Recurrent neural networks for complicated seismic dynamic response prediction of a slope system

Abstract Earthquake-induced landslides have resulted in huge casualties and considerable financial repercussions, and slope dynamic response analysis has always been a hot issue. The prediction of the dynamic response of a slope before the occurrence of future earthquakes will benefit disaster prevention and reduction. Traditional methods (such as the finite element method) are mostly based on simplified physical mechanisms and cannot accurately predict the dynamic response of complicated slope systems. This article innovatively applies novel recurrent neural networks to the prediction of the slope dynamic response. Using the results of large-scale shaking-table tests, we introduced a moving-steps strategy and established three recurrent neural network models: Simple-RNN, LSTM and GRU models. Moreover, a multi-layer perceptron prediction model was trained for comparative verification. We also conducted three experiments to investigate the effect of the data volume on the models. Results show that recurrent neural networks perform well in the analysis of the seismic dynamic response of a slope and provide better predictions than the multi-layer perceptron network. When there are many data, the LSTM and GRU models have advantages, and the confidence indexes of their predictions with normalized error within ±5% are 84.5% and 86.4%, respectively. It is concluded that recurrent neural networks are suitable for the time-series prediction of dynamic responses to seismic loads. To some extent, this paper may help reduce the future risks and losses of earthquake-triggered landslide disasters.