fig6

Figure 6. (A) Predicted hardness of H111 dataset by four best ML-1(H111) models from each descriptor group vs. experimental results (H111). (B) Predicted hardness of H27 dataset by three best ML-1(H111) models from each descriptor group and averaged 40 good ML-1(H111) models vs. experimental results (H27). (C) Predicted hardness of H138 dataset by best ML-2(H138) model vs. experimental results (H138). (D) Predicted hardness of H27 dataset by best ML-2(H138) model SVM_rbf/AD_8 (8th loop) and averaged 40 good ML-2(H138) models vs. experimental results (H27). (E) Predicted hardness of H138 dataset by best ML-2(H138) model SVM_rbf/AD_8 (8th loop) compared with experimental values (H138) and their relative difference. The inset tables show the statistical error analyses of the ML models. ML: Machine learning.