Standardization of milk mid-infrared spectrometers for the transfer and use of multiple models

Abstract

An increasing number of models are being developed to provide information from milk Fourier transform mid-infrared (FT-MIR) spectra on fine milk composition, technological properties of milk, or even cows' physiological status. In this context, and to take advantage of these existing models, the purpose of this work was to evaluate whether a spectral standardization method can enable the use of multiple equations within a network of different FT-MIR spectrometers. The piecewise direct standardization method was used, matching "slave" instruments to a common reference, the "master." The effect of standardization on network reproducibility was assessed on 66 instruments from 3 different brands by comparing the spectral variability of the slaves and the master with and without standardization. With standardization, the global Mahalanobis distance from the slave spectra to the master spectra was reduced on average from 2,655.9 to 14.3, representing a significant reduction of noninformative spectral variability. The transfer of models from instrument to instrument was tested using 3 FT-MIR models predicting (1) the quantity of daily methane emitted by dairy cows, (2) the concentration of polyunsaturated fatty acids in milk, and (3) the fresh cheese yield. The differences, in terms of root mean squared error, between master predictions and slave predictions were reduced after standardization on average from 103 to 17 g/d, from 0.0315 to 0.0045 g/100 mL of milk, and from 2.55 to 0.49 g of curd/100 g of milk, respectively. For all the models, standard deviations of predictions among all the instruments were also reduced by 5.11 times for methane, 5.01 times for polyunsaturated fatty acids, and 7.05 times for fresh cheese yield, showing an improvement of prediction reproducibility within the network. Regarding the results obtained, spectral standardization allows the transfer and use of multiple models on all instruments as well as the improvement of spectral and prediction reproducibility within the network. The method makes the models universal, thereby offering opportunities for data exchange and the creation and use of common robust models at an international level to provide more information to the dairy sector from direct analysis of milk.

Strategies for noise reduction and standardization of milk mid-infrared spectra from dairy cattle

“…These RMSE values equate to a reduction of 73% for fat, 81% for protein, and 82% for lactose. These reductions in RMSE were similar to those presented by Grelet et al (2017) for methane emissions (83%), polyunsaturated fatty acids (86%), and cheese yield (81%).…”

“…The effectiveness of standardization for reducing prediction errors when transferring calibration models between instruments for fat composition traits has been demonstrated previously (Grelet et al, 2015;Bonfatti et al, 2017a). Grelet et al (2017) also demonstrated the effectiveness of standardization for reducing prediction errors for traits with lower quality calibration models such as methane emissions and cheese yield.…”

“…In doing so, other non-instrument errors and bias were introduced. The risk of correcting for noninstrument factors such as breed and feed when using a retroactive approach was also signaled by Grelet et al (2017). In the present study, we were able to resolve this by partitioning spectra into subsets and applying standardization within month and with a separate primary instrument assigned for each of the North and South Islands.…”

Diagnosing the pregnancy status of dairy cows: How useful is milk mid-infrared spectroscopy?

“…These 538 wavenumbers were in the regions from 928 to 1,596 cm −1 and from 1,693 to 3,025 cm −1 . Subsequently, potential spectral outliers were excluded by calculating the standardized Mahalanobis distance or global distance, and records with global distance >3 were eliminated (De Maesschalck et al, 2000;Grelet et al, 2017). The data were also checked for unusual milk fat and protein contents (i.e., 1.5 g/dL of milk < fat < 9 g/dL of milk, 1 g/dL of milk < protein < 7 g/dL of milk) and SCC (0.01% upper values were deleted) following the recommendation of the International Committee for Animal Recording (ICAR, 2017b).…”

Short communication: Development of an equation for estimating methane emissions of dairy cows from milk Fourier transform mid-infrared spectra by using reference data obtained exclusively from respiration chambers

“…To avoid any instrument interference and ensure that the milk FT-MIR spectra are comparable regardless of the spectrometer used and the date of analysis, the milk FT-MIR spectra were standardized according to the procedure described in Grelet et al (2017). A first derivative was applied to the milk FT-MIR spectra as recommended by Soyeurt et al (2011).…”