Multiple Breeds and Countries’ Predictions of Mineral Contents in Milk from Milk Mid-Infrared Spectrometry

• Published in: Foods Vol. 10; no. 9; p. 2235
• Main Authors: Christophe, Octave S., Grelet, Clément, Bertozzi, Carlo, Veselko, Didier, Lecomte, Christophe, Höeckels, Peter, Werner, Andreas, Auer, Franz-Josef, Gengler, Nicolas, Dehareng, Frédéric, Soyeurt, Hélène
• Format: Journal Article Web Resource
• Language: English
• Published: Switzerland MDPI AG 21.09.2021; MDPI
• Subjects: Analytical chemistry; Animal production & animal husbandry; Austria; Calibration; dairy herds; Dairy industry; Datasets; Dietary minerals; Emission analysis; Environmental impact; Food Science; Health (social science); Health Professions (miscellaneous); herd improvement; Hypertension; Inductively coupled plasma; Infrared spectra; Infrared spectroscopy; Lactation; least squares; Life sciences; Microbiology; mid-infrared; Milk; milk composition; Mineral composition; mineral content; Minerals; Plant Science; Potassium; prediction; Predictions; Productions animales & zootechnie; Sciences des denrées alimentaires; Sciences du vivant; Scientific imaging; Sodium; Spectrometry; spectroscopy; Austria; Belgium; France; United States > US; Luxembourg; Germany; milk; minerals; mid-infrared
• ISSN: 2304-8158; 2304-8158
• DOI: 10.3390/foods10092235

Measuring the mineral composition of milk is of major interest in the dairy sector. This study aims to develop and validate robust multi-breed and multi-country models predicting the major minerals through milk mid-infrared spectrometry using partial least square regressions. A total of 1281 samples coming from five countries were analyzed to obtain spectra and in ICP-AES to measure the mineral reference contents. Models were built from records coming from four countries (n = 1181) and validated using records from the fifth country, Austria (n = 100). The importance of including local samples was tested by integrating 30 Austrian samples in the model while validating with the remaining 70 samples. The best performances were achieved using this second set of models, confirming the need to cover the spectral variability of a country before making a prediction. Validation root mean square errors were 54.56, 63.60, 7.30, 59.87, and 152.89 mg/kg for Na, Ca, Mg, P, and K, respectively. The built models were applied on the Walloon milk recording large-scale spectral database, including 3,510,077. The large-scale predictions on this dairy herd improvement database provide new insight regarding the minerals’ variability in the population, as well as the effect of parity, stage of lactation, breeds, and seasons.