Skip to main content

TableĀ 1 Summary statistics for PLSR calibration models for chemical components

From: An NIRS-based assay of chemical composition and biomass digestibility for rapid selection of Jerusalem artichoke clones

Parameter N Full spectra CARS-optimized spectra RF-optimized spectra
RMSEC R 2 C RMSECV R 2 CV RMSEC R 2 C RMSECV R 2 CV RMSEC R 2 C RMSECV R 2 CV
Soluble sugars 40 2.14 0.90 2.78 0.81 0.88 0.95 1.98 0.91 1.63 0.95 2.07 0.90
Cellulose 45 0.70 0.93 0.96 0.86 0.47 0.96 0.71 0.93 0.74 0.94 0.89 0.89
Hemicellulose 45 0.20 0.96 0.46 0.93 0.27 0.97 0.41 0.95 0.24 0.98 0.32 0.97
Lignin 45 0.48 0.88 0.87 0.77 0.49 0.92 0.71 0.85 0.42 0.95 0.56 0.92
Ash 45 0.29 0.79 0.44 0.63 0.27 0.85 0.38 0.72 0.23 0.92 0.27 0.86
  1. N number of samples, CARS competitive adaptive reweighted sampling, RF random frog, RMSEC root mean standard error of calibration, R2C coefficient determination of calibration, RMSECV root mean standard error of cross-validation, R2CV coefficient determination of cross-validation