Figure4

Figure 4. Performance of machine learning models. The predicted damping capacity is plotted as a function of the measured values. The blue dots represent the training set and the purple dots are for the testing set. (A). Support vector regression with radial basis function kernel (svr.rbf). (B). Random forest regression tree model (rf). (C). Polynomial regression model (poly). (D). Neural network (nnet). (E). Gradient boosting model (gbm). (F). Ensemble learning model of extreme gradient boosting (mxgb). The insets show the mean and standard deviation of the predicted value obtained by the bootstrap resampling method.