Mid-infrared spectrometry of milk as a predictor of energy intake and efficiency in lactating dairy cows

Interest is increasing in the feed intake complex of individual dairy cows, both for management and animal breeding. However, energy intake data on an individual-cow basis are not routinely available. The objective of the present study was to quantify the ability of routinely undertaken mid-infrared (MIR) spectroscopy analysis of individual cow milk samples to predict individual cow energy intake and efficiency. Feed efficiency in the present study was described by residual feed intake (RFI), which is the difference between actual energy intake and energy used (e.g., milk production, maintenance, and body tissue anabolism) or supplied from body tissue mobilization. A total of 1,535 records for energy intake, RFI, and milk MIR spectral data were available from an Irish research herd across 36 different test days from 535 lactations on 378 cows. Partial least squares regression analyses were used to relate the milk MIR spectral data to either energy intake or efficiency. The coefficient of correlation (R_EX) of models to predict RFI across lactation ranged from 0.48 to 0.60 in an external validation data set; the predictive ability was, however, strongest (R_EX = 0.65) in early lactation (<60 d in milk). The inclusion of milk yield as a predictor variable improved the accuracy of predicting energy intake across lactation (R_EX = 0.70). The correlation between measured RFI and measured energy balance across lactation was 0.85, whereas the correlation between RFI and energy balance, both predicted from the MIR spectrum, was 0.65. Milk MIR spectral data are routinely generated for individual cows throughout lactation and, therefore, the prediction equations developed in the present study can be immediately (and retrospectively where MIR spectral data have been stored) applied to predict energy intake and efficiency to aid in management and breeding decisions.     

The use of mid-infrared spectrometry to predict body energy status of Holstein cows

Energy balance, especially in early lactation, is known to be associated with subsequent health and fertility in dairy cows. However, its inclusion in routine management decisions or breeding programs is hindered by the lack of quick, easy, and inexpensive measures of energy balance. The objective of this study was to evaluate the potential of mid-infrared (MIR) analysis of milk, routinely available from all milk samples taken as part of large-scale milk recording and milk payment operations, to predict body energy status and related traits in lactating dairy cows. The body energy status traits investigated included energy balance and body energy content. The related traits of body condition score and energy intake were also considered. Measurements on these traits along with milk MIR spectral data were available on 17 different test days from 268 cows (418 lactations) and were used to develop the prediction equations using partial least squares regression. Predictions were externally validated on different independent subsets of the data and the results averaged. The average accuracy of predicting body energy status from MIR spectral data was as high as 75% when energy balance was measured across lactation. These predictions of body energy status were considerably more accurate than predictions obtained from the sometimes proposed fat-to-protein ratio in milk. It is not known whether the prediction generated from MIR data are a better reflection of the true (unknown) energy status than the actual energy status measures used in this study. However, results indicate that the approach described may be a viable method of predicting individual cow energy status for a large scale of application.     

Application of machine-learning methods to milk mid-infrared spectra for discrimination of cow milk from pasture or total mixed ration diets

The prevalence of “grass-fed” labeled food products on the market has increased in recent years, often commanding a premium price. To date, the majority of methods used for the authentication of grass-fed source products are driven by auditing and inspection of farm records. As such, the ability to verify grass-fed source claims to ensure consumer confidence will be important in the future. Mid-infrared (MIR) spectroscopy is widely used in the dairy industry as a rapid method for the routine monitoring of individual herd milk composition and quality. Further harnessing the data from individual spectra offers a promising and readily implementable strategy to authenticate the milk source at both farm and processor levels. Herein, a comprehensive comparison of the robustness, specificity, and accuracy of 11 machine-learning statistical analysis methods were tested for the discrimination of grass-fed versus non-grass-fed milks based on the MIR spectra of 4,320 milk samples collected from cows on pasture or indoor total mixed ration–based feeding systems over a 3-yr period. Linear discriminant analysis and partial least squares discriminant analysis (PLS-DA) were demonstrated to offer the greatest level of accuracy for the prediction of cow diet from MIR spectra. Parsimonious strategies for the selection of the most discriminating wavelengths within the spectra are also highlighted.     

Bayesian estimation of sensitivity and specificity of a milk pregnancy-associated glycoprotein ELISA test for pregnancy diagnosis between 23 and 27 days after insemination in Holstein dairy cows

Pregnancy diagnosis using pregnancy-associated glycoprotein (PAG) ELISA technology in blood or milk samples is validated from 28 d after insemination in dairy cows. The objective of this study was to estimate the sensitivity (Se) and specificity (Sp) of a commercial milk PAG-based ELISA in Holstein dairy cows between 23 and 27 d after insemination. Milk samples (n = 268) from 257 Holstein dairy cows 23 to 27 d after AI were submitted for PAG ELISA testing. Pregnancy status was confirmed by either a second milk PAG ELISA test conducted between 28 and 50 d after insemination (n = 200) or transrectal ultrasonography performed between 28 and 59 d after insemination (n = 68). A Bayesian latent class model was used to compare the paired results from the test at 23 to 27 d after AI test to the reference test. The latent class model typically used for comparing 2 or more imperfect tests was extended to include the possibility of pregnancy loss between the 23 to 27 d test and the reference test. Informative priors for the probability of pregnancy loss, and for the Se and Sp of the PAG and ultrasonography reference tests were obtained from the scientific literature. Estimated median Se and Sp of the PAG ELISA test conducted between 23 and 27 d after AI were 0.98 (95% credible interval 0.93 to 1.0) and 0.98 (0.89 to 1.0), respectively, when using a standardized corrected optical density threshold of 0.15. Although the accuracy of the test under investigation was excellent, more data will be needed to confirm the optimal diagnostic cut point for PAG in milk for early pregnancy diagnosis in this time window. The optimal timing of pregnancy diagnosis will depend on herd-specific logistics and the action to be taken to re-inseminate nonpregnant cows.     

Milk mid-infrared spectral data as a tool to predict feed intake in lactating Norwegian Red dairy cows

Mid-infrared (MIR) spectroscopy of milk was used to predict dry matter intake (DMI) and net energy intake (NEI) in 160 lactating Norwegian Red dairy cows. A total of 857 observations were used in leave-one-out cross-validation and external validation to develop and validate prediction equations using 5 different models. Predictions were performed using (multiple) linear regression, partial least squares (PLS) regression, or best linear unbiased prediction (BLUP) methods. Linear regression was implemented using just milk yield (MY) or fat, protein, and lactose concentration in milk (Mcont) or using MY together with body weight (BW) as predictors of intake. The PLS and BLUP methods were implemented using just the MIR spectral information or using the MIR together with Mcont, MY, BW, or NEI from concentrate (NEIconc). When using BLUP, the MIR spectral wavelengths were always treated as random effects, whereas Mcont, MY, BW, and NEIconc were considered to be fixed effects. Accuracy of prediction (R) was defined as the correlation between the predicted and observed feed intake test-day records. When using the linear regression method, the greatest R of predicting DMI (0.54) and NEI (0.60) in the external validation was achieved when the model included both MY and BW. When using PLS, the greatest R of predicting DMI (0.54) and NEI (0.65) in the external validation data set was achieved when using both BW and MY as predictors in combination with the MIR spectra. When using BLUP, the greatest R of predicting DMI (0.54) in the external validation was when using MY together with the MIR spectra. The greatest R of predicting NEI (0.65) in the external validation using BLUP was achieved when the model included both BW and MY in combination with the MIR spectra or when the model included both NEIconc and MY in combination with MIR spectra. However, although the linear regression coefficients of actual on predicted values for DMI and NEI were not different from unity when using PLS, they were less than unity for some of the models developed using BLUP. This study shows that MIR spectral data can be used to predict NEI as a measure of feed intake in Norwegian Red dairy cattle and that the accuracy is augmented if additional, often available data are also included in the prediction model.     

Energy profiling of dairy cows from routine milk mid-infrared analysis

The balance of body energy within and across lactations can have health and fertility consequences for the dairy cow. This study aimed to create a large calibration data set of dairy cow body energy traits across the cow's productive life, with concurrent milk mid-infrared (MIR) spectral data, to generate a prediction tool for use in commercial dairy herds. Detailed phenotypic data from 1,101 Holstein Friesian cows from the Langhill research herd (SRUC, Scotland) were used to generate energy balance (EB) and effective energy intake (EI), both in megajoules per day. Pretreatment of spectral data involved standardization to account for drift over time and machine. Body energy estimates were aligned with their spectral data to generate a prediction of these traits based on milk MIR spectroscopy. After data edits, partial least squares analysis generated prediction equations with a coefficient of determination from split sample 10-fold cross validation of 0.77 and 0.75 for EB and EI, respectively. These prediction equations were applied to national milk MIR spectra on over 11 million animal test dates (January 2013 to December 2016) from 4,453 farms. The predictions generated from these were subject to phenotypic analyses with a fixed regression model highlighting differences between the main dairy breeds in terms of energy traits. Genetic analyses generated heritability estimates for EB and EI ranging from 0.12 to 0.17 and 0.13 to 0.15, respectively. This study shows that MIR-based predictions from routinely collected national data can be used to generate predictions of dairy cow energy turnover profiles for both animal management and genetic improvement of such difficult and expensive-to-record traits.     

Phenotypic and genetic characterization of the occurrence of noncoagulating milk in dairy sheep

Milk coagulation ability is of central importance for the sheep dairy industry because almost all sheep milk is destined for cheese processing. The occurrence of milk with impaired coagulation properties is an obstacle to cheese processing and, in turn, to the profitability of the dairy companies. In this work, we investigated the causes of noncoagulation of sheep milk; specifically, we studied the effect of milk physicochemical properties on milk coagulation status [coagulating and noncoagulating (NC) milk samples, which do or do not coagulate within 30 min, respectively], and whether mid-infrared spectroscopy (MIR) could be used to assess variability in coagulation status. We also investigated the genetic background of milk coagulation ability. Individual milk samples were collected from 996 Sarda ewes farmed in 47 flocks located in Sardinia (Italy). Considered traits were daily milk yield, milk composition traits, and milk coagulation properties (rennet coagulation time, curd firming time, and curd firmness), and MIR spectra were acquired. About 9% of samples did not coagulate within 30 min. A logistic regression approach was used to test the effect of milk-related traits on milk coagulation status. A principal component (PC) analysis was carried out on the milk MIR spectra, and PC scores were then used as covariates in a logistic regression model to assess their relationship with milk coagulation status. Results of the present work demonstrated that the probability of having NC samples increases as milk contents of proteins and chlorides and somatic cell score increase. The analysis of PC extracted from milk spectra that influenced coagulation status highlighted key regions associated with lactose and protein concentrations, and others not associated with routinely collected milk composition traits. These results suggest that the occurrence of NC is mostly related to damage of the epithelium secretory mammary cells, which occurs with the advancement of a lactation or due to unhealthy mammary gland status. Genetic analysis of milk coagulation status and of the extracted PC confirmed the genetic background of the milk coagulability of sheep milk.     

Short communication: Prediction of retention pay-off using a machine learning algorithm

Replacement decisions have a major effect on dairy farm profitability. Dynamic programming (DP) has been widely studied to find the optimal replacement policies in dairy cattle. However, DP models are computationally intensive and might not be practical for daily decision making. Hence, the ability of applying machine learning on a prerun DP model to provide fast and accurate predictions of nonlinear and intercorrelated variables makes it an ideal methodology. Milk class (1 to 5), lactation number (1 to 9), month in milk (1 to 20), and month of pregnancy (0 to 9) were used to describe all cows in a herd in a DP model. Twenty-seven scenarios based on all combinations of 3 levels (base, 20% above, and 20% below) of milk production, milk price, and replacement cost were solved with the DP model, resulting in a data set of 122,716 records, each with a calculated retention pay-off (RPO). Then, a machine learning model tree algorithm was used to mimic the evaluated RPO with DP. The correlation coefficient factor was used to observe the concordance of RPO evaluated by DP and RPO predicted by the model tree. The obtained correlation coefficient was 0.991, with a corresponding value of 0.11 for relative absolute error. At least 100 instances were required per model constraint, resulting in 204 total equations (models). When these models were used for binary classification of positive and negative RPO, error rates were 1% false negatives and 9% false positives. Applying this trained model from simulated data for prediction of RPO for 102 actual replacement records from the University of Wisconsin-Madison dairy herd resulted in a 0.994 correlation with 0.10 relative absolute error rate. Overall results showed that model tree has a potential to be used in conjunction with DP to assist farmers in their replacement decisions.     

Assessing the effect of pregnancy stage on milk composition of dairy cows using mid-infrared spectra

Changes in milk production traits (i.e., milk yield, fat, and protein contents) with the pregnancy stage are well documented. To our knowledge, the effect of pregnancy on the detailed milk composition has not been studied so far. The mid-infrared (MIR) spectrum reflects the detailed composition of a milk sample and is obtained by a nonexhaustive and widely used method for milk analysis. Therefore, this study aimed to investigate the effect of pregnancy on milk MIR spectrum in addition to milk production traits (milk yield, fat, and protein contents). A model including regression on the number of days pregnant was applied on milk production traits (milk yield, fat, and protein contents) and on 212 spectral points from the MIR spectra of 9,757 primiparous Holstein cows from Walloon herds. Effects of pregnancy stage were expressed on a relative scale (effect divided by the squared root of the phenotypic variance); this allowed comparisons between effects on milk traits and on 212 spectral points. Effect of pregnancy stage on production traits were in line with previous studies indicating that the model accounted well for the pregnancy effect. Trends of the relative effect of the pregnancy stage on the 212 spectral points were consistent with known and observed effect on milk traits. The highest effect of the pregnancy was observed in the MIR spectral region from 968 to 1,577 cm^?1. For some specific wavenumbers, the effect was higher than for fat and protein contents in the beginning of the pregnancy (from 30 to 90 or 120 d pregnant). In conclusion, the effect of early pregnancy can be observed in the detailed milk composition through the analysis of the MIR spectrum of bovine milk. Further analyses are warranted to explore deeply the use of MIR spectra of bovine milk for breeding and management of dairy cow pregnancy.     

Prediction of blood metabolites from milk mid-infrared spectra in early-lactation cows

Dairy cows commonly experience an unbalanced energy status in early lactation, and this condition can lead to the onset of several metabolic disorders. Blood metabolic profile testing is a valid tool to monitor and detect the most common early lactation disorders, but blood sampling and analysis are time-consuming and expensive, and the procedure is invasive and stressful for the cows. Mid-infrared (MIR) spectroscopy is routinely used to analyze milk composition, being a cost-effective and nondestructive method. The present study aimed to assess the feasibility of using routine milk MIR spectra for the prediction of main blood metabolites in dairy cows, and to investigate associations between measured blood metabolites and milk traits. Twenty herds of Holstein Friesian, Brown Swiss, or Simmental cows located in Northeast Italy were visited 1 to 4 times between December 2017 and June 2018, and blood and milk samples were collected from all lactating cows within 35 d in milk. Concentrations of main blood metabolites and milk MIR spectra were recorded from 295 blood and milk samples and used to develop prediction models for blood metabolic traits through backward interval partial least squares analysis. Blood β-hydroxybutyrate (BHB), urea, and nonesterified fatty acids were the most predictable traits, with coefficients of determination of 0.63, 0.58, and 0.52, respectively. On the contrary, predictive performance for blood glucose, triglycerides, cholesterol, glutamic oxaloacetic transaminase, and glutamic pyruvic transaminase were not accurate. Associations of blood BHB and urea with their respective contents in milk were moderate to strong, whereas all other correlations were weak. Predicted blood BHB showed an improved performance in detecting cows with hyperketonemia (blood BHB ≥ 1.2 mmol/L), compared with commercial calibration equation for milk BHB. Results highlighted the opportunity of using milk MIR spectra to predict blood metabolites and thus to collect routine information on the metabolic status of early-lactation cows at a population level.     

Pregnancy status predicted using milk mid-infrared spectra from dairy cattle

Accurate and timely pregnancy diagnosis is an important component of effective herd management in dairy cattle. Predicting pregnancy from Fourier-transform mid-infrared (FT-MIR) spectroscopy data is of particular interest because the data are often already available from routine milk testing. The purpose of this study was to evaluate how well pregnancy status could be predicted in a large data set of 1,161,436 FT-MIR milk spectra records from 863,982 mixed-breed pasture-based New Zealand dairy cattle managed within seasonal calving systems. Three strategies were assessed for defining the nonpregnant cows when partitioning the records according to pregnancy status in the training population. Two of these used records for cows with a subsequent calving only, whereas the third also included records for cows without a subsequent calving. For each partitioning strategy, partial least squares discriminant analysis models were developed, whereby spectra from all the cows in 80% of herds were used to train the models, and predictions on cows in the remaining herds were used for validation. A separate data set was also used as a secondary validation, whereby pregnancy diagnosis had been assigned according to the presence of pregnancy-associated glycoproteins (PAG) in the milk samples. We examined different ways of accounting for stage of lactation in the prediction models, either by including it as an effect in the prediction model, or by pre-adjusting spectra before fitting the model. For a subset of strategies, we also assessed prediction accuracies from deep learning approaches, utilizing either the raw spectra or images of spectra. Across all strategies, prediction accuracies were highest for models using the unadjusted spectra as model predictors. Strategies for cows with a subsequent calving performed well in herd-independent validation with sensitivities above 0.79, specificities above 0.91 and area under the receiver operating characteristic curve (AUC) values over 0.91. However, for these strategies, the specificity to predict nonpregnant cows in the external PAG data set was poor (0.002–0.04). The best performing models were those that included records for cows without a subsequent calving, and used unadjusted spectra and days in milk as predictors, with consistent results observed across the training, herd-independent validation and PAG data sets. For the partial least squares discriminant analysis model, sensitivity was 0.71, specificity was 0.54 and AUC values were 0.68 in the PAG data set; and for an image-based deep learning model, the sensitivity was 0.74, specificity was 0.52 and the AUC value was 0.69. Our results demonstrate that in pasture-based seasonal calving herds, confounding between pregnancy status and spectral changes associated with stage of lactation can inflate prediction accuracies. When the effect of this confounding was reduced, prediction accuracies were not sufficiently high enough to use as a sole indicator of pregnancy status.     

The use of milk Fourier-transform mid-infrared spectroscopy to diagnose pregnancy and determine spectral regional associations with pregnancy in US dairy cows

Accurate early diagnosis of pregnancy is important for timely reproductive management of dairy farms. Fourier-transform mid-infrared (FT-MIR) milk spectral data are routinely used for determining milk components such as fat and protein, whereas milk composition is known to change with advancing stages of pregnancy. The objectives of this study were to compare partial least squares discriminant analysis (PLS-DA) and a Bayesian variable selection regression model (BayesC) for the diagnosis of pregnancy status (PS) from milk FT-MIR data and to infer any spectral regions that might be highly associated with PS at various stages of pregnancy. Conception dates on confirmed pregnant cows were obtained from Holstein cows within 123 herds in Michigan, Ohio, and Indiana during 2018 and 2019. Milk samples from these pregnant cows at 7 different stages of pregnancy were case-control matched to open contemporary herd mates to be within the same stage (±10 d for days in milk) of lactation for the same milk sample test date. The FT-MIR data were obtained for all of these milk samples. Ten-fold herd-independent cross-validation was used to compare PLS-DA versus BayesC using the area under the receiver operating characteristic curve (AUC). The BayesC model demonstrated higher mean AUC compared with PLS-DA at all stages exceeding 60 d of pregnancy. The mean BayesC AUC at stage 1 (1–30 d) was 0.58 ± 0.02, which was superior to a random guess (AUC = 0.50) yet too low to be of practical use. The mean BayesC AUC at stage 7 (≥180 d) was 0.13 greater compared with that of stage 1 (1–30 d) and 0.07 to 0.10 greater compared with stages 2, 3, 4, 5, and 6 (31–180 d in 30-d increments). The mean AUC of stages 2 to 6 were 0.03 to 0.06 greater compared with stage 1 yet again too low to be of practical use. Because of high multicollinearity between many adjacent wavenumbers, a spatially constrained clustering algorithm was used to adaptively partition wavenumbers into 68 windows before inferring associations of spectral regions with pregnancy. Pregnancy status was highly associated with wavenumber windows 1,063 to 1,134 cm^?1, 1,201 to 1,257 cm^?1, and 1,260 to 1,432 cm^?1 based on an estimated BayesC posterior probability of association (PPA) approaching 100% for each of these windows at all pregnancy stages. Other windows ranging from 1,730 to 1,764 cm^?1, 1,775 to 1,992 cm^?1, 1,995 to 2,163 cm^?1, and 2,167 to 2,316 cm^?1 had varying medium to high PPA (30% to 100%) across stages. The estimated PPA in wavenumber regions from 1,477 to 1,507 cm^?1, and 1,510 to 1,574 cm^?1 was weaker in stages 1 and 2 compared with later stages, whereas for the regions 2,984 to 3,077 cm^?1 and 3,081 to 3,133 cm^?1 the effect of pregnancy was greater for stage 1 compared with other stages. Despite our conclusion that milk FT-MIR data poorly diagnose PS, our study provides new insights into spectral regions that are strongly associated with PS and warrant greater attention.     

Validation of mid-infrared spectrometry in milk for predicting body energy status in Holstein-Friesian cows

Cow energy balance is known to be associated with cow health and fertility; therefore, routine access to data on energy balance can be useful in both management and breeding decisions to improve cow performance. The objective of this study was to determine if individual cow milk mid-infrared spectra (MIR) could be useful to predict cow energy balance across contrasting production systems. Direct energy balance was calculated as the differential between energy intake and energy output in milk and maintenance (maintenance was predicted using body weight). Body energy content was calculated from (change in) body weight and body condition score. Following editing, 2,992 morning, 2,742 midday, and 2,989 evening milk MIR records from 564 lactations on 337 Scottish cows, managed in a confinement system on 1 of 2 diets, were available. An additional 844 morning and 820 evening milk spectral records from 338 lactations on 244 Irish cows offered a predominantly grazed grass diet were also available. Equations were developed to predict body energy status using the milk spectral data and milk yield as predictor variables. Several different approaches were used to test the robustness of the equations calibrated in one data set and validated in another. The analyses clearly showed that the variation in the validation data set must be represented in the calibration data set. The accuracy (i.e., square root of the coefficient of multiple determinations) of predicting, from MIR, direct energy balance, body energy content, and energy intake was 0.47 to 0.69, 0.51 to 0.56, and 0.76 to 0.80, respectively. This highlights the ability of milk MIR to predict body energy balance, energy content, and energy intake with reasonable accuracy. Very high accuracy, however, was not expected, given the likely random errors in the calculation of these energy status traits using field data.     

Precalibration evaluation procedures for mid-infrared milk analyzers

The purpose of this paper is to present a detailed account of the precalibration procedures developed and implemented by the USDA Federal Milk Market Administrators (FMMA) for evaluating mid-infrared (MIR) milk analyzers. Mid-infrared analyzers specifically designed for milk testing provide a rapid and cost-effective means for determining milk composition for payment and dairy herd improvement programs. These instruments determine the fat, protein, and lactose content of milk, and enable the calculation of total solids, solids-not-fat, and other solids. All MIR analyzers are secondary testing instruments that require calibration by chemical reference methods. Precalibration is the process of assuring that the instrument is in good working order (mechanically and electrically) and that the readings before calibration are stable and optimized. The main components of precalibration are evaluation of flow system integrity, homogenization efficiency, water repeatability, zero shift, linearity, primary slope, milk repeatability, purging efficiency, and establishment of intercorrection factors. These are described in detail and apply to both filter-based and Fourier transform infrared instruments operating using classical primary and reference wavelengths. Under the USDA FMMA Precalibration Evaluation Program, the precalibration procedures were applied longitudinally over time using a wide variety of instruments and instrument models. Instruments in this program were maintained to pass the criteria for all precalibration procedures. All instruments used similar primary wavelengths to measure fat, protein, and lactose but there were differences in reference wavelength selection. Intercorrection factors were consistent over time within all instruments and similar among groups of instruments using similar primary and reference wavelengths. However, the magnitude and sign of the intercorrection factors were significantly affected by the choice of reference wavelengths.     

Feasibility of Discriminating Dried Dairy Ingredients and Preheat Treatments Using Mid-Infrared and Raman Spectroscopy

This study investigated the feasibility of mid-infrared (MIR) and Raman spectroscopy for (i) discrimination of three dried dairy ingredients, namely skim milk powder (SMP), whey protein concentrate (WPC) and demineralised whey protein (DWP) powder, and (ii) discrimination of preheat treatments of dried dairy ingredients using partial least squares discriminant analysis (PLS-DA). PLS1-DA models developed using MIR ranges of 800–1800 and 1200–1800 cm^?1 yielded the best discrimination (correct identification of 97.2% for SMP discrimination and 100% for WPC and DWP discrimination). The best PLS2-DA model using MIR spectroscopy was developed over the spectral range of 800–1800 cm^?1 and produced correct identification of 100% for dairy ingredient discrimination. Models developed using Raman 800–1800 and 1200–1800 cm^?1 spectral ranges correctly discriminated (100% correctly identified) each dairy ingredient. Although all PLS1-DA and PLS2-DA models developed using both spectral technologies for preheat treatment discrimination had good discrimination accuracy (86–100%), they employed a high number of factors (8–9 for the best model). The use of the Martens uncertainty test successfully reduced the number of factors employed (3–4 for the best models) and improved the performance of PLS1-DA models for preheat treatment discrimination (all 100% correctly identified). This feasibility study demonstrates the potential of both MIR and Raman spectroscopy for rapid characterisation of dried dairy ingredients.     

Diagnostic milk biomarkers for predicting the metabolic health status of dairy cattle during early lactation

Data on metabolic profiles of blood sampled at d 3, 6, 9, and 21 in lactation from 117 lactations (99 cows) were used for unsupervised k-means clustering. Blood metabolic parameters included β-hydroxybutyrate (BHB), nonesterified fatty acids, glucose, insulin-like growth factor-1 (IGF-1) and insulin. Clustering relied on the average and range of the 5 blood parameters of all 4 sampling days. The clusters were labeled as imbalanced (n = 42) and balanced (n = 72) metabolic status based on the values of the blood parameters. Various random forest models were built to predict the metabolic cluster of cows during early lactation from the milk composition. All the models were evaluated using a leave-group-out cross-validation, meaning data from a single cow were always present in either train or test data to avoid any data leakage. Features were either milk fatty acids (MFA) determined by gas chromatography (MFA [GC]) or features that could be determined during a routine dairy herd improvement (DHI) analysis, such as concentration of fat, protein, lactose, fat/protein ratio, urea, and somatic cell count (determined and reported routinely in DHI registrations), either or not in combination with MFA and BHB determined by mid-infrared (MIR), denoted as MFA [MIR] and BHB [MIR], respectively, which are routinely analyzed but not routinely reported in DHI registrations yet. Models solely based on fat, protein, lactose, fat/protein ratio, urea and somatic cell count (i.e., DHI model) were characterized by the lowest predictive performance [area under the receiver operating characteristic curve (AUC_ROC) = 0.69]. The combination of the features of the DHI model with BHB [MIR] and MFA [MIR] powerfully increased the predictive performance (AUC_ROC = 0.81). The model based on the detailed MFA profile determined by GC analysis did not outperform (AUC_ROC = 0.81) the model using the DHI-features in combination with BHB [MIR] and MFA [MIR]. Predictions solely based on samples at d 3 were characterized by lower performance (AUC_ROC DHI + BHB [MIR] + MFA [MIR] model at d 3: 0.75; AUC_ROC MFA [GC] model at d 3: 0.73). High predictive performance was found using samples from d 9 and 21. To conclude, overall, the DHI + BHB [MIR] + MFA [MIR] model allowed to predict metabolic status during early lactation. Accordingly, these parameters show potential for routine prediction of metabolic status.     

Real-time milk analysis integrated with stacking ensemble learning as a tool for the daily prediction of cheese-making traits in Holstein cattle

Cheese-making traits in dairy cattle are important to the dairy industry but are difficult to measure at the individual level because there are limitations on collecting phenotypic information. Mid-infrared spectroscopy has its advantages, but it can only be used during monthly milk recordings. Recently, in-line devices for real-time analysis of milk quality have been developed. The AfiLab recording system (Afimilk) offers significant benefits as phenotypes can be collected from each cow at each milking session. The objective of this study was to assess the potential of integrating AfiLab real-time milk analyzer measures with the stacking ensemble learning technique using heterogeneous base learners for the in-line daily monitoring of cheese-making traits in Holstein cattle with a view to developing a precision livestock farming system for monitoring the technological quality of milk. Data and samples for wet-laboratory analyses were collected from 499 Holstein cows belonging to 2 farms where the AfiLab system was installed. The traits of concern were 9 milk coagulation traits [3 milk coagulation properties (MCP), and 6 curd firming traits (CF_t)], and 7 cheese-making traits [3 cheese yield (CY) traits, and 4 milk nutrient recovery in the curd (REC) traits]. The near-infrared AfiLab spectral data and on-farm information (days in milk and parity) were used to assess the predictive ability of different statistical methods [elastic net (EN), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), and artificial neural network (ANN)] across different cross-validation scenarios. These statistical methods were considered the base learners, which were then combined in a stacking ensemble learning. Results indicate that including information on the cows (days in milk and parity) in the AfiLab infrared prediction increased its accuracy by 10.3% for traditional MCP, 13.8% for curd firming, 9.8% for CY, and 11.2% for REC traits compared with those obtained from near-infrared AfiLab alone. The statistical approaches exhibited high prediction accuracies (R²) averaged across the cross-validation scenarios for traditional MCP (0.58 for ANN, 0.55 for EN and GBM, 0.52 for XGBoost, and 0.62 for stacking ensemble), CF_t (0.55 for ANN, 0.54 for EN and GBM, 0.53 for XGBoost, and 0.61 for stacking ensemble), and similar R² averages for CY and REC (0.55 for ANN, 0.54 for EN and GBM, 0.53 for XGBoost, and 0.61 for stacking ensemble). The ANN approach was more accurate than the other base learners (EN, GBM, and XGBoost) and improved accuracy across cross-validation scenarios on average by 7% for traditional MCP, 5% for CF_t, 8% for CY, and 7% for REC. The stacking ensemble method improved prediction accuracy by 3% to 31% for traditional MCP, 2% to 26% for CF_t, 1% to 38% for CY traits, and 2% to 27% for REC traits compared with the base learners. The prediction accuracies of the different approaches evaluated tended to decrease from the 10-fold cross-validation to the independent validation scenario, although there was a smaller reduction in prediction accuracy with the stacking ensemble learning technique across all the cross-validation scenarios. Our results show that combining in-line on-farm information with stacking ensemble machine learning represents an effective alternative for obtaining robust daily predictions of milk cheese-making traits.     

Potential estimation of major mineral contents in cow milk using mid-infrared spectrometry

Milk and dairy products are a major source of minerals, particularly calcium, involved in several metabolic functions in humans. Currently, several dairy products are enriched with calcium to prevent osteoporosis. The development of an inexpensive and fast quantitative analysis for minerals is required to offer dairy farmers an opportunity to improve the added value of the produced milk. The aim of this study was to develop 5 equations to measure Ca, K, Mg, Na, and P contents directly in bovine milk using mid-infrared (MIR) spectrometry. A total of 1,543 milk samples were collected between March 2005 and May 2006 from 478 cows during the Walloon milk recording and analyzed by MIR spectrometry. Using a principal component approach, 62 milk samples were selected by their spectral variability and separated in 2 calibration sets. Five outliers were detected and deleted. The mineral contents of the selected samples were measured by inductively coupled plasma atomic emission spectrometry. Using partial least squares combined with a repeatability file, 5 calibration equations were built to estimate the contents of Ca, K, Mg, Na, and P in milk. To assess the accuracy of the developed equations, a full cross-validation and an external validation were performed. The cross-validation coefficients of determination (R²cv) were 0.80, 0.70, and 0.79 for Ca, Na, and P, respectively (n = 57), and 0.23 and 0.50 for K and Mg, respectively (n = 31). Only Ca, Na, and P equations showed sufficient R²cv for a potential application. These equations were validated using 30 new milk samples. The validation coefficients of determination were 0.97, 0.14, and 0.88 for Ca, Na, and P, respectively, suggesting the potential to use the Ca and P calibration equations. The last 30 samples were added to the initial milk samples and the calibration equations were rebuilt. The R²cv for Ca, K, Mg, Na, and P were 0.87, 0.36, 0.65, 0.65, and 0.85, respectively, confirming the potential utilization of the Ca and P equations. Even if new samples should be added in the calibration set, the first results of this study showed the feasibility to quantify the calcium and phosphorus directly in bovine milk using MIR spectrometry.     

The relationships between early lactation energy status indicators and endocrine fertility traits in dairy cows

The relationships between dairy cow milk-based energy status (ES) indicators and fertility traits were studied during periods 8 to 21, 22 to 35, 36 to 49, and 50 to 63 d in milk. Commencement of luteal activity (C-LA) and interval from calving to the first heat (CFH), based on frequent measurements of progesterone by the management tool Herd Navigator (DeLaval), were used as fertility traits. Energy status indicator traits were milk β-hydroxybutyrate (BHB) concentration provided by Herd Navigator and milk fat:protein ratio, concentration of C18:1 cis-9, the ratio of fatty acids (FA) C18:1 cis-9 and C10:0 in test-day milk samples, and predicted plasma concentration of nonesterified fatty acids (NEFA) on test days. Plasma NEFA predictions were based either directly on milk mid-infrared spectra (MIR) or on milk fatty acids based on MIR spectra (NEFA_mir and NEFA_fa, respectively). The average (standard deviation) C-LA was 39.3 (±16.6) days, and the average CFH was 50.7 (±17.2) days. The correlations between fertility traits and ES indicators tended to be higher for multiparous (r < 0.28) than for primiparous (r < 0.16) cows. All correlations were lower in the last period than in the other periods. In period 1, correlations of C-LA with NEFA_fa and BHB, respectively, were 0.15 and 0.14 for primiparous and 0.26 and 0.22 for multiparous cows. The associations between fertility traits and ES indicators indicated that negative ES during the first weeks postpartum may delay the onset of luteal activity. Milk FPR was not as good an indicator for cow ES as other indicators. According to these findings, predictions of plasma NEFA and milk FA based on milk MIR spectra of routine test-day samples and the frequent measurement of milk BHB by Herd Navigator gave equally good predictions of cow ES during the first weeks of lactation. Our results indicate that routinely measured milk traits can be used for ES evaluation in early lactation.     

Prediction of fatty acid profiles in cow,ewe, and goat milk by mid-infrared spectrometry

Mid-infrared (MIR) spectrometry was used to estimate the fatty acid (FA) composition in cow, ewe, and goat milk. The objectives were to compare different statistical approaches with wavelength selection to predict the milk FA composition from MIR spectra, and to develop equations for FA in cow, goat, and ewe milk. In total, a set of 349 cow milk samples, 200 ewe milk samples, and 332 goat milk samples were both analyzed by MIR and by gas chromatography, the reference method. A broad FA variability was ensured by using milk from different breeds and feeding systems. The methods studied were partial least squares regression (PLS), first-derivative pretreatment + PLS, genetic algorithm + PLS, wavelets + PLS, least absolute shrinkage and selection operator method (LASSO), and elastic net. The best results were obtained with PLS, genetic algorithm + PLS and first derivative + PLS. The residual standard deviation and the coefficient of determination in external validation were used to characterize the equations and to retain the best for each FA in each species. In all cases, the predictions were of better quality for FA found at medium to high concentrations (i.e., for saturated FA and some monounsaturated FA with a coefficient of determination in external validation >0.90). The conversion of the FA expressed in grams per 100 mL of milk to grams per 100 g of FA was possible with a small loss of accuracy for some FA.