Table 2.

Selected hyperparameter values for each model.

Parameters		Values Tested	Selected Value per Model
			Classification			Regression
			Low–Medium	Low–High	Low–Medium–High	Spectra	Spectra & Ambient
XGBoost	Number of trees	100, 300, 800, 1000	800	1000	1000	1000	1000
	Eta (learning rate)	0.1, 0.01	0.1	0.1	0.1	0.01	0.01
	Tree depth	2, 4, 6, 8, 10, 12	12	8	8	8	8
	L1	0.00001, 0.01, 0, 0.1, 1, 100	0.00001	0.00001	0.00001	0	0.01
	L2	0.00001, 0.01, 0, 0.1, 1, 100	0.00001	0.01	0.00001	0	0.1
	Percent of features	0.3, 0.5, 0.8	0.5	0.5	0.5	0.3	0.3
SVM	C	0.1, 1, 10, 100	100	100	100
	γ	1, 0.1, 0.01, 0.001	1	1	1