Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan
Journal
Science of the Total Environment
Journal Volume
662
Pages
332-346
Date Issued
2019
Author(s)
Abstract
Landslides represent a part of the cascade of geological hazards in a wide range of geo-environments. In this study, we aim to investigate and compare the performance of two state-of-the-art machine learning models, i.e., decision tree (DT) and random forest (RF) approaches to model the massive rainfall-triggered landslide occurrences in the Izu-Oshima Volcanic Island, Japan at a regional scale. At first, a landslide inventory map is prepared consisting of 44 landslide polygons (10,444 pixels) from aerial photo-interpretation and field surveys. To estimate the robustness of the models, we randomly adapted two different samples (S1 and S2), comprising of both positive and negative cells (70% of total landslides - 7293 pixels) for training and remaining (30%–3151 pixels) for validation. Twelve causative factors including altitude, slope angle, slope aspect, plan curvature, total curvature, compound topographic index, stream power index, distance to drainage network, drainage density, distance to geological boundaries, lithology and cumulative rainfall were selected as predictors to implement the landslide susceptibility model. The area under the receiver operating characteristics (ROC) curves (AUC) and other statistical signifiers were used to verify the model accuracies. The result shows that the DT and RF models achieved remarkable predictive performance (AUC > 0.9), producing near accurate susceptibility maps. The overall efficiency of RF (AUC = 0.956) is found significantly higher than the DT (AUC = 0.928) results. Additionally, we noticed that the performance of RF for modeling landslide susceptibility is very robust even though the training and validation samples are altered. Considering the performances, we suggest that both RF and DT models can be used in other similar non-eruption-related landslide studies in the tephra-deposited rich volcanoes, as they are capable of rapidly generating accurate and stable LSM maps for risk mitigation, management practices, and decision-making. Moreover, the RF-based model is promising and enough to be recommended as a method to map regional landslide susceptibility. ? 2019 Elsevier B.V.
Subjects
Antennas; Artificial intelligence; Data mining; Decision trees; Landslides; Learning algorithms; Learning systems; Lithology; Magnetic susceptibility; Pixels; Rain; Volcanoes; Aerial photo interpretation; Compound topographic indices; Izu-Oshima Volcano Island; Landslide susceptibility; Machine learning models; Rainfall induced landslides; Random forests; Receiver operating characteristics curves (ROC); Decision making; rain; algorithm; assessment method; decision making; landslide; machine learning; numerical model; precipitation intensity; slope stability; altitude; area under the curve; Article; compound topographic index; cumulative rainfall; decision tree; distance to drainage network; distance to geological boundaries; drainage density; environmental management; environmental parameters; forecasting; geology; Japan; landslide; learning algorithm; lithology; plan curvature; priority journal; random forest; receiver operating characteristic; risk assessment; risk evaluation and mitigation strategy; slope angle; slope aspect; stratification; stream power index; topography; total curvature; volcano; Chubu; Honshu; Izu Islands; Izuoshima; Japan; Shizuoka [Chubu]
SDGs
Type
journal article