Data Mining and Statistical Approaches in Debris-Flow Susceptibility Modelling Using Airborne LiDAR Data

Abstract

Cameron Highland is a popular tourist hub in the mountainous area of Peninsular Malaysia. Most communities in this area suffer frequent incidence of debris flow, especially during monsoon seasons. Despite the loss of lives and properties recorded annually from debris flow, most studies in the region concentrate on landslides and flood susceptibilities. In this study, debris-flow susceptibility prediction was carried out using two data mining techniques; Multivariate Adaptive Regression Splines (MARS) and Support Vector Regression (SVR) models. The existing inventory of debris-flow events (640 points) were selected for training 70% (448) and validation 30% (192). Twelve conditioning factors namely; elevation, plan-curvature, slope angle, total curvature, slope aspect, Stream Transport Index (STI), profile curvature, roughness index, Stream Catchment Area (SCA), Stream Power Index (SPI), Topographic Wetness Index (TWI) and Topographic Position Index (TPI) were selected from Light Detection and Ranging (LiDAR)-derived Digital Elevation Model (DEM) data. Multi-collinearity was checked using Information Factor, Cramer’s V, and Gini Index to identify the relative importance of conditioning factors. The susceptibility models were produced and categorized into five classes; not-susceptible, low, moderate, high and very-high classes. Models performances were evaluated using success and prediction rates where the area under the curve (AUC) showed a higher performance of MARS (93% and 83%) over SVR (76% and 72%). The result of this study will be important in contingency hazards and risks management plans to reduce the loss of lives and properties in the area.

IoT-Based Geotechnical Monitoring of Unstable Slopes for Landslide Early Warning in the Darjeeling Himalayas

“…Satellite based and ground based networks like synthetic aperture radars (SAR), light detection and ranging (LiDAR), etc. are also used to monitor the slopes in real time [24][25][26][27][28][29]. Multi-interfero-metric techniques like Permanent Scatterer Synthetic Aperture Radar Interferometry (PSInSAR) can be used for ground displacement studies with very high accuracy [30,31].…”

Slope Stability Monitoring Using Novel Remote Sensing Based Fuzzy Logic

“…Moreover, Figure 6 depicts the ROC curves of the used models. Note that plotting this curve is a common way for evaluating the accuracy of prediction for diagnostic problems [45], and shows the specificity versus sensitivity [46,47]. According to this figure, the EHO surpasses other models as it achieved the largest accuracy of prediction (AUROC = 0.758).…”

Development of a data-driven model for spatial and temporal shallow landslide probability of occurrence at catchment scale

“…Table 7 shows the number of models in 100fold bootstrap step that included each predictor. The higher was the number of the models which considered a particular variable; the higher was its significance in influencing the outcomes (Lay et al 2019). Slope angle and land use were selected by all the models in each study area, resulting the parameters that had the Table 6 Range of the rainfall features (3-day and 30-day cumulated rainfall) and of the soil saturation degree at the beginning of an event for the shallow landslides triggering events occurred in Versa-Scuropasso and Ardivestra catchments in 2007-2018 time span Each test-site presented other significant predictors, represented in particular by aspect and topographic position index in Versa-Scuropasso area, and by bedrock geology and catchment area in Ardivestra catchment.…”