Landslide Susceptibility Mapping Based on Random Forest and Boosted Regression Tree Models, and a Comparison of Their Performance

Soyoung Park,Jinsoo Kim

doi:10.3390/app9050942

Abstract

This study aims to analyze and compare landslide susceptibility at Woomyeon Mountain, South Korea, based on the random forest (RF) model and the boosted regression tree (BRT) model. Through the construction of a landslide inventory map, 140 landslide locations were found. Among these, 42 (30%) were reserved to validate the model after 98 (70%) had been selected at random for model training. Fourteen landslide explanatory variables related to topography, hydrology, and forestry factors were considered and selected, based on the results of information gain for the modeling. The results were evaluated and compared using the receiver operating characteristic curve and statistical indices. The analysis showed that the RF model was better than the BRT model. The RF model yielded higher specificity, overall accuracy, and kappa index than the BRT model. In addition, the RF model, with a prediction rate of 0.865, performed slightly better than the BRT model, which had a prediction rate of 0.851. These results indicate that the landslide susceptibility maps (LSMs) produced in this study had good performance for predicting the spatial landslide distribution in the study area. These LSMs could be helpful for establishing mitigation strategies and for land use planning.

Highlights

A landslide is defined as a natural disaster that occurs when gravity causes a mass of debris, soil, or rock to move on a downward slope [1]
The information gain (IG), random forest (RF), and boosted regression tree (BRT) models were implemented in R (Foundation for Statistical Computing, Vienna, Austria) using the “FSelector,”
Landslide-related spatial data consisting of a landslide inventory, and landslide explanatory variables were collected and prepared

Summary

Introduction

A landslide is defined as a natural disaster that occurs when gravity causes a mass of debris, soil, or rock to move on a downward slope [1]. The majority of landslides occur as a result of hydroclimatic events, such as prolonged or intensive rain. Mechanisms such as seismic triggers, wind, and freeze–thaw cycles are known to initiate landslides [2]. Mountains with shallow layers of soil that have formed in place from weathered gneiss and granite make up roughly 70% of the Korean peninsula [3]. Such terrain is vulnerable to weakening during heavy rainfall. The heavy rain associated with typhoons has the potential to cause landslides in South Korea [4].

Objectives

Methods

Results

Discussion

Conclusion