TABLE 6.

Comparison of the results between different modeling methods.

Modeling method	${\mathrm{R}}_{cv}^2$	Training set		Test set
		${\mathrm{R}}^2$	RMSE	${\mathrm{R}}^2$	RMSE
Linear model	0.60	0.69	0.17	0.79	0.14
MIX-SVR model	0.96	0.97	0.01	0.95	0.01
RBF-SVR model	0.90	0.85	0.08	0.91	0.06
Poly-SVR model	0.87	0.61	0.02	0.79	0.01
Linear-SVR model	0.53	0.20	0.04	0.03	0.07
RF model	0.66	0.86	0.01	0.86	0.01