Abstract
In this manuscript 170 slopes are analyzed utilizing an artificial intelligence approach. Five neural network architectures including the back propagation neural network architecture, general regression neural network, group method of data handling, Kohonen learning paradigm and probabilistic neural network architectures are used. The back propagation neural network architecture and the general regression neural network demonstrated better applicability to the slope stability problem. Nine input parameters and one output parameter are used in the analysis. The output parameter is the factor of the safety of the slopes, the input parameters are the height of slope, the inclination of slope, the height of water level, the depth of firm base, the cohesion of soil, the friction angle of soil, the unit weight of soil, but the important input parameters are horizontal and vertical seismic coefficients. The importance of the seismic coefficients for a slope stability safety is presented. A sensitivity study is performed to assess the importance of the slope and dynamic input parameters.