Combining spatial data in landslide reactivation susceptibility mapping: A likelihood ratio-based approach in W Belgium

A key issue in landslide susceptibility mapping concerns the relevance of the spatial data combination used in the prediction. Various combinations of high-resolution predictor variables and possibilities of selecting them from a larger dataset are analysed. The scarp reactivation of several landslides in a hilly region of W Belgium is investigated at the pixel scale. The susceptibility modelling uses the reactivated scarp segments as the dependent variable and 13 factors at a 2 m-resolution related to topography, hydrology, land use and lithology as potential independent variables. The modelling uses a likelihood ratio approach based on the comparison, for each independent variable, between two empirical distribution functions (EDFs), respectively for the reactivated and non-reactivated areas. It uses these EDFs as favourability values to build membership values and combine them with a fuzzy Gamma operator. Five different data combinations are tested and compared by analysing the prediction-rate curves obtained by cross-validation. The geomorphological value of the resulting susceptibility maps is also discussed. This research shows relevant results for predicting the susceptibility to scarp reactivation. We highlight the need for testing several data combinations and underline that combining quantitative criteria with expert opinion is an asset for reliable predictions.