Table 6.

The base models of XGBoost and their evaluations.

XGBoost models	nrounds	Maximum tree depth	Training					Testing
			R2	RMSE	MAE	VAF	Accuracy	R2	RMSE	MAE	VAF	Accuracy
XGBoost1	50	1	0.967	0.803	0.526	96.502	95.315	0.962	0.966	0.645	95.760	95.293
XGBoost2	50	2	0.977	0.650	0.402	97.578	96.828	0.979	0.536	0.680	97.895	96.528
XGBoost3	50	3	0.904	1.395	0.876	90.053	92.825	0.899	1.122	0.848	89.762	93.295
XGBoost4	100	1	0.957	0.896	0.629	95.593	94.562	0.952	0.943	0.723	94.777	95.340
XGBoost5	100	2	0.938	1.112	0.764	93.474	93.579	0.937	1.175	0.805	93.248	94.695
XGBoost6	100	3	0.952	0.923	0.626	95.169	94.595	0.968	0.795	0.651	96.645	95.387
XGBoost7	100	1	0.950	0.990	0.66	94.773	94.442	0.943	0.906	0.679	94.238	94.612
XGBoost8	150	2	0.923	1.182	0.771	92.003	93.397	0.882	1.598	1.241	85.342	92.732
XGBoost9	150	3	0.957	0.973	0.631	94.796	94.741	0.959	1.033	0.723	95.330	93.528
XGBoost10	150	1	0.909	1.367	0.861	90.419	92.900	0.900	0.653	0.791	90.020	94.786
XGBoost11	150	2	0.935	1.160	0.762	93.092	93.567	0.951	1.144	0.461	93.577	91.276
XGBoost12	150	3	0.928	1.219	0.828	92.017	93.046	0.952	0.942	0.814	94.961	94.355
XGBoost13	200	1	0.943	1.059	0.708	94.131	93.913	0.924	0.684	0.644	92.392	95.753
XGBoost14	200	2	0.963	0.812	0.568	96.507	94.978	0.904	1.007	0.85	90.304	94.105
XGBoost15	200	3	0.965	0.811	0.547	96.402	95.117	0.909	0.863	0.795	90.701	94.561