Forecasting Deformation Time Series of Surrounding Rock for Tunnel Using Gaussian Process

Abstract

Forecasting deformation of surrounding rock for tunnel is a highly complicated nonlinear problem which is hard to be solved by using conventional methods. A novel method based on Gaussian Process (GP) machine learning is proposed for solving the problem of deformation prediction of surrounding rock for tunnel. GP is a newly developed machine learning method based on the strict statistical learning theory. It has excellent capability for solving the highly nonlinear problem with small samples and high dimension. A GP model for deformation time series prediction of surrounding rock for tunnel is established. The results of a case study show that the model is feasible. It can forecast deformation of surrounding rock for tunnel efficiently and precisely. The results of studies also show that GP are very suitable for solving small samples prediction problems.