Table 9 Comparative analysis with prior studies.
Reference | Models | Key features | R2 |
|---|---|---|---|
Ensemble | Â | 0.83 | |
RF | Â | 0.81 | |
Multi-layer perceptron ANN | Â | 0.76 | |
SVR | Â | 0.47 | |
Gaussian process regression | Â | 0.47 | |
Linear regression | Â | 0.46 | |
Gradient boosting | Â | 0.81 | |
K-nearest neighbors | Â | 0.68 | |
| Â | SHAP | Â | |
Ensemble | Â | 0.95 | |
Multi-layer perceptron | Â | 0.46 | |
XGBoost | Â | 0.78 | |
Gradient Boosting | Â | 0.80 | |
RF | Â | 0.80 | |
DT | Â | 0.76 | |
SVR | Â | 0.71 | |
Linear regression | Â | 0.36 | |
CG-BP ANN | Â | 0.91 | |
Present study | Â | SHAP and PDP | Â |
Python GUI for immediate predictions | |||
SVR-GWO | Â | 0.96 | |
SVR-GTO | Â | 0.95 | |
ANN-GWO | Â | 0.92 | |
ANN-GTO | Â | 0.90 |