Development of a data-driven model to predict landslide sensitive areas

Abstract

The occurrence of landslides has always been a problem in spatial planning as one of the environmental threats. The aim of the present study is to estimate the landslide sensitive areas in the Urmia Lake basin based on determining effective criteria and spatial and non-spatial data-driven models. The criteria used in this research include distance to faults, distance to roads, distance to hydrology network, land use, lithology, soil classes, Elevation, slope, aspect and Precipitation. The novelty of this study is to present new combination approaches to determine the effective criteria in landslide sensitive areas (Urmia Lake basin). In this regard, the geographically weighted regression (GWR) with exponential and bi-square kernels and artificial neural network (ANN) combined with a binary particle swarm optimization algorithm (BPSO). The best value of the fitness function (1-R2) for ANN, GWR with the exponential kernel, and GWR with bi-square kernel was obtained 0.2780, 0.07453, and 0.0022, respectively, Which indicates higher compatibility of the bi-square kernel than the other models. It was also found that the criteria used have a significant effect on the landslide sensitive zoning.