A Novel Stacking Heterogeneous Ensemble Model with Hybrid Wrapper-Based Feature Selection for Reservoir Productivity Predictions

Table 2

Hyperparameter grid.

Model	Parameter	Candidate values
LR	—	—
SVR	C	, , , ,
	Gamma	0.1, 0.2, 0.3, 0.4
	Kernel	RBF, linear
RF	n_estimator	700, 650, 600, 550, 500, 450, 400, 350, 300, 250, 200
	max_features	0.9, 0.8, 0.7, 0.6, 0.5
	max_depth	9, 8, 7, 6, 5, 4, 3
Xgboost	n_estimator	700, 650, 600, 550, 500, 450, 400, 350, 300, 250, 200
	max_depth	9, 8, 7, 6, 5, 4, 3
NN	max_iter	700, 650, 600, 550, 500, 450, 400, 350, 300, 250, 200
	learning_rate	0.001, 0.005, 0.01, 0.02