GIS-Based Expert Knowledge for Landslide Susceptibility Mapping (LSM): Case of Mostaganem Coast District, West of Algeria

Abstract

Landslides are one of the natural disasters that affect socioeconomic wellbeing. Accordingly, this work aimed to realize a landslide susceptibility map in the coastal district of Mostaganem (Western Algeria). For this purpose, we applied a knowledge-driven approach and the Analytical Hierarchy Process (AHP) in a Geographical Information System (GIS) environment. We combined landslide-controlling parameters, such as lithology, slope, aspect, land use, curvature plan, rainfall, and distance to stream and to fault, using two GIS tools: the Raster calculator and the Weighted Overlay Method (WOM). Locations with elevated landslide susceptibility were close the urban nucleus and to a national road (RN11); in both sites, we registered the presence of strong water streams. The quality of the modeled maps has been verified using the ground truth landslide map and the Area Under Curve (AUC) of the Receiver Operating Characteristic curve (ROC). The study results confirmed the excellent reliability of the produced maps. In this regard, validation based on the ROC indicates an accuracy of 0.686 for the map produced using a knowledge-driven approach. The map produced using the AHP combined with the WOM showed high accuracy (0.753).

Evaluating the Effect of Root Cohesion on Shallow Landslides for Physically Based Modeling

“…(53) Many researchers have also used ROC analysis to categorize risk classes for landslide hazard maps. (33,38,46,47) In this study, the cut-off point of the Youden index was determined to be higher than the actual generated daily rainfall, which appeared to be due to a limitation of this method in determining the positive discriminant standard and the optimal likelihood. In addition, the importance of preceding precipitation may need to be considered because, in the SHALSTAB model, it is evaluated from the daily rainfall rather than the cumulative rainfall.…”

“…The accuracy evaluation of landslide prediction analysis is very important. Many researchers (1,4,33,46,47) have calculated the reliability of their models using ROC analysis. In this study, the prediction accuracy was evaluated using ROC analysis as follows: if an unstable grid cell was coincident with a landslide, it was counted as a true positive; if an unstable grid cell fell outside a landslide point, it was counted as a false positive; if a stable grid cell was coincident with a non-landslide point, it was counted as a true negative; if a stable grid cell fell outside a non-landslide point, it was counted as a false negative.…”

GIS-Based Soft Computing Models for Landslide Susceptibility Mapping: A Case Study of Pithoragarh District, Uttarakhand State, India

“…In addition, Naïve Bayes (NB), Multilayer Perceptron (MLP) neural network classifier, and Alternating Decision Tree (ADT) are widely employed algorithms to investigate landslide susceptibility [39][40][41]. Recently, Senouci et al [42] deployed a knowledgedriven approach alongside Analytical Hierarchy Process (AHP) in a GIS-based environment to evaluate the landslide susceptibility map in Algeria. Hong et al [41] evaluated twoclass Kernel Logistic Regression (KLR), SVM, and ADT for landslide susceptibility mapping at the Yihuang area (China).…”

Performance Evaluation of Five GIS-Based Models for Landslide Susceptibility Prediction and Mapping: A Case Study of Kaiyang County, China

“…In the past few decades, many prediction models have been developed to map the sensitivity of landslides. The main evaluation methods include the empirical model (fuzzy logic [13][14][15], analytic hierarchy process [16][17][18][19][20][21], etc. ), statistical analysis model (weights of evidence [22][23][24][25], frequency ratio [19,[26][27][28][29], certainty factor (CF) [18,19,30], information value model [31,32], etc.…”