Fig. 5
The characterization of PLSR models for chemical composition. a Principal components selection of PLSR models for explaining the NIRS variance. b Predictive performance of PLSR models for chemical composition. CARS competitive adaptive reweighted sampling, RF random frog, R2C coefficient determination of calibration, R2CV coefficient determination of cross-validations, R2V coefficient determination of validations, RMSEC root mean standard error of calibration, RMSECV root mean standard error of cross-validation, RMSEP root mean square error of prediction, RPD the ratio of performance to deviation, RER the range error ratio