Landslide Displacement Prediction Based on Variational Mode Decomposition and LSTM

Landslide displacement prediction is a challenging task. In this paper, a hybrid model based on Variational Mode Decomposition (VMD) and Long Short-Term Memory neural network (LSTM) is proposed to predict landslide displacement. The VMD method is used to decompose the cumulative displacement data of landslides and the time series of environmental impact factors (reservoir water level, rainfall), and then use the LSTM model for prediction. Take the Baishuihe landslide ZG93 and ZG118 as examples to verify the performance of the model. The results indicate that the VMD-LSTM model shows higher accuracy than other models and has potential for application in landslide displacement prediction.