Landslide and Wildfire Susceptibility Assessment in Southeast Asia Using Ensemble Machine Learning Methods

Abstract

Southeast Asia (SEA) is a region affected by landslide and wildfire; however, few studies on susceptibility modeling for the two hazards together have been conducted for this region, and the intersection and the uncertainty of the two hazards are rarely assessed. Thus, the intersection of landslide and wildfire susceptibility and the spatial uncertainty of the susceptibility maps were studied in this paper. Reliable landslide and wildfire susceptibility maps are necessary for disaster management and land use planning. This work used three advanced ensemble machine learning algorithms: RF (Random Forest), GBDT (Gradient Boosting Decision Tree) and AdaBoost (Adaptive Boosting) to assess the landslide and wildfire susceptibility for SEA. A geo-database was established with 2759 landslide locations, 1633 wildfire locations and 18 predictor variables in total. The performances of the models were assessed using the overall classification accuracy (ACC), Precision, the area under the ROC (receiver operating curve) (AUC) and confusion matrix values. The results showed RF performs superior in both landslide (ACC = 0.81, Precision = 0.78 and AUC= 0.89) and wildfire (ACC= 0.83, Precision = 0.83 and AUC = 0.91) susceptibility modeling, followed by GBDT and AdaBoost. The overall superiority of RF over other models indicates that it is potentially an efficient model for landslide and wildfire susceptibility mapping. The landslide and wildfire susceptibility were obtained using the RF model. This paper also conducted an overlay analysis of the two hazards. The uncertainty of the susceptibility was further assessed using the coefficient of variation (CV). Additionally, the distance to roads is relatively important in both landslide and wildfire susceptibility, which is the most important in landslides and the second most important in wildfires. The result of this paper is useful for mastering the whole situation of hazard susceptibility and proves that RF is a robust model in the hazard susceptibility assessment in SEA.

Characterizing Topographic Influences of Bushfire Severity Using Machine Learning Models: A Case Study in a Hilly Terrain of Victoria, Australia

“…For bushfire severity research where higher precision (correctly predicted positive observation to the total predicted positive observations) is required, Random Forest seems to be a better choice than GB especially for achieving better precision in the identified burn severity areas. Similar superiority in performance of RF model has also been shown in previous research [92]. However, RF model consistently missed out a significant number of burn severity areas which has been reported by low recall (correctly predicted positive observations to the all observations in actual) metrics.…”

Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models

“…It continuously improves prediction accuracy through interactions. A new decision tree was established in the gradient direction of the reducing residuals in each iteration [43]. The GBDT tree is constructed sequentially.…”

Interdependencies Between Wildfire‐Induced Alterations in Soil Properties, Near‐Surface Processes, and Geohazards

“…Geohazards (Table 1), such as shallow landslides, debris flows, and soil erosion, are some of the most notable and far‐reaching post‐fire processes that can trigger a catastrophic ripple effect. Coincident with worsening wildfires, longer fire seasons, expanding fire‐prone terrain, and the growing wildland‐urban interface, wildfire‐induced geohazards and their associated mortality and morbidity risks are increasing in many regions globally (Abbate et al., 2019; De Graff, 2014; Fraser et al., 2022; He et al., 2021; Neary et al., 2019; Tang et al., 2019; Vitolo et al., 2019).…”