Predicting cow milk quality traits from routinely available milk spectra using statistical machine learning methods

Transferability across countries of equations developed using milk mid-infrared spectroscopy to estimate daily body condition score change in dairy cows

Routine milk samples are commonly subjected to spectroscopic analysis within the mid-infrared (MIR) region of the electromagnetic spectrum to estimate macro-constituents of milk like fat, protein, lactose, and urea content. These spectra, however, can also be used to predict other traits, such as daily body condition score (BCS) change. The objective of the present study was to assess the transferability across countries of equations to predict daily body condition score change (ΔBCS) developed using milk MIR data collected in Ireland and in Canada. Body condition was scored on a scale from 1 (emaciated) to 5 (obese) in both countries. A total of 347,254 BCS records from 80,400 Canadian cows were available along with 73,193 BCS records from 6,572 Irish cows. Partial least squares regression (PLSR) and neural networks (NN) were separately used to predict daily ΔBCS. Two scenarios were studied 1) using Canadian and Irish data combined as the calibration data set to predict daily ΔBCS in Canada and in Ireland separately, and 2) Canadian and Irish data used separately to predict daily ΔBCS in each country separately. These prediction methods were applied to data with and without pretreatment (i.e., first derivative of the spectrum) as well as with and without standardizing daily ΔBCS across countries. For all the scenarios investigated, the correlation between actual and predicted daily ΔBCS when calibrated and validated (using cross-validation) in the same country ranged from 0.92 to 0.94, and from 0.85 to 0.87 for the Canadian and Irish data sets, respectively. When the data from Canada and Ireland were combined in the calibration process to predict daily ΔBCS, the correlations between actual and predicted ΔBCS were ≥ 0.90 and ≥ 0.80 for Canadian and Irish daily ΔBCS, respectively indicating no improvement in predictive ability. Predictive performance when calibrated using just Canadian data and validated using just Irish data was poor, and vice versa. Nonetheless, when developing equations for a country for which a limited database (i.e., 100 records) of gold standard and MIR data were available, predictive performance improved when the limited database was supplemented with the large data set from the other country. In general, for some of the investigated scenarios, standardizing the daily ΔBCS data within country before undertaking the calibration improved prediction accuracy. In conclusion, the benefit of merging data from different countries, at least based on the trait (i.e., daily ΔBCS) and countries (i.e., Ireland and Canada) considered in the present study were limited and, in cases, counter-productive.

Integrating mid-infrared spectroscopy, machine learning, and graphical bias correction for fatty acid prediction in water buffalo milk

BACKGROUND

Buffalo milk, constituting 15% of global production, has higher fatty acids content than Holstein milk. Fourier-transform mid-infrared (FT-MIR) spectroscopy is widely used for dairy analysis, but its application to buffalo milk, with larger fat globules, remains understudied. The ultimate goal of this study is to develop machine learning models based on FT-MIR spectroscopy for predicting fatty acids in buffalo milk and to assess the accuracy of commercial milk analyzers. This research provides a convenient, fast, and environmentally friendly method for detecting the fatty acid composition in buffalo milk.

RESULTS

We employed six machine learning algorithms to establish a detection model for 34 fatty acids in buffalo milk. The predictive models demonstrated robust capabilities for high-content fatty acids [C14:0, C15:0, C16:0, C17:0, C18:0, C18:1, saturated fatty acid (SFA), monounsaturated fatty acid (MUFA)], with errors within a 15% range. Traditional FT6000 detection methods exhibited limitations in measuring SFAs and polyunsaturated fatty acids (PUFA). Implementing a mean difference correction of 0.21 for MUFAs and applying regression equations (SFA × 1.0639 + 0.0705; PUFA × 0.5472 + 0.0047) significantly improved measurement accuracy.

CONCLUSION

This study successfully developed a predictive model for fatty acids in Mediterranean buffalo milk based on FT-MIR spectroscopy. Additionally, a correction was applied to the existing measurement device, FT6000, enabling more accurate measurements of fatty acids in buffalo milk. The findings have practical implications for the food industry, offering a faster and more reliable approach to assess and monitor fatty acid composition in buffalo milk, potentially influencing product development and quality control processes. © 2024 Society of Chemical Industry.

Beyond the hype: using AI, big data, wearable devices, and the internet of things for high-throughput livestock phenotyping

Phenotyping of animals is a routine task in agriculture which can provide large datasets for the functional annotation of genomes. Using the livestock farming sector to study complex traits enables genetics researchers to fully benefit from the digital transformation of society as economies of scale substantially reduces the cost of phenotyping animals on farms. In the agricultural sector genomics has transitioned towards a model of 'Genomics without the genes' as a large proportion of the genetic variation in animals can be modelled using the infinitesimal model for genomic breeding valuations. Combined with third generation sequencing creating pan-genomes for livestock the digital infrastructure for trait collection and precision farming provides a unique opportunity for high-throughput phenotyping and the study of complex traits in a controlled environment. The emphasis on cost efficient data collection mean that mobile phones and computers have become ubiquitous for cost-efficient large-scale data collection but that the majority of the recorded traits can still be recorded manually with limited training or tools. This is especially valuable in low- and middle income countries and in settings where indigenous breeds are kept at farms preserving more traditional farming methods. Digitalization is therefore an important enabler for high-throughput phenotyping for smaller livestock herds with limited technology investments as well as large-scale commercial operations. It is demanding and challenging for individual researchers to keep up with the opportunities created by the rapid advances in digitalization for livestock farming and how it can be used by researchers with or without a specialization in livestock. This review provides an overview of the current status of key enabling technologies for precision livestock farming applicable for the functional annotation of genomes.

Heat Stability Assessment of Milk: A Review of Traditional and Innovative Methods

It is important to differentiate milk with different thermostabilities for diverse applications in food products and for the appropriate selection of processing and maintenance of manufacturing facilities. In this review, an overview of the chemical changes in milk subjected to high-temperature heating is given. An emphasis is given to the studies of traditional and state-of-the-art strategies for assessing the milk thermostability, as well as their influencing factors. Traditional subjective and objective techniques have been used extensively in many studies for evaluating thermostability, whereas recent research has been focused on novel approaches with greater objectivity and accuracy, including innovative physical, spectroscopic, and predictive tools.

Predicting subacute ruminal acidosis from milk mid-infrared estimated fatty acids and machine learning on Canadian commercial dairy herds

Our objective was to validate the possibility of detecting SARA from milk Fourier transform mid-infrared spectroscopy estimated fatty acids (FA) and machine learning. Subacute ruminal acidosis is a common condition in modern commercial dairy herds for which the diagnostic remains challenging due to its symptoms often being subtle, nonexclusive, and not immediately apparent. This observational study aimed at evaluating the possibility of predicting SARA by developing machine learning models to be applied to farm data and to provide an estimated portrait of SARA prevalence in commercial dairy herds. A first data set composed of 488 milk samples of 67 cows (initial DIM = 8.5 ± 6.18; mean ± SD) from 7 commercial dairy farms and their corresponding SARA classification (SARA+ if rumen pH <6.0 for 300 min, else SARA-) was used for the development of machine learning models. Three sets of predictive variables: i) milk major components (MMC), ii) milk FA (MFA), and iii) MMC combined with MFA (MMCFA) were submitted to 3 different algorithms, namely Elastic net (EN), Extreme gradient boosting (XGB), and Partial least squares (PLS), and evaluated using 3 different scenarios of cross-validation. Accuracy, sensitivity, and specificity of the resulting 27 models were analyzed using a linear mixed model. Model performance was not significantly affected by the choice of algorithm. Model performance was improved by including fatty acids estimations (MFA and MMCFA as opposed to MMC alone). Based on these results, one model was selected (algorithm: EN; predictive variables: MMCFA; 60.4, 65.4, and 55.3% of accuracy, sensitivity, and specificity, respectively) and applied to a large data set comprising the first test-day record (milk major components and FA within the first 70 DIM of 211,972 Holstein cows (219,503 samples) collected from 3001 commercial dairy herds. Based on this analysis, the within-herd SARA prevalence of commercial farms was estimated at 6.6 ± 5.29% ranging from 0 to 38.3%. A subsequent linear mixed model was built to investigate the herd-level factors associated to higher within-herd SARA prevalence. Milking system, proportion of primiparous cows, herd size and seasons were all herd-level factors affecting SARA prevalence. Furthermore, milk production was positively, and milk fat yield negatively associated with SARA prevalence. Due to their moderate levels of accuracy, the SARA prediction models developed in our study, using data from continuous pH measurements on commercial farms, are not suitable for diagnostic purpose. However, these models can provide valuable information at the herd level.

Establishment and risk factor assessment of the abnormal body temperature probability prediction model (ABTP) for dairy cattle

The study aims to develop an abnormal body temperature probability (ABTP) model for dairy cattle, utilizing environmental and physiological data. This model is designed to enhance the management of heat stress impacts, providing an early warning system for farm managers to improve dairy cattle welfare and farm productivity in response to climate change. The study employs the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm to analyze environmental and physiological data from 320 dairy cattle, identifying key factors influencing body temperature anomalies. This method supports the development of various models, including the Lyman Kutcher-Burman (LKB), Logistic, Schultheiss, and Poisson models, which are evaluated for their ability to predict abnormal body temperatures in dairy cattle effectively. The study successfully validated multiple models to predict abnormal body temperatures in dairy cattle, with a focus on the temperature-humidity index (THI) as a critical determinant. These models, including LKB, Logistic, Schultheiss, and Poisson, demonstrated high accuracy, as measured by the AUC and other performance metrics such as the Brier score and Hosmer-Lemeshow (HL) test. The results highlight the robustness of the models in capturing the nuances of heat stress impacts on dairy cattle. The research develops innovative models for managing heat stress in dairy cattle, effectively enhancing detection and intervention strategies. By integrating advanced technologies and novel predictive models, the study offers effective measures for early detection and management of abnormal body temperatures, improving cattle welfare and farm productivity in changing climatic conditions. This approach highlights the importance of using multiple models to accurately predict and address heat stress in livestock, making significant contributions to enhancing farm management practices.

Predicting methane emissions of individual grazing dairy cows from spectral analyses of their milk samples

Data on the enteric methane emissions of individual cows are useful not just in assisting management decisions and calculating herd inventories but also as inputs for animal genetic evaluations. Data generation for many animal characteristics, including enteric methane emissions, can be expensive and time consuming, so being able to extract as much information as possible from available samples or data sources is worthy of investigation. The objective of the present study was to attempt to predict individual cow methane emissions from the information contained within milk samples, specifically the spectrum of light transmittance across different wavelengths of the mid-infrared (MIR) region of the electromagnetic spectrum. A total of 93,888 individual spot measures of methane (i.e., individual samples of an animal's breath when using the GreenFeed technology) from 384 lactations on 277 grazing dairy cows were collapsed into weekly averages expressed as grams per day; each weekly average coincided with a MIR spectral analysis of a morning or evening individual cow milk sample. Associations between the spectra and enteric methane measures were performed separately using partial least squares regression or neural networks with different tuning parameters evaluated. Several alternative definitions of the enteric methane phenotype (i.e., average enteric methane in the 6 d preceding or 6 d following taking the milk sample or the average of the 6 d before and after the milk sample, all of which also included the enteric methane emitted on the day of milk sampling), the candidate model features (e.g., milk yield, milk composition, and milk MIR) as well as validation strategy (i.e., cross-validation or leave-one-experimental treatment-out) were evaluated. Irrespective of the validation method, the prediction accuracy was best when the average of the milk MIR from the morning and evening milk sample was used and the prediction model was developed using neural networks; concurrently including milk yield and days in milk in the prediction model generated superior predictions relative to just the spectral information alone. Furthermore, prediction accuracy was best when the enteric methane phenotype was the average of at least 20 methane spot measures across a 6-d period flanking each side of the milk sample with associated spectral data. Based on the strategy that achieved the best accuracy of prediction, the correlation between the actual and predicted daily methane emissions when based on 4-fold cross-validation varied per validation stratum from 0.68 to 0.75; the corresponding range when validated on each of the 8 different experimental treatments focusing on alternative pasture grazing systems represented in the dataset varied from 0.55 to 0.71. The root mean square error of prediction across the 4-folds of cross-validation was 37.46 g/d, whereas the root mean square error averaged across all folds of leave-one-treatment-out was 37.50 g/d. Results suggest that even with the likely measurement errors contained within the MIR spectrum and gold standard enteric methane phenotype, enteric methane can be reasonably well predicted from the infrared spectrum of milk samples. What is yet to be established, however, is whether (a) genetic variation exists in this predicted enteric methane phenotype and (b) selection on estimates of genetic merit for this phenotype translate to actual phenotypic differences in enteric methane emissions.

Minerals and essential amino acids of bovine colostrum: Phenotypic variability and predictive ability of mid- and near-infrared spectroscopy

Colostrum quality and volume are fundamental for calves because it is the primary supplier of antibodies and the first source of energy, carbohydrates, lipids, proteins, minerals, and vitamins for the newborn. Assessing the detailed composition (i.e., AA and mineral content) of bovine colostrum (BC) on-line and at a reasonable cost would help dairy stakeholders such as farmers or veterinarians for precision feeding purposes and industries producing preparations containing BC such as foodstuff, supplements, and medicaments. In the present study we evaluated mid- (MIRS) and near-infrared spectroscopy (NIRS) prediction ability for AA and mineral composition of individual BC. Second, we the investigated the major factors affecting the phenotypic variability of such traits also evaluating the correlations with the Ig concentration. Results demonstrated that MIRS and NIRS were able to provide sufficiently accurate predictions for all the AA. The coefficient of determination in external validation (R2V) fell, in fact, within the range of 0.70 to 0.86, with the exception of Ile, His, and Met. Only some minerals reached a sufficient accuracy (i.e., Ca, P, S, and Mg; R2V ≥ 0.66) using MIRS, and also S (R2V = 0.87) using NIRS. Phenotypically, both parity and calving season affected the variability of these BC composition traits. Heifers' colostrum was the one with the greatest concentration of Ca and P, the 2 most abundant minerals. These minerals were however very low in cows calving in summer compared with the rest of the year. The pattern of AA across parities and calving season was not linear, likely because their variability was scarcely (or not) affected by these effects. Finally, samples characterized by high IgG concentration were those presenting on average greater concentration of AA. Findings suggest that infrared spectroscopy has the potential to be used to predict certain AA and minerals, outlining the possibility of implementing on-site analyses for the evaluation of the broad-sense BC quality.

Possible Alternatives: Identifying and Quantifying Adulteration in Buffalo, Goat, and Camel Milk Using Mid-Infrared Spectroscopy Combined with Modern Statistical Machine Learning Methods

Adulteration of higher priced milks with cheaper ones to obtain extra profit can adversely affect consumer health and the market. In this study, pure buffalo milk (BM), goat milk (GM), camel milk (CM), and their mixtures with 5-50% (vol/vol) cow milk or water were used. Mid-infrared spectroscopy (MIRS) combined with modern statistical machine learning was used for the discrimination and quantification of cow milk or water adulteration in BM, GM, and CM. Compared to partial least squares (PLS), modern statistical machine learning-especially support vector machines (SVM), projection pursuit regression (PPR), and Bayesian regularized neural networks (BRNN)-exhibited superior performance for the detection of adulteration. The best prediction models for the different predictive traits are as follows: The binary classification models developed by SVM resulted in differentiation of CM-cow milk, and GM/CM-water mixtures. PLS resulted in differentiation of BM/GM-cow milk and BM-water mixtures. All of the above models have 100% classification accuracy. SVM was used to develop multi-classification models for identifying the high and low proportions of cow milk in BM, GM, and CM, as well as the high and low proportions of water adulteration in BM and GM, with correct classification rates of 94%, 100%, 100%, 99%, and 100%, respectively. In addition, a PLS-based model was developed for identifying the high and low proportions of water adulteration in CM, with correct classification rates of 100%. A regression model for quantifying cow milk in BM was developed using PCA + BRNN, with RMSEV = 5.42%, and RV2 = 0.88. A regression model for quantifying water adulteration in BM was developed using PCA + PPR, with RMSEV = 1.70%, and RV2 = 0.99. Modern statistical machine learning improved the accuracy of MIRS in predicting BM, GM, and CM adulteration more effectively than PLS.

Mid-infrared spectroscopy for large-scale phenotyping of bovine colostrum gross composition and immunoglobulin concentration

Immunoglobulin G is the fundamental antibody for acquisition of passive transfer of immunity in ruminant newborns. Colostrum, in fact, must be administered as soon as possible after birth to ensure a successful transfer of IgG from the dam to the calf. Assessment of colostrum Ig concentration and gross composition via gold standards is expensive, time consuming, and hardly implementable for large-scale investigations. Therefore, in the present study we evaluated the predictive ability of mid-infrared spectroscopy (MIRS) as an indirect determination method. A total of 714 colostrum samples collected within 6 h from parturition from Italian Holstein cows, 30% primiparous and 70% pluriparous, were scanned using a benchtop spectrometer after dilution in pure water. The prediction models were developed by correlating spectral information with the reference measurements: IgG concentration (93.54 ± 33.87 g/L), total Ig concentrations (102.82 ± 35.04 g/L), and content of protein (14.71 ± 3.51%), fat (4.61 ± 3.04%), and lactose (2.36 ± 0.51 mg/100 mg). We found a good to excellent performance in prediction of colostrum IgG concentration and traditional composition traits in cross-validation (R2CV ≥ 0.92) and a promising and good predictive ability in external validation with R2V equal to 0.84, 0.89, and 0.74 for IgG, protein, and fat, respectively. In the case of IgG and protein content, for example, the coefficient of determination in external validation was greater than 0.84. The other Ig fractions, A and M, presented insufficient prediction accuracy likely due to their extremely low concentration compared with IgG (4.56 and 5.06 g/L vs. 93.54 g/L). The discriminant ability of MIRS-predicted IgG and protein content was outstanding when trying to classify samples according to the quality level (i.e., low vs. high concentration of IgG). In particular, the cut-off that better discriminate low- from high-quality colostrum was 75.40 g/L in the case of the MIRS-predicted IgG and 13.32% for the MIRS-predicted protein content. Therefore, MIRS is proposed as a rapid and cheap tool for large-scale punctual IgG, protein, and lactose quantification and for the screening of low-quality samples. From a practical perspective, there is the possibility to install colostrum models in the MIRS benchtop machineries already present in laboratories in charge of official milk testing. Colostrum phenotypes collected on an individual basis will be useful to breeders for the definition of specific selection strategies and to farmers for management scopes. Finally, our findings may be relevant for other stakeholders, given the fact that colostrum is an emerging ingredient for the animal and human food and pharmaceutical industry.

Evaluating the use of statistical and machine learning methods for estimating breed composition of purebred and crossbred animals in thirteen cattle breeds using genomic information

Introduction: The ability to accurately predict breed composition using genomic information has many potential uses including increasing the accuracy of genetic evaluations, optimising mating plans and as a parameter for genotype quality control. The objective of the present study was to use a database of genotyped purebred and crossbred cattle to compare breed composition predictions using a freely available software, Admixture, with those from a single nucleotide polymorphism Best Linear Unbiased Prediction (SNP-BLUP) approach; a supplementary objective was to determine the accuracy and general robustness of low-density genotype panels for predicting breed composition. Methods: All animals had genotype information on 49,213 autosomal single nucleotide polymorphism (SNPs). Thirteen breeds were included in the analysis and 500 purebred animals per breed were used to establish the breed training populations. Accuracy of breed composition prediction was determined using a separate validation population of 3,146 verified purebred and 4,330 two and three-way crossbred cattle. Results: When all 49,213 autosomal SNPs were used for breed prediction, a minimal absolute mean difference of 0.04 between Admixture vs. SNP-BLUP breed predictions was evident. For crossbreds, the average absolute difference in breed prediction estimates generated using SNP-BLUP and Admixture was 0.068 with a root mean square error of 0.08. Breed predictions from low-density SNP panels were generated using both SNP-BLUP and Admixture and compared to breed prediction estimates using all 49,213 SNPs (representing the gold standard). Breed composition estimates of crossbreds required more SNPs than predicting the breed composition of purebreds. SNP-BLUP required ≥3,000 SNPs to predict crossbred breed composition, but only 2,000 SNPs were required to predict purebred breed status. The absolute mean (standard deviation) difference across all panels <2,000 SNPs was 0.091 (0.054) and 0.315 (0.316) when predicting the breed composition of all animals using Admixture and SNP-BLUP, respectively compared to the gold standard prediction. Discussion: Nevertheless, a negligible absolute mean (standard deviation) difference of 0.009 (0.123) in breed prediction existed between SNP-BLUP and Admixture once ≥3,000 SNPs were considered, indicating that the prediction of breed composition could be readily integrated into SNP-BLUP pipelines used for genomic evaluations thereby avoiding the necessity for a stand-alone software.

Estimation of body condition score change in dairy cows in a seasonal calving pasture-based system using routinely available milk mid-infrared spectra and machine learning techniques

Body condition score (BCS) is a subjective estimate of body reserves in cows. Body condition score and its change in early lactation have been associated with cow fertility and health. The aim of the present study was to estimate change in BCS (ΔBCS) using mid-infrared spectra of the milk, with a particular focus on estimating ΔBCS in cows losing BCS at the fastest rate (i.e., the cows most of interest to the producer). A total of 73,193 BCS records (scale 1 to 5) from 6,572 cows were recorded. Daily BCS was interpolated from cubic splines fitted through the BCS records, and subsequently used to calculate daily ΔBCS. Body condition score change records were merged with milk mid-infrared spectra recorded on the same week. Both morning (a.m.) and evening (p.m.) spectra were available. Two different statistical methods were used to estimate ΔBCS: partial least squares regression and a neural network (NN). Several combinations of variables were included as model features, such as days in milk (DIM) only, a.m. spectra only and DIM, p.m. spectra only and DIM, and a.m. and p.m. spectra as well as DIM. The data used to estimate ΔBCS were either based on the first 120 DIM or all 305 DIM. Daily ΔBCS had a standard deviation of 1.65 × 10^-3 BCS units in the 305 DIM data set and of 1.98 × 10^-3 BCS units in the 120 DIM data set. Each data set was divided into 4 sub-data sets, 3 of which were used for training the prediction model and the fourth to test it. This process was repeated until all the sub-data sets were considered as the test data set once. Using all 305 DIM, the lowest root mean square error of validation (RMSEV; 0.96 × 10^-3 BCS units) and the strongest correlation between actual and estimated ΔBCS (0.82) was achieved with NN using a.m. and p.m. spectra and DIM. Using the 120 DIM data, the lowest RMSEV (0.98 × 10^-3 BCS units) and the strongest correlation between actual and estimated ΔBCS (0.87) was achieved with NN using DIM and either a.m. spectra only or a.m. and p.m. spectra together. The RMSEV for records in the lowest 2.5% ΔBCS percentile per DIM in early lactation was reduced up to a maximum of 13% when spectra and DIM were both considered in the model compared with a model that considered just DIM. The performance of the NN using DIM and a.m. spectra only with the 120 DIM data was robust across different strata of farm, parity, year of sampling, and breed. Results from the present study demonstrate the ability of mid-infrared spectra of milk coupled with machine learning techniques to estimate ΔBCS; specifically, the inclusion of spectral data reduced the RMSEV over and above using DIM alone, particularly for cows losing BCS at the fastest rate. This approach can be used to routinely generate estimates of ΔBCS that can subsequently be used for farm decisions.

Integrating on-farm and genomic information improves the predictive ability of milk infrared prediction of blood indicators of metabolic disorders in dairy cows

BACKGROUND

Blood metabolic profiles can be used to assess metabolic disorders and to evaluate the health status of dairy cows. Given that these analyses are time-consuming, expensive, and stressful for the cows, there has been increased interest in Fourier transform infrared (FTIR) spectroscopy of milk samples as a rapid, cost-effective alternative for predicting metabolic disturbances. The integration of FTIR data with other layers of information such as genomic and on-farm data (days in milk (DIM) and parity) has been proposed to further enhance the predictive ability of statistical methods. Here, we developed a phenotype prediction approach for a panel of blood metabolites based on a combination of milk FTIR data, on-farm data, and genomic information recorded on 1150 Holstein cows, using BayesB and gradient boosting machine (GBM) models, with tenfold, batch-out and herd-out cross-validation (CV) scenarios.

RESULTS

The predictive ability of these approaches was measured by the coefficient of determination (R²). The results show that, compared to the model that includes only FTIR data, integration of both on-farm (DIM and parity) and genomic information with FTIR data improves the R² for blood metabolites across the three CV scenarios, especially with the herd-out CV: R² values ranged from 5.9 to 17.8% for BayesB, from 8.2 to 16.9% for GBM with the tenfold random CV, from 3.8 to 13.5% for BayesB and from 8.6 to 17.5% for GBM with the batch-out CV, and from 8.4 to 23.0% for BayesB and from 8.1 to 23.8% for GBM with the herd-out CV. Overall, with the model that includes the three sources of data, GBM was more accurate than BayesB with accuracies across the CV scenarios increasing by 7.1% for energy-related metabolites, 10.7% for liver function/hepatic damage, 9.6% for oxidative stress, 6.1% for inflammation/innate immunity, and 11.4% for mineral indicators.

CONCLUSIONS

Our results show that, compared to using only milk FTIR data, a model integrating milk FTIR spectra with on-farm and genomic information improves the prediction of blood metabolic traits in Holstein cattle and that GBM is more accurate in predicting blood metabolites than BayesB, especially for the batch-out CV and herd-out CV scenarios.

Predicting starch content in cassava fresh roots using near-infrared spectroscopy

The cassava starch market is promising in sub-Saharan Africa and increasing rapidly due to the numerous uses of starch in food industries. More accurate, high-throughput, and cost-effective phenotyping approaches could hasten the development of cassava varieties with high starch content to meet the growing market demand. This study investigated the effectiveness of a pocket-sized SCiO™ molecular sensor (SCiO) (740-1070 nm) to predict starch content in freshly ground cassava roots. A set of 344 unique genotypes from 11 field trials were evaluated. The predictive ability of individual trials was compared using partial least squares regression (PLSR). The 11 trials were aggregated to capture more variability, and the performance of the combined data was evaluated using two additional algorithms, random forest (RF) and support vector machine (SVM). The effect of pretreatment on model performance was examined. The predictive ability of SCiO was compared to that of two commercially available near-infrared (NIR) spectrometers, the portable ASD QualitySpec^® Trek (QST) (350-2500 nm) and the benchtop FOSS XDS Rapid Content™ Analyzer (BT) (400-2490 nm). The heritability of NIR spectra was investigated, and important spectral wavelengths were identified. Model performance varied across trials and was related to the amount of genetic diversity captured in the trial. Regardless of the chemometric approach, a satisfactory and consistent estimate of starch content was obtained across pretreatments with the SCiO (correlation between the predicted and the observed test set, (R² _P): 0.84-0.90; ratio of performance deviation (RPD): 2.49-3.11, ratio of performance to interquartile distance (RPIQ): 3.24-4.08, concordance correlation coefficient (CCC): 0.91-0.94). While PLSR and SVM showed comparable prediction abilities, the RF model yielded the lowest performance. The heritability of the 331 NIRS spectra varied across trials and spectral regions but was highest (H² > 0.5) between 871-1070 nm in most trials. Important wavelengths corresponding to absorption bands associated with starch and water were identified from 815 to 980 nm. Despite its limited spectral range, SCiO provided satisfactory prediction, as did BT, whereas QST showed less optimal calibration models. The SCiO spectrometer may be a cost-effective solution for phenotyping the starch content of fresh roots in resource-limited cassava breeding programs.

Selecting Milk Spectra to Develop Equations to Predict Milk Technological Traits

Including all available data when developing equations to relate midinfrared spectra to a phenotype may be suboptimal for poorly represented spectra. Here, an alternative local changepoint approach was developed to predict six milk technological traits from midinfrared spectra. Neighbours were objectively identified for each predictand as those most similar to the predictand using the Mahalanobis distances between the spectral principal components, and subsequently used in partial least square regression (PLSR) analyses. The performance of the local changepoint approach was compared to that of PLSR using all spectra (global PLSR) and another LOCAL approach, whereby a fixed number of neighbours was used in the prediction according to the correlation between the predictand and the available spectra. Global PLSR had the lowest RMSEV for five traits. The local changepoint approach had the lowest RMSEV for one trait; however, it outperformed the LOCAL approach for four traits. When the 5% of the spectra with the greatest Mahalanobis distance from the centre of the global principal component space were analysed, the local changepoint approach outperformed the global PLSR and the LOCAL approach in two and five traits, respectively. The objective selection of neighbours improved the prediction performance compared to utilising a fixed number of neighbours; however, it generally did not outperform the global PLSR.

Application of Optical Quality Control Technologies in the Dairy Industry: An Overview

Sustainable development of the agricultural industry, in particular, the production of milk and feed for farm animals, requires accurate, fast, and non-invasive diagnostic tools. Currently, there is a rapid development of a number of analytical methods and approaches that meet these requirements. Infrared spectrometry in the near and mid-IR range is especially widespread. Progress has been made not only in the physical methods of carrying out measurements, but significant advances have also been achieved in the development of mathematical processing of the received signals. This review is devoted to the comparison of modern methods and devices used to control the quality of milk and feed for farm animals.

Analysis of Milk from Different Sources Based on Light Propagation and Random Laser Properties

Milk is a valuable contributor to a healthy diet as it contains nutritional components such as fats, proteins, carbohydrates, calcium, phosphorous and vitamins. This research aimed to differentiate milk from animal, plant and human sources based on light propagation and random-laser properties. Experimental, statistical and theoretical analyses were used. Light propagation in different types of milk such as almond milk, oat milk, soy milk, fresh milk, goat milk and human breast milk was measured using the spectrometry method. Near-IR and visible light transmission through the diluted milk samples were compared. Soy milk and fresh milk have the highest absorbance and fluorescence of light, respectively, due to a high content of fat, protein and carbohydrates. Principal component analysis was used to determine the accuracy of the experimental results. The research method is comprehensive as it covers light propagation from 350 nm to 1650 nm of wavelength range and non-intrusive as it does not affect the sample. Meanwhile, analysis of milk was also conducted based on random-laser properties such as multiple emission peaks and lasing threshold. Higher fat content in milk produces a lower random lasing threshold. Thus, we found that milk from animals, plants and humans can be analyzed using light absorption, fluorescence and random lasers. The research method might be useful for future study of milk contaminants that change the properties of milk.

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.

Identifying Health Status in Grazing Dairy Cows from Milk Mid-Infrared Spectroscopy by Using Machine Learning Methods

Simple Summary

Diseases in dairy livestock farming can lead to important economic losses. Several studies have been conducted to identify illness such as lameness by using MIR spectrometry data and relying on partial least squares discriminant analysis. However, this method suffers some limitations. In this study, random forest, support vector machine, neural network, convolutional neural network and ensemble models were used to test the feasibility of identifying cow sickness among 1909 milk sample MIR spectra from Holstein-Friesian, Jersey and Holstein-Friesian × Jersey crossbreed cows. The results obtained show that it is possible to identify a health problem with a reasonable level of accuracy using a neural network.

Abstract

The early detection of health problems in dairy cattle is crucial to reduce economic losses. Mid-infrared (MIR) spectrometry has been used for identifying the composition of cow milk in routine tests. As such, it is a potential tool to detect diseases at an early stage. Partial least squares discriminant analysis (PLS-DA) has been widely applied to identify illness such as lameness by using MIR spectrometry data. However, this method suffers some limitations. In this study, a series of machine learning techniques—random forest, support vector machine, neural network (NN), convolutional neural network and ensemble models—were used to test the feasibility of identifying cow sickness from 1909 milk sample MIR spectra from Holstein-Friesian, Jersey and crossbreed cows under grazing conditions. PLS-DA was also performed to compare the results. The sick cow records had a time window of 21 days before and 7 days after the milk sample was analysed. NN showed a sensitivity of 61.74%, specificity of 97% and positive predicted value (PPV) of nearly 60%. Although the sensitivity of the PLS-DA was slightly higher than NN (65.6%), the specificity and PPV were lower (79.59% and 15.25%, respectively). This indicates that by using NN, it is possible to identify a health problem with a reasonable level of accuracy.

Infrared Spectroscopy and Chemometric Applications for the Qualitative and Quantitative Investigation of Grapevine Organs

The fourth agricultural revolution is leading us into a time of using data science as a tool to implement precision viticulture. Infrared spectroscopy provides the means for rapid and large-scale data collection to achieve this goal. The non-invasive applications of infrared spectroscopy in grapevines are still in its infancy, but recent studies have reported its feasibility. This review examines near infrared and mid infrared spectroscopy for the qualitative and quantitative investigation of intact grapevine organs. Qualitative applications, with the focus on using spectral data for categorization purposes, is discussed. The quantitative applications discussed in this review focuses on the methods associated with carbohydrates, nitrogen, and amino acids, using both invasive and non-invasive means of sample measurement. Few studies have investigated the use of infrared spectroscopy for the direct measurement of intact, fresh, and unfrozen grapevine organs such as berries or leaves, and these studies are examined in depth. The chemometric procedures associated with qualitative and quantitative infrared techniques are discussed, followed by the critical evaluation of the future prospects that could be expected in the field.