A Comparison of Feature-Based MLR and PLS Regression Techniques for the Prediction of Three Soil Constituents in a Degraded South African Ecosystem

Table 2

Number of spectral features used and total number of calculated variables for determination of key soil constituents.

	Absorption features; (6 var.)	Curve features; (1 var.)	Hull features; (2 var.)	Total number of variables
𝐶org	2^1	0	2	15
Iron	3	1	1	21
Clay	2	0	2	16

¹For the AF near 1730 nm, only five variables are calculated (see text).