Application and Comparison of Machine Learning Algorithms for Predicting Rock Deformation in Hydraulic Tunnels

Table 2

Model hyperparameters.

Model	Hyperparameters
LSTM	input_size = 1; time_step = 6; batch_size = 1;
	num_layer = 2; hidden_size = 64; learn_rate = 0.002
	drop_out = 0.2; optimization:Adam;
	Activation function:tanh
GPR	kernel = kernel1, n_restarts_optimizer = 100, alpha = 0.0029, random_state = 42
SVR	kernel = “rbf”, C = 100, gamma = 0.1, epsilon = 0.0019