NIR spectroscopy and partial least squares regression for the determination of phosphate content and viscosity behaviour of potato starch

A set of 97 potato starch samples with a phosphate content corresponding to a phosphorus content between 0.029 and 0.11 g per 100 g dry matter was ana lysed using a Rapid Visco Analyzer (RVA) and near infrared (NIR) spectrosco py, (700-2498 nm). NIR-based prediction of phosphate content was possible w ith a root mean square error of cross-validation (RMSECV) of 0.006% using P LSR (partial least squares regression). However, the NIR/PLSR model relied on weak spectral signals, and was highly sensitive to sample preparation. T he best prediction of phosphate content from the RVA viscograms was a linea r regression model based on the RVA variable Breakdown, which gave a RMSECV of 0.008%. NIR/PLSR prediction of the RVA variables Peak viscosity and Bre akdown was successful, probably because they were highly related to phospha te content in the present data. Prediction of the other RVA variables from NIR/PLSR was mediocre (Through, Final Viscosity) or not possible (Setback, Peak time, Pasting temperature).