Estimation of Soil Cohesion Using Machine Learning Method: A Random Forest Approach

Table 2

Hyperparameters of ML methods used in this study.

ML methods	Hyperparameters description
RF	Using TreeBagger MatLab function
	A number of 500 trees
	Minimum leaf size of 5
SVM	Using fitrsvm MatLab function
	Using hyperparameter optimization that minimize 10-fold cross-validation
	The 6 hyperparameters are box constraint, kernel function, kernel scale parameter, polynomial kernel function order, half the width of the epsilon-insensitive band, standardize method for data
ANN	Using fitrrgp MatLab function
	Using hyperparameter optimization that minimizes 10-fold cross-validation
	The 5 hyperparameters are basis function, kernel function, kernel scale, sigma value, standardize method for data