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

Table 3

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

Model	Method	Transformation	train	test	RPD
SVM	Radial	1° der SG +	0.81	0.87	2.76
SVM	Linear	1° der SG +	0.82	0.84	2.54
SVM	Linear	Det +	0.80	0.83	2.40
RF	800 trees	1° der SG +	0.79	0.79	5.44
RF	800 trees	Det +	0.76	0.76	5.03
RF	800 trees	MSC +	0.75	0.75	5.00