Use of Machine Learning Models for Prediction of Organic Carbon and Nitrogen in Soil from Hyperspectral Imagery in Laboratory

Table 2

Results of adjustment factors for the SVM and RF models for the soil OC variable.

Model	Method	Transformation	train	test	RPD
SVM	Radial	1° der SG +	0.87	0.92	3.56
SVM	Radial	Det +	0.85	0.90	3.23
SVM	Linear	1° der SG +	0.88	0.90	3.13
RF	800 trees	1° der SG +	0.87	0.87	6.74
RF	800 trees	MSC +	0.82	0.82	5.95
RF	800 trees	Det +	0.83	0.83	5.94