Prediction of Landslide Displacement by the Novel Coupling Method of HP Filtering Method and Extreme Gradient Boosting

Rainfall and change in reservoir water levels often lead to landslides, threatening the lives and properties of people in neighboring areas. Therefore, it is necessary to predict the landslide displacement. This paper proposes a novel coupling method of extreme gradient boosting (XGBoost) and Hodrick–Prescott (HP) filtering method to predict the landslide displacement. First, the HP filtering method is used to decompose the total landslide displacement into trend displacement and periodic displacement. The trend displacement is affected by the potential energy of landslide and the boundary constraints, and it is predicted by using the least square polynomial function. Rainfall and reservoir water level fluctuation are the main factors affecting the periodic displacement, and the extreme gradient boosting is used to predict the periodic displacement. The total displacement is obtained by adding the predicted trend displacement and the predicted periodic displacement. The Bazimen and Baishuihe landslides are taken as an example to verify the ability of this proposed model. Compared with other prediction methods (back propagation neural network (BP-NN), support vector machine regression (SVR)), this proposed method has the higher accuracy. Therefore, the proposed method can effectively predict the displacement of landslides.