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

<table>Correlation plots and histograms of calibration residues for the prediction of soil organic carbon and iron oxides using the two presented modeling approaches and developed based on bare soil field spectra in HyMap’s spectral resolution of 116 bands. Approach A: multiple linear regression of spectral parameters, approach B: partial least squares regression.</table>

Applied and Environmental Soil Science

fig8

Figure 8

Figure 8: A Comparison of Feature-Based MLR and PLS Regression Techniques for the Prediction of Three Soil Constituents in a Degraded South African Ecosystem 

Figure 8 | A Comparison of Feature-Based MLR and PLS Regression Techniques for the Prediction of Three Soil Constituents in a Degraded South African Ecosystem 