Spatial landslide hazard assessment along the Jelapang Corridor of the North-South Expressway in Malaysia using high resolution airborne LiDAR data

Abstract

Mapping landslide-prone regions are crucial in natural hazard management and urban development activities in hilly and tropical regions. This research aimed to delineate a spatial prediction of landslide hazard areas along the Jelapang Corridor of the North-South Expressway in Malaysia by using two statistical models, namely, logistic regression (LR) and evidential belief function (EBF). Landslides result in high economic and social loses in Malaysia, particularly to highway concessionaries such as PLUS Expressways Berhad. LR and EBF determine the correlation between conditioning factors and landslide occurrence. EBF can also be applied in bivariate statistical analysis. Thus, EBF can be used to assess the effect of each class of conditioning factors on landslide occurrence. A landslide inventory map with 26 landslide sites was recorded using field measurements. Subsequently, the landslide inventory was randomly divided into two data sets. Approximately 70 % of the data were used for training the models, and 30 % were used for validating the results. Eight landslide conditioning factors were prepared for landslide susceptibility analysis: altitude, slope, aspect, curvature, stream power index, topographic wetness index, terrain roughness index, and distance from river. The landslide probability index was derived from both methods and subsequently classified into five susceptible classes by using the quantile method. The resultant landslide susceptibility maps were evaluated using the area under the curve technique. Results revealed the proficiency of the LR method in landslide susceptibility mapping. The achieved success and prediction rates for LR were 90 and 88 %, respectively. However, EBF was not successful in providing reasonable accurate results. The acquired success and prediction rates for EBF were 53 and 50 %, respectively. Hence, the LR technique can be utilized in landslide hazard studies for land use management and planning.

Entropy-Based Hybrid Integration of Random Forest and Support Vector Machine for Landslide Susceptibility Analysis

“…The rest of the causative factors, such as curvature, aspect, and lineaments, have a lower influence on the landslide susceptibility of the region. Such a combination of LCF's is seen in similar studies of mountainous regions [5,11,12,36,48,70,81].…”

“…Landslide susceptibility mapping (LSM) is carried out using various statistical models to determine the frequency and probability of a landslide event [24]. Some commonly used models include frequency ratio (FR) [25][26][27], certainty factor (CF) [28][29][30], Shannon entropy (SE) [31][32][33][34], weight of index (WOI) [35,36], and evidential belief function (EBF) [37,38]. The disadvantages of statistical methods include lower predictive potential, simplifying complex relationships, and human interference during feature selection [8,39].…”

Determination of Landslide Slip Plane Using Geology and Geoelectrical Analysis at Mount Geger Pulus Legok Emo Slope Segment, Cililin, West Java

“…Metode pengkajian bahaya longsor dengan skala regional telah dilakukan misalnya oleh Segoni et al (2018) di bagian utara Tuscany, Italia, dengan cara memadukan ambang batas curah hujan dengan peta kerentanan untuk penilaian bahaya longsor yang dinamis; Yusof et al (2015) di sepanjang koridor Jelapang, Jalan Tol Utara -Selatan di Malaysia dengan menggunakan data LiDAR resolusi tinggi dan Kirschbaum et al (2015) di Amerika Tengah dan Hispaniola yang mengintegrasikan peta kerentanan regional dan perkiraan curah hujan berbasis satelit ke dalam binary decision tree (pohon keputusan biner), dengan mempertimbangkan baik curah hujan harian maupun curah hujan pendahuluan.…”

Assessment of Geohazards along Highways Based on the Weights of Evidence and GIS: A Case Study in Guangxi Province, China

“…et al (2015) conducted a sensitivity analysis on the subsidence of karst areas based on the WOE method. Researchers use logistic regression models (Behnia et al 2018, Kim et al 2016, frequency ratio methods (Regmi et al 2016, Yusof et al 2015, the analytic hierarchy process (AHP) method (Lyu et al 2018, Vaani et al 2012, Zhang, He, et al 2018, machine learning method (A.H. Al-Najjar et al 2021, Kai et al 2018) and other models, and select various influencing factors to classify geological disasters such as landslides and collapses, and determine the prone areas.…”