Landslide displacement prediction based on CEEMDAN and grey wolf optimized-support vector regression model

Landslide prediction is very important and challenging for reducing geological hazards. In the Three Gorges Reservoir area, landslides show stepped deformation due to seasonal rainfall periodic fluctuation of reservoir water level. The purpose this study use complete ensemble empirical mode decomposition with adaptive noise grey wolf optimization support vector regression method displacement prediction. Firstly, cumulative decomposed by CEEMDAN obtain both trend term displacement. Secondly, according displacement, rainfall, level data, influencing factors related are determined. Then, GWO-SVR model used predict final result obtained adding calculated predicted values each component. Shuizhuyuan landslide in China, was taken as an example, long-term data monitoring point SZY-03 were selected analysis. results that root mean square error (RMSE) coefficient determination ( R 2 ) between measured 0.9845 0.9964, respectively. trained has high computational accuracy, which proves can be type area.