Fig. 3: The selection of the best machine learning model.

Distribution of predicted versus measured lg|Z|0.01Hz values from successive test sets used in the 10-fold cross-validation using different machine learning models, a–e correspond to artificial neural network (ANN), linear regression (LR), support vector regression (SVR), decision tree (DT) and random forest (RF) model, respectively. f A comparison of the accuracy for each model, including R2, MAPE, and RMSE values.