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.
Highlights
Rapid population growth and its increasing concentration in urban areas have worsened the severity and impact of gravity-induced disasters across the globe, in the mountainous environment
The quantitative model prediction index from the pixel values was classified into five classes using natural break classification scheme (0.005–0.155, 0.156–0.305, 0.306–0.455, 0.456–0.605, 0.606–0.776), this index received threshold digital number between 0 and 1 which signifies the possibility of debris flow pixel value in the catchment area
This research demonstrated the use of laser scanning technology with Multivariate Adaptive Regression Splines (MARS) and Regression Support vector machine (R-Support Vector Machine (SVM)) to develop models for the prediction of an area susceptible to debris flow, in the Ringlet region of the Cameron Highlands, which is affected by recurrent mass-movement related natural disasters
Summary
Rapid population growth and its increasing concentration in urban areas have worsened the severity and impact of gravity-induced disasters across the globe, in the mountainous environment. If solid sediment controls the liquid content, the constituent formed is avalanche; whereas if liquid forces control the solid content that results in floods, on the other hand, when an equal concert of liquid and solid presents it is formed as debris flows [3]. This forms a discern transition between avalanches and floods, based on their geological type and mechanical conduct characteristic [2]. A study by Berti et al [14] estimated the reoccurrence periods for moderate debris flows to be a single occurrence in every two to three years interlude
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
