Abstract:Landslide is a common geological disaster, which usually evolves and occurs under complex geological conditions and brings great damage to the safety of human life and property. The understanding of the development of landslides is important for the prevention and control of disasters. Based on the field time series data of landslide cumulative displacement, a landslide displacement prediction method based on Genetic Simulated Annealing algorithm is proposed. The Genetic Simulated Annealing algorithm BP neural network is used to analyze the observation point Z118 in Baishui River landslide warning area, the cumulative displacement of the first three months is applied to predict the accumulated displacement of the fourth month. The results of BP neural network model and Elman neural network model are compared. At the same time, the prediction results of Genetic Simulated Annealing algorithm and Support Vector Machine are compared. The results show that the landslide displacement prediction model established in this article can effectively improve the prediction accuracy, and provide a reference for landslide displacement prediction in engineering construction.