Skip to main content

View full-text article in PMC

. 2023 Jan 30;13:1666. doi: 10.1038/s41598-023-28770-2

Table 5.

Performance of the XGBoost model in comparison with the DTs model.

	Models	Train			Test			Overall
	Models	RMSE (Pa.s.)	R²	AARD (%)	RMSE (Pa.s.)	R²	AARD (%)	RMSE (Pa.s.)	R²	AARD (%)
Under saturated	XGBoost^a	4.038E−5	0.999	0.576	4.830E−5	0.999	1.194	4.198E−5	0.999	0.699
Under saturated	DTs	NR	NR	NR	NR	NR	NR	1.000E−4	0.999	2.255
Saturated	XGBoost^a	2.956E−5	0.998	2.058	8.305E−5	0.981	5.416	4.026E−50	0.994	2.730
Saturated	DTs^b	NR	NR	NR	NR	NR	NR	1.000E−4	0.996	4.485
Dead oil	XGBoost^a	6.320E−4	0.928	7.018	7.481E−4	0.867	12.542	4.315E−4	0.931	7.982
Dead oil	DTs^b	NR	NR	NR	NR	NR	NR	4.000E−5	0.992	6.524
All data	XGBoost^a	2.525E−5	0.998	1.212	5.437E−5	0.992	2.728	3.107E−5	0.997	1.515
All data	DTs^b	1.000E−4	0.997	2.688	1.000E−4	0.994	6.148	1.000E−4	0.997	3.379

^aXGBoost model (This Study).

^bDTs model²⁰.

NR Not Reported.