fig2

Figure 2. Performance comparison of the machine-learning models. (A) Overall comparison based on the training-set R²; Performance of the hybrid model, KRR and GBR for (B) CO₂ conversion, (C) CO yield and (D) H₂ yield. RMSE: Root mean square error; MAE: mean absolute error; MSE: mean squared error; SPXY: sample set partitioning based on joint X-Y distances; GBR: gradient boosting regressor; KRR: kernel ridge regression; RF: random forest; SVR: support vector regression; BPANN: backpropagation artificial neural network; KNN: K-nearest neighbors.