Debris Flow Susceptibility Assessment Using the Integrated Random Forest Based Steady-State Infinite Slope Method: A Case Study in Changbai Mountain, China

Alu Si,Guangzhi Rong,Emmanuel Kazuva,Jiquan Zhang,Yichen Zhang,Yongbin Bao,Zhenhua Dong

doi:10.3390/w12072057

Alu Si, Guangzhi Rong + Show 5 more

Open Access

https://doi.org/10.3390/w12072057

Copy DOI

Abstract

Debris flow events often pose significant damage and are a threat to infrastructure and even livelihoods. Recent studies have mainly focused on determining the susceptibility of debris flow using deterministic or heuristic/probabilistic models. However, each type of model has its own significant advantages with some irreparable disadvantages. The random forest model, which is sensitive to the region where the terrain conditions are suitable for the occurrence of debris flow, was applied along with the steady-state infinite slope method, which is capable of describing the initiation mechanism of debris flow. In this manner, a random-forest-based steady-state infinite slope method was used to conduct susceptibility assessment of debris-flow at Changbai mountain area. Results showed that the assessment accuracy of the proposed random-forest-based steady-state infinite slope method reached 90.88%; however, the accuracy of just the random forest model or steady-state infinite slope method was only 88.48% or 60.45%, respectively. Compared with the single-model assessment results, the assessment accuracy of the proposed method improved by 2.4% and 30.43%, respectively. Meanwhile, the debris-flow-prone area of the proposed method was reduced. The random-forest-based steady-state infinite slope method inherited the excellent diagnostic performance of the random-forest models in the region where the debris flow disaster already occurred; meanwhile, this method further refined the debris-flow-prone area from the suitable terrain area based on physico-mechanical properties; thus, the performance of this method was better than those of the other two models.

Highlights

As one of the most widespread natural process in mountainous environments, the occurrence of debris flow events often poses significant damage and a threat to infrastructure, urban development, and the livelihood of humans, even potentially resulting in loss of life [1,2,3]
Susceptibility assessment results of the random forest (RF) model and steady-state infinite slope (SSIS) method are shown in Figure 8a,b, respectively
This study aims to use the proposed random-forest-based steady-state infinite slope method to analyze debris flow susceptibility of Changbai mountain area

Summary

Introduction

As one of the most widespread natural process in mountainous environments, the occurrence of debris flow events often poses significant damage and a threat to infrastructure, urban development, and the livelihood of humans, even potentially resulting in loss of life [1,2,3]. With rapid socio-economic development, this situation tends to be more critical, if it is not well handled. In this case, relevant studies in these popular research areas have been the focus of many researchers. Water 2020, 12, 2057 owing to the predisposing and triggering factors of this natural phenomenon, the total control of debris flow events is always difficult, transforming the focus of contemporary studies from reducing the occurrence of debris flow to predicting its spatial and temporal occurrence. Many studies focus on thoroughly determining the susceptibility to representing the likelihood of debris flow occurrence. In these studies, the heuristic and probabilistic models are widely used. It means that areas with conditions similar to those that have already been affected by debris flow are more prone to further debris flow events [5,6,7]

Objectives

Methods

Results

Discussion

Conclusion