GIS-based evaluation of landslide susceptibility using a novel hybrid computational intelligence model on different mapping units

Abstract

Landslide susceptibility mapping is significant for landslide prevention. Many approaches have been used for landslide susceptibility prediction, however, their performances are unstable. This study constructed a hybrid model, namely box counting dimension-based kernel logistic regression model, which uses fractal dimension calculated by box counting method as input data based on grid cells mapping unit and terrain mapping unit. The performance of this model was evaluated in the application in Zhidan County, Shaanxi Province, China. Firstly, a total of 221 landslides were identified and mapped, and 11 landslide predisposing factors were considered. Secondly, the landslide susceptibility maps (LSMs) of the study area were obtained by constructing the model on two different mapping units. Finally, the results were evaluated with five statistical indexes, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and Accuracy. The statistical indexes of the model obtained on the terrain mapping unit were larger than those based on grid cells mapping unit. For training and validation datasets, the area under the receiver operating characteristic curve (AUC) of the model based on terrain mapping unit were 0.9374 and 0.9527, respectively, indicating that establishing this model on the terrain mapping unit was advantageous in the study area. The results show that the fractal dimension improves the prediction ability of the kernel logistic model. In addition, the terrain mapping unit is a more promising mapping unit in Loess areas.