Research on Landslide Displacement Prediction Based on DES-CGSSA-BP Model

A landslide is a type of natural disaster that has the highest frequency, widest distribution and heaviest losses worldwide; landslides seriously threaten human life property major engineering facilities. Therefore, it important to improve displacement prediction technology avoid mitigate disasters. method based on chaotic Gaussian mutation sparrow search algorithm-optimised BP neural network (CG-SSA-BP) proposed address problems traditional algorithm (SSA)-optimised (SSA-BP) network; tends fall into local optima, slow convergence low accuracy for prediction. This paper takes Baishui River in Three Gorges reservoir area as research object, double exponential smoothing (DES) used decompose trend term periodic solve nonlinear system problem. The results show model CG-SSA-BP better stability compared with SSA-BP.