Classification of surrounding rocks in tunnel based on Gaussian process machine learning

Classification of surrounding rocks in tunnel is very important for design and construction. Aiming to the fact that it is still difficult to reasonably determine the classification of surrounding rocks in tunnel, the model based on Gaussian process machine learning is proposed for classifying surrounding rocks. With the help of simple learning process, the uncertain mapping relationship between classification of surrounding rocks and its influencing factors is established by Gaussian process for binary classification model. The model is applied to a real engineering. The results of case study show that Gaussian process for binary classification model is feasible and has the same results with artificial neural networks and support vector machine. Nevertheless, compared with artificial neural networks and support vector machine, it has attractive merit of self-adaptive parameters determination.