The use of milk Fourier-Transform Infrared spectra for predicting cheese-making traits in Grana Padano PDO

: The prediction of the cheese yield (%CY) traits for curd, solids, and retained water and the amount of fat, protein, solids and energy recovered from the milk into the curd (%REC) by Bayesian models, using Fourier-transform infrared spectroscopy (FTIR), can be of significant economic interest to the dairy industry and can contribute to the improvement of the cheese process efficiency. The yields give a quantitative measure of the ratio between weights of the input and output of the process, whereas the nutrient recovery allows to assess the quantitative transfer of a component from milk to cheese (expressed in % of the initial weight). The aims of this study were to: i) investigate the feasibility of using bulk milk spectra to predict %CY and %REC traits, ii) quantify the effect of the dairy industry and the contribution of single spectrum wavelengths on the prediction accuracy of these traits using vat milk samples destined to the production of Grana Padano Protected Designation of Origin (PDO) cheese. Information from 72 cheese-making days (in total 216 vats) from 3 dairy industries were collected. For each vat, the milk was weighed and analyzed for composition (total solids, lactose, protein, and fat). After 48h from cheese making, each cheese was weighted, and the resulting whey was sampled for composition as well (total solids, lactose, protein and fat). Two spectra from each milk sample were collected in the range between 5,011 and 925 cm-1 and averaged before the data analysis. The calibration models were developed via a Bayesian approach by using the BGLR (Bayesian Generalized Linear Regression) package of R software. The performance of the models was assessed by the coefficient of determination (R2VAL) and the root mean squared error (RMSEVAL) of validation. Random cross-validation (CV) was applied [80% calibration (CAL) and 20% validation (VAL) set] with 10 replicates. Then, a Stratified Cross Validation (SCV) was performed to assess the effect of the dairy industry on prediction accuracy. The study was repeated using a selection of informative wavelengths to assess the necessity of using whole spectra to optimize prediction accuracy. Results showed the feasibility of using FTIR spectra and Bayesian models to predict cheese-making traits. The R2VAL values obtained with the CV procedure were promising in particular for the CY and %REC for protein, ranging from 0.44 to 0.66 with very low RMSEVAL (from 0.16 to 0.53). Prediction accuracy obtained with the SCV was strongly influenced by the dairy factory industry. The general low values gained with the SCV do not permit a practical application of this approach, but they highlight the importance of building calibration models with a data set covering the largest possible sample variability. This study also demonstrated that the use of the full FTIR spectra may be redundant for the prediction of the cheese-making traits and that a specific selection of the most informative wavelengths led to improved prediction accuracy. This could lead to the development of dedicated spectrometers using selected wavelengths with built-in calibrations for the on-line prediction of these innovative traits.