Predicting bovine tuberculosis status of dairy cows from mid-infrared spectral data of milk using deep learning

AI and Data Analytics in the Dairy Farms: A Scoping Review

The strong growth of the world population will cause a major increase in demand for bovine milk, making it necessary to use various technologies to increase milk production efficiently. Some technologies that can contribute to solving part of this problem are those related to data analytics tools, big data, and sensor development. It is timely to review modern technologies and data analytics methods for milk predictions in view of supporting decision-making in dairy farms. To this end, a scoping review was carried out, which resulted in 151 articles of interest. Among the most important results, we found that (i) the identified studies are relatively recent with an average publication time of 5.95 years; (ii) the scope of the selected studies is mostly concentrated on milk and prediction (29%), early detection of lameness (26%), and timely detection of mastitis (13%); (iii) the type of analysis is mostly predictive (87%), and prescriptive is barely present (3%); (iv) the types of input data used in the studies are preferably historical (70%), and real-time data (25%) are used less frequently; (v) we found that the method of artificial neural networks (47%) and the convolutional neural networks (24%) are the most used for the studies regarding bovine milk output predictions. In the selected studies, the artificial neural network methods have considerable accuracy, recall, precision, and F1 Scores on average but with high ranges and standard deviations. (vi) Simulation tools are scarcely used, being present in 4% of cases. In the treatment of variability, the models reviewed are mostly deterministic (77%), and the stochastic models (5%) are considered in a small number of cases. Based on our analysis, we conclude that future research on decision-making tools will benefit from the advantages of artificial neural networks in data analytics combined with optimization-simulation methods.

Enhancing Immunoglobulin G Goat Colostrum Determination Using Color-Based Techniques and Data Science

Circulating immunoglobulin G (IgG) concentrations in newborn goat kids are not sufficient to protect the animal against external agents. Therefore, consumption of colostrum, rich in immune components, shortly after birth is crucial. Traditional laboratory methods used to measure IgG concentrations, such as ELISA or RID, are reliable but costly and impractical for many farmers. This study proposes a more accessible alternative for farmers to predict IgG concentration in goat colostrum by integrating color-based techniques with machine learning models, specifically decision trees and neural networks, through the development of two regression models based on colostrum color data from Majorera dairy goats. A total of 813 colostrum samples were collected in a previous study (June 1997-April 2003) that utilized multiple regression analysis as a reference to verify that applying data science techniques improves accuracy and reliability. The decision tree model outperformed the neural network, achieving higher accuracy and lower error rates. Both models provided predictions that closely matched IgG concentrations obtained by ELISA. Therefore, this methodology offers a practical and affordable solution for the on-farm assessment of colostrum quality (i.e., IgG concentration). This approach could significantly improve farm management practices, ensuring better health outcomes in newborn animals by facilitating timely and accurate colostrum quality evaluation.

European Dairy Cattle Evaluations and International Use of Genomic Data

The European and global dairy breeding industry has benefited enormously from collaboration and sharing of data. The new era of genomics has disrupted the information flow due to the requirement to protect commercial investments. New trait phenotypes, evaluation models, and breeding goals continue to evolve and will impact the way national and proprietary data are shared and presented to the dairy industry. The global nature of cattle breeding will, however, continue to require some form of collaboration, even under the new ways of working.

Biometric identification of dairy cows via real-time facial recognition

Biometrics methods, which currently identify humans, can potentially identify dairy cows. Given that animal movements cannot be easily controlled, identification accuracy and system robustness are challenging when deploying an animal biometrics recognition system on a real farm. Our proposed method performs multiple-cow face detection and face classification from videos by adjusting recent state-of-the-art deep-learning methods. As part of this study, a system was designed and installed at four meters above a feeding zone at the Volcani Institute's dairy farm. Two datasets were acquired and annotated, one for facial detection and the second for facial classification of 77 cows. We achieved for facial detection a mean average precision (at Intersection over Union of 0.5) of 97.8% using the YOLOv5 algorithm, and facial classification accuracy of 96.3% using a Vision-Transformer model with a unique loss-function borrowed from human facial recognition. Our combined system can process video frames with 10 cows' faces, localize their faces, and correctly classify their identities in less than 20 ms per frame. Thus, up to 50 frames per second video files can be processed with our system in real-time at a dairy farm. Our method efficiently performs real-time facial detection and recognition on multiple cow faces using deep neural networks, achieving a high precision in real-time operation. These qualities can make the proposed system a valuable tool for an automatic biometric cow recognition on farms.

Assessing the relationship between somatic cell count and the milk mid-infrared spectrum in Chinese Holstein cows

BACKGROUND

Milk produced by dairy cows is a complex combination of many components, but the effect of mastitis has only been investigated for a few of these components. Milk mid-infrared (MIR) spectra can reflect the global composition of milk, and this study aimed to detect the relationships between milk MIR spectral wavenumbers and milk somatic cell count (SCC)-a sensitive biomarker for mastitis.

METHODS

Pearson correlation analysis was used to calculate the correlation coefficient between somatic count score (SCS) and spectral wavenumbers. A general linear mixed model was applied to investigate the effect of three different classes of SCC (low, middle and high) on spectral wavenumbers.

RESULTS

The mean correlation coefficient between the 'fingerprint region' (wavenumbers 925-1582 cm-1 ) and the SCS was higher than that for other regions of the MIR spectrum, and the specific wavenumber with the strongest correlation with the SCS was within the 'fingerprint region'. SCC class had a significant (p < 0.05) effect on 639 spectral wavenumbers. In particular, some spectral wavenumbers within the 'fingerprint region' were highly affected by the SCC class.

LIMITATION

The data were collected from only one province in China, so the generalisability of the findings may be limited.

CONCLUSION

SCC had close relationships with milk spectral wavenumbers related to important milk components or chemical bonds.

Genomic Selection for Dairy Cattle Behaviour Considering Novel Traits in a Changing Technical Production Environment

Cow behaviour is a major factor influencing dairy herd profitability and is an indicator of animal welfare and disease. Behaviour is a complex network of behavioural patterns in response to environmental and social stimuli and human handling. Advances in agricultural technology have led to changes in dairy cow husbandry systems worldwide. Increasing herd sizes, less time availability to take care of the animals and modern technology such as automatic milking systems (AMSs) imply limited human-cow interactions. On the other hand, cow behaviour responses to the technical environment (cow-AMS interactions) simultaneously improve production efficiency and welfare and contribute to simplified "cow handling" and reduced labour time. Automatic milking systems generate objective behaviour traits linked to workability, milkability and health, which can be implemented into genomic selection tools. However, there is insufficient understanding of the genetic mechanisms influencing cow learning and social behaviour, in turn affecting herd management, productivity and welfare. Moreover, physiological and molecular biomarkers such as heart rate, neurotransmitters and hormones might be useful indicators and predictors of cow behaviour. This review gives an overview of published behaviour studies in dairy cows in the context of genetics and genomics and discusses possibilities for breeding approaches to achieve desired behaviour in a technical production environment.

Selective breeding can contribute to bovine tuberculosis control and eradication

Bovine tuberculosis (bTB) persists in many countries having a significant impact on public health and livestock industry finances. The incidence and prevalence of new cases in parts of the UK and elsewhere over the past decades warrant intensified efforts towards achieving Officially Tuberculosis Free (OTF) status in the respective regions. Genetic selection aiming to identify and remove inherently susceptible animals from breeding has been proposed as an additional measure in ongoing programmes towards controlling the disease. The presence of genetic variation among individual animals in their capacity to respond to Mycobacterium bovis exposure has been documented and heritability estimates of 0.06-0.18 have been reported. Despite their moderate magnitude, these estimates suggest that host resistance to bTB is amenable to improvement with selective breeding. Although relatively slow, genetic progress can be constant, cumulative and permanent, thereby complementing ongoing disease control measures. Importantly, mostly no antagonistic genetic correlations have been found between bTB resistance and other animal traits suggesting that carefully incorporating the former in breeding decisions should not adversely affect bovine productivity. Simulation studies have demonstrated the potential impact of genetic selection on reducing the probability of a breakdown to occur or the duration and severity of a breakdown that has already been declared. Furthermore, research on the bovine genome has identified multiple genomic markers and genes associated with bTB resistance. Nevertheless, the combined outcomes of these studies suggest that host resistance to bTB is a complex, polygenic trait, with no single gene alone explaining the inherent differences between resistant and susceptible animals. Such results support the development of accurate genomic breeding values that duly capture the collective effect of multiple genes to underpin selective breeding programmes. In addition to improving host resistance to bTB, scientists and practitioners have considered the possibility of reducing host infectivity. Ongoing studies have suggested the presence of genetic variation for infectivity and confirmed that bTB eradication would be accelerated if selective breeding considered both host resistance and infectivity traits. In conclusion, research activity on bTB genetics has generated knowledge and insights to support selective breeding as an additional measure towards controlling and eradicating the disease.

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.

Novel prediction models for hyperketonemia using bovine milk Fourier-transform infrared spectroscopy

Metabolic diseases driven by negative energy balance in dairy cattle contribute to reduced milk production, increased disease incidence, culling, and death. Cow side tests for negative energy balance markers are available but are labor-intensive. Milk sample analysis using Fourier transform infrared spectroscopy (FTIR) allows for sampling numerous cows simultaneously. FTIR prediction models have moderate accuracy for hyperketonemia diagnosis (beta-hydroxybutyrate (BHB) ≥ 1.2 mmol/L). Most research using FTIR has focused on homogenous datasets and conventional prediction models, including partial least squares, linear discriminant analysis, and ElasticNet. Our objective was to evaluate more diverse modeling options, such as deep learning, gradient boosting machine models, and model ensembles for hyperketonemia classification. We compiled a sizable, heterogeneous dataset including milk FTIR and concurrent blood samples. Blood samples were tested for blood BHB, and wavenumber data was obtained from milk FTIR analysis. Using this dataset, we trained conventional prediction models and other options listed above. We demonstrate prediction model performance is similar for convolutional neural networks and ensemble models to simpler algorithm options. Results obtained from this study indicate that deep learning and model ensembles are potential algorithm options for predicting hyperketonemia in dairy cattle. Additionally, our results indicate hyperketonemia prediction models can be developed using heterogeneous datasets.

Literature Review on Technological Applications to Monitor and Evaluate Calves' Health and Welfare

Precision livestock farming (PLF) research is rapidly increasing and has improved farmers' quality of life, animal welfare, and production efficiency. PLF research in dairy calves is still relatively recent but has grown in the last few years. Automatic milk feeding systems (AMFS) and 3D accelerometers have been the most extensively used technologies in dairy calves. However, other technologies have been emerging in dairy calves' research, such as infrared thermography (IRT), 3D cameras, ruminal bolus, and sound analysis systems, which have not been properly validated and reviewed in the scientific literature. Thus, with this review, we aimed to analyse the state-of-the-art of technological applications in calves, focusing on dairy calves. Most of the research is focused on technology to detect and predict calves' health problems and monitor pain indicators. Feeding and lying behaviours have sometimes been associated with health and welfare levels. However, a consensus opinion is still unclear since other factors, such as milk allowance, can affect these behaviours differently. Research that employed a multi-technology approach showed better results than research focusing on only a single technique. Integrating and automating different technologies with machine learning algorithms can offer more scientific knowledge and potentially help the farmers improve calves' health, performance, and welfare, if commercial applications are available, which, from the authors' knowledge, are not at the moment.

Association between Days Open and Parity, Calving Season or Milk Spectral Data

Milk spectral data on 2118 cows from nine herds located in northern China were used to access the association of days open (DO). Meanwhile, the parity and calving season of dairy cows were also studied to characterize the difference in DO between groups of these two cow-level factors. The result of the linear mixed-effects model revealed that no significant differences were observed between the parity groups. However, a significant difference in DO exists between calving season groups. The interaction between parity and calving season presented that primiparous cows always exhibit lower DO among all calving season groups, and the variation in DO among parity groups was especially clearer in winter. Survival analysis revealed that the difference in DO between calving season groups might be caused by the different P/AI at the first TAI. In addition, the summer group had a higher chance of conception in the subsequent services than other groups, implying that the micro-environment featured by season played a critical role in P/AI. A weak linkage between DO and wavenumbers ranging in the mid-infrared region was detected. In summary, our study revealed that the calving season of dairy cows can be used to optimize the reproduction management. The potential application of mid-infrared spectroscopy in dairy cows needs to be further developed.

Progress and opportunities through use of genomics in animal production

The rearing of farmed animals is a vital component of global food production systems, but its impact on the environment, human health, animal welfare, and biodiversity is being increasingly challenged. Developments in genetic and genomic technologies have had a key role in improving the productivity of farmed animals for decades. Advances in genome sequencing, annotation, and editing offer a means not only to continue that trend, but also, when combined with advanced data collection, analytics, cloud computing, appropriate infrastructure, and regulation, to take precision livestock farming (PLF) and conservation to an advanced level. Such an approach could generate substantial additional benefits in terms of reducing use of resources, health treatments, and environmental impact, while also improving animal health and welfare.

Artificial Intelligence Models for Zoonotic Pathogens: A Survey

Zoonotic diseases or zoonoses are infections due to the natural transmission of pathogens between species (animals and humans). More than 70% of emerging infectious diseases are attributed to animal origin. Artificial Intelligence (AI) models have been used for studying zoonotic pathogens and the factors that contribute to their spread. The aim of this literature survey is to synthesize and analyze machine learning, and deep learning approaches applied to study zoonotic diseases to understand predictive models to help researchers identify the risk factors, and develop mitigation strategies. Based on our survey findings, machine learning and deep learning are commonly used for the prediction of both foodborne and zoonotic pathogens as well as the factors associated with the presence of the pathogens.

Use of Milk Infrared Spectral Data as Environmental Covariates in Genomic Prediction Models for Production Traits in Canadian Holstein

The purpose of this study was to provide a procedure for the inclusion of milk spectral information into genomic prediction models. Spectral data were considered a set of covariates, in addition to genomic covariates. Milk yield and somatic cell score were used as traits to investigate. A cross-validation was employed, making a distinction for predicting new individuals' performance under known environments, known individuals' performance under new environments, and new individuals' performance under new environments. We found an advantage of including spectral data as environmental covariates when the genomic predictions had to be extrapolated to new environments. This was valid for both observed and, even more, unobserved families (genotypes). Overall, prediction accuracy was larger for milk yield than somatic cell score. Fourier-transformed infrared spectral data can be used as a source of information for the calculation of the 'environmental coordinates' of a given farm in a given time, extrapolating predictions to new environments. This procedure could serve as an example of integration of genomic and phenomic data. This could help using spectral data for traits that present poor predictability at the phenotypic level, such as disease incidence and behavior traits. The strength of the model is the ability to couple genomic with high-throughput phenomic information.

Effectiveness of visible - Near infrared spectroscopy coupled with simulated annealing partial least squares analysis to predict immunoglobulins G, A, and M concentration in bovine colostrum

Visible - near infrared spectroscopy coupled with variable selection using simulated annealing PLS regression was tested to predict immunoglobulin fractions (g/L) of bovine colostrum, namely IgG, IgA and IgM. Immunoglobulins were quantified in 678 samples using the gold standard radial immunodiffusion. Samples were divided in calibration (50%) and validation (50%) datasets. Maximum number of selected variables were limited to 200 and root mean squared error in cross validation (RMSE_CV) was used as loss function. Performance of the final model developed using the calibration dataset was assessed on the validation dataset. Overall, simulated annealing PLS improved validation RMSE_CV compared to ordinary PLS regression by 3% to 17%. The present study demonstrated the effectiveness of the calibration model for accurate quantification of IgG, the most abundant immunoglobulin of bovine colostrum (RMSE_CV = 13.28 g/L; R² = 0.83). These outcomes could be useful to assess colostrum quality intended for animal and human usage.

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.

Leveraging AI in Photonics and Beyond

Artificial intelligence (AI) techniques have been spreading in most scientific areas and have become a heated focus in photonics research in recent years. Forward modeling and inverse design using AI can achieve high efficiency and accuracy for photonics components. With AI-assisted electronic circuit design for photonics components, more advanced photonics applications have emerged. Photonics benefit a great deal from AI, and AI, in turn, benefits from photonics by carrying out AI algorithms, such as complicated deep neural networks using photonics components that use photons rather than electrons. Beyond the photonics domain, other related research areas or topics governed by Maxwell’s equations share remarkable similarities in using the help of AI. The studies in computational electromagnetics, the design of microwave devices, as well as their various applications greatly benefit from AI. This article reviews leveraging AI in photonics modeling, simulation, and inverse design; leveraging photonics computing for implementing AI algorithms; and leveraging AI beyond photonics topics, such as microwaves and quantum-related topics.

Over 20 Years of Machine Learning Applications on Dairy Farms: A Comprehensive Mapping Study

Machine learning applications are becoming more ubiquitous in dairy farming decision support applications in areas such as feeding, animal husbandry, healthcare, animal behavior, milking and resource management. Thus, the objective of this mapping study was to collate and assess studies published in journals and conference proceedings between 1999 and 2021, which applied machine learning algorithms to dairy farming-related problems to identify trends in the geographical origins of data, as well as the algorithms, features and evaluation metrics and methods used. This mapping study was carried out in line with PRISMA guidelines, with six pre-defined research questions (RQ) and a broad and unbiased search strategy that explored five databases. In total, 129 publications passed the pre-defined selection criteria, from which relevant data required to answer each RQ were extracted and analyzed. This study found that Europe (43% of studies) produced the largest number of publications (RQ1), while the largest number of articles were published in the Computers and Electronics in Agriculture journal (21%) (RQ2). The largest number of studies addressed problems related to the physiology and health of dairy cows (32%) (RQ3), while the most frequently employed feature data were derived from sensors (48%) (RQ4). The largest number of studies employed tree-based algorithms (54%) (RQ5), while RMSE (56%) (regression) and accuracy (77%) (classification) were the most frequently employed metrics used, and hold-out cross-validation (39%) was the most frequently employed evaluation method (RQ6). Since 2018, there has been more than a sevenfold increase in the number of studies that focused on the physiology and health of dairy cows, compared to almost a threefold increase in the overall number of publications, suggesting an increased focus on this subdomain. In addition, a fivefold increase in the number of publications that employed neural network algorithms was identified since 2018, in comparison to a threefold increase in the use of both tree-based algorithms and statistical regression algorithms, suggesting an increasing utilization of neural network-based algorithms.

Automated Processing and Phenotype Extraction of Ovine Medical Images Using a Combined Generative Adversarial Network and Computer Vision Pipeline

The speed and accuracy of phenotype detection from medical images are some of the most important qualities needed for any informed and timely response such as early detection of cancer or detection of desirable phenotypes for animal breeding. To improve both these qualities, the world is leveraging artificial intelligence and machine learning against this challenge. Most recently, deep learning has successfully been applied to the medical field to improve detection accuracies and speed for conditions including cancer and COVID-19. In this study, we applied deep neural networks, in the form of a generative adversarial network (GAN), to perform image-to-image processing steps needed for ovine phenotype analysis from CT scans of sheep. Key phenotypes such as gigot geometry and tissue distribution were determined using a computer vision (CV) pipeline. The results of the image processing using a trained GAN are strikingly similar (a similarity index of 98%) when used on unseen test images. The combined GAN-CV pipeline was able to process and determine the phenotypes at a speed of 0.11 s per medical image compared to approximately 30 min for manual processing. We hope this pipeline represents the first step towards automated phenotype extraction for ovine genetic breeding programmes.

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.

Sequence-based genome-wide association study of individual milk mid-infrared wavenumbers in mixed-breed dairy cattle

BACKGROUND

Fourier-transform mid-infrared (FT-MIR) spectroscopy provides a high-throughput and inexpensive method for predicting milk composition and other novel traits from milk samples. While there have been many genome-wide association studies (GWAS) conducted on FT-MIR predicted traits, there have been few GWAS for individual FT-MIR wavenumbers. Using imputed whole-genome sequence for 38,085 mixed-breed New Zealand dairy cattle, we conducted GWAS on 895 individual FT-MIR wavenumber phenotypes, and assessed the value of these direct phenotypes for identifying candidate causal genes and variants, and improving our understanding of the physico-chemical properties of milk.

RESULTS

Separate GWAS conducted for each of 895 individual FT-MIR wavenumber phenotypes, identified 450 1-Mbp genomic regions with significant FT-MIR wavenumber QTL, compared to 246 1-Mbp genomic regions with QTL identified for FT-MIR predicted milk composition traits. Use of mammary RNA-seq data and gene annotation information identified 38 co-localized and co-segregating expression QTL (eQTL), and 31 protein-sequence mutations for FT-MIR wavenumber phenotypes, the latter including a null mutation in the ABO gene that has a potential role in changing milk oligosaccharide profiles. For the candidate causative genes implicated in these analyses, we examined the strength of association between relevant loci and each wavenumber across the mid-infrared spectrum. This revealed shared association patterns for groups of genomically-distant loci, highlighting clusters of loci linked through their biological roles in lactation and their presumed impacts on the chemical composition of milk.

CONCLUSIONS

This study demonstrates the utility of FT-MIR wavenumber phenotypes for improving our understanding of milk composition, presenting a larger number of QTL and putative causative genes and variants than found from FT-MIR predicted composition traits. Examining patterns of significance across the mid-infrared spectrum for loci of interest further highlighted commonalities of association, which likely reflects the physico-chemical properties of milk constituents.

Machine Learning in Agriculture: A Comprehensive Updated Review

The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords' combinations of "machine learning" along with "crop management", "water management", "soil management", and "livestock management", and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018-2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

Evaluating the performance of machine learning methods and variable selection methods for predicting difficult-to-measure traits in Holstein dairy cattle using milk infrared spectral data

Fourier-transform infrared (FTIR) spectroscopy is a powerful high-throughput phenotyping tool for predicting traits that are expensive and difficult to measure in dairy cattle. Calibration equations are often developed using standard methods, such as partial least squares (PLS) regression. Methods that employ penalization, rank-reduction, and variable selection, as well as being able to model the nonlinear relations between phenotype and FTIR, might offer improvements in predictive ability and model robustness. This study aimed to compare the predictive ability of 2 machine learning methods, namely random forest (RF) and gradient boosting machine (GBM), and penalized regression against PLS regression for predicting 3 phenotypes differing in terms of biological meaning and relationships with milk composition (i.e., phenotypes measurable directly and not directly in milk, reflecting different biological processes which can be captured using milk spectra) in Holstein-Friesian cattle under 2 cross-validation scenarios. The data set comprised phenotypic information from 471 Holstein-Friesian cows, and 3 target phenotypes were evaluated: (1) body condition score (BCS), (2) blood β-hydroxybutyrate (BHB, mmol/L), and (3) κ-casein expressed as a percentage of nitrogen (κ-CN, % N). The data set was split considering 2 cross-validation scenarios: samples-out random in which the population was randomly split into 10-folds (8-folds for training and 1-fold for validation and testing); and herd/date-out in which the population was randomly assigned to training (70% herd), validation (10%), and testing (20% herd) based on the herd and date in which the samples were collected. The random grid search was performed using the training subset for the hyperparameter optimization and the validation set was used for the generalization of prediction error. The trained model was then used to assess the final prediction in the testing subset. The grid search for penalized regression evidenced that the elastic net (EN) was the best regularization with increase in predictive ability of 5%. The performance of PLS (standard model) was compared against 2 machine learning techniques and penalized regression using 2 cross-validation scenarios. Machine learning methods showed a greater predictive ability for BCS (0.63 for GBM and 0.61 for RF), BHB (0.80 for GBM and 0.79 for RF), and κ-CN (0.81 for GBM and 0.80 for RF) in samples-out cross-validation. Considering a herd/date-out cross-validation these values were 0.58 (GBM and RF) for BCS, 0.73 (GBM and RF) for BHB, and 0.77 (GBM and RF) for κ-CN. The GBM model tended to outperform other methods in predictive ability around 4%, 1%, and 7% for EN, RF, and PLS, respectively. The prediction accuracies of the GBM and RF models were similar, and differed statistically from the PLS model in samples-out random cross-validation. Although, machine learning techniques outperformed PLS in herd/date-out cross-validation, no significant differences were observed in terms of predictive ability due to the large standard deviation observed for predictions. Overall, GBM achieved the highest accuracy of FTIR-based prediction of the different phenotypic traits across the cross-validation scenarios. These results indicate that GBM is a promising method for obtaining more accurate FTIR-based predictions for different phenotypes in dairy cattle.

Evaluating the Bovine Tuberculosis Eradication Mechanism and Its Risk Factors in England's Cattle Farms

Controlling bovine tuberculosis (bTB) disease in cattle farms in England is seen as a challenge for farmers, animal health, environment and policy-makers. The difficulty in diagnosis and controlling bTB comes from a variety of factors: the lack of an accurate diagnostic test which is higher in specificity than the currently available skin test; isolation periods for purchased cattle; and the density of active badgers, especially in high-risk areas. In this paper, to enable the complex evaluation of bTB disease, a dynamic Bayesian network (DBN) is designed with the help of domain experts and available historical data. A significant advantage of this approach is that it represents bTB as a dynamic process that evolves periodically, capturing the actual experience of testing and infection over time. Moreover, the model demonstrates the influence of particular risk factors upon the risk of bTB breakdown in cattle farms.

Predicting pregnancy status from mid-infrared spectroscopy in dairy cow milk using deep learning

Accurately identifying pregnancy status is imperative for a profitable dairy enterprise. Mid-infrared (MIR) spectroscopy is routinely used to determine fat and protein concentrations in milk samples. Mid-infrared spectra have successfully been used to predict other economically important traits, including fatty acid content, mineral content, body energy status, lactoferrin, feed intake, and methane emissions. Machine learning has been used in a variety of fields to find patterns in vast quantities of data. This study aims to use deep learning, a sub-branch of machine learning, to establish pregnancy status from routinely collected milk MIR spectral data. Milk spectral data were obtained from National Milk Records (Chippenham, UK), who collect large volumes of data continuously on a monthly basis. Two approaches were followed: using genetic algorithms for feature selection and network design (model 1), and transfer learning with a pretrained DenseNet model (model 2). Feature selection in model 1 showed that the number of wave points in MIR data could be reduced from 1,060 to 196 wave points. The trained model converged after 162 epochs with validation accuracy and loss of 0.89 and 0.18, respectively. Although the accuracy was sufficiently high, the loss (in terms of predicting only 2 labels) was considered too high and suggested that the model would not be robust enough to apply to industry. Model 2 was trained in 2 stages of 100 epochs each with spectral data converted to gray-scale images and resulted in accuracy and loss of 0.97 and 0.08, respectively. Inspection on inference data showed prediction sensitivity of 0.89, specificity of 0.86, and prediction accuracy of 0.88. Results indicate that milk MIR data contains features relating to pregnancy status and the underlying metabolic changes in dairy cows, and such features can be identified by means of deep learning. Prediction equations from trained models can be used to alert farmers of nonviable pregnancies as well as to verify conception dates.