training. The optimal model is selected to simulate landslide susceptibility maps under four return periods (5, 10, 20, and 50 years). Additionally, the mean decreases in the Gini and SHAP values are employed to identify the most significant factors contributing to landslides. The results indicate the following: (1) Effective antecedent precipitation is the most influential factor in landslide occurrence, ranging from one to two times higher than other factors. (2) Most meteorological stations in the study area show antecedent effective precipitation that follows a lognormal distribution, mainly in coastal areas, with a secondary fit to the general extreme value distribution. The spatial distribution of antecedent effective precipitation is more prominent in the coastal and western mountainous regions, with lower values that then increase with longer return periods in central areas. (3) The XGBoost model achieves the best performance, with an area under the curve of 0.96 and an accuracy of 89.02%. (4) The landslide susceptibility maps for the four return periods reveal three high-risk zones: the southern coastal mountains, the western Zhejiang mountains, and the areas surrounding the hilly region of Shaoxing to Taizhou in central Zhejiang. This study provides dynamic decision-making support for the prevention and control of rainstorm-induced landslide risks.https://www.mdpi.com/2076-3417/15/11/6241landslidesusceptibility assessmentmachine learningeffective antecedent precipitationreturn period
spellingShingle Chuanmei Cheng
Ying Li
Dong Zhu
Yu Liu
Yongqiu Wu
Degen Lin
Hao Guo
Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent Precipitation
Applied Sciences
landslide
susceptibility assessment
machine learning
effective antecedent precipitation
return period
title Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent Precipitation
title_full Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent Precipitation
title_fullStr Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent Precipitation
title_full_unstemmed Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent Precipitation
title_short Rain-Induced Shallow Landslide Susceptibility Under Multiple Scenarios Based on Effective Antecedent Precipitation
title_sort rain induced shallow landslide susceptibility under multiple scenarios based on effective antecedent precipitation
topic landslide
susceptibility assessment
machine learning
effective antecedent precipitation
return period
url https://www.mdpi.com/2076-3417/15/11/6241
work_keys_str_mv AT chuanmeicheng raininducedshallowlandslidesusceptibilityundermultiplescenariosbasedoneffectiveantecedentprecipitation
AT yingli raininducedshallowlandslidesusceptibilityundermultiplescenariosbasedoneffectiveantecedentprecipitation
AT dongzhu raininducedshallowlandslidesusceptibilityundermultiplescenariosbasedoneffectiveantecedentprecipitation
AT yuliu raininducedshallowlandslidesusceptibilityundermultiplescenariosbasedoneffectiveantecedentprecipitation
AT yongqiuwu raininducedshallowlandslidesusceptibilityundermultiplescenariosbasedoneffectiveantecedentprecipitation
AT degenlin raininducedshallowlandslidesusceptibilityundermultiplescenariosbasedoneffectiveantecedentprecipitation
AT haoguo raininducedshallowlandslidesusceptibilityundermultiplescenariosbasedoneffectiveantecedentprecipitation