Symposium review: Challenges and opportunities for evaluating and using the genetic potential of dairy cattle in the new era of sensor data from automation

Validation of a leg-mounted pedometer for the measurement of steps in lactating Holstein cows

The aim of this study was to validate the pedometer AfiAct II (AfiMilk) for the measurement of steps in lactating Holstein cows housed in a freestall design by assessing its agreement with visual observation of step counts. A total of 41 primiparous (n = 12) and multiparous (n = 29) cows were enrolled in the study between August and September 2018. Steps were monitored continuously by the pedometer and visually assessed for a 24-h period using video recordings. Visually observed steps were categorized as walking and stationary steps. The total number of steps taken per cow was calculated using the sum of walking and stationary steps. Unprocessed step count data from the study day were retrieved from the AfiMilk system in time-blocks of approximately 15 min. Repeated measures correlation was used to quantify the association between the pedometer measurements and visual observation of step counts. Nonindependence among observations were accounted adjusting for interindividual (cow) variability with an analysis of covariance. Pearson correlation coefficients (r) were categorized from negligible (0.00-0.30) to very high (0.90-1.00). Bland-Altman plots were created to evaluate the bias between the pedometer and visual observations. A total of 2,261 time-blocks were used in this study with an average (mean ± standard deviation) of 55.14 ± 8.1 time-blocks per cow. A high correlation was found for the evaluation between the pedometer and observed walking steps (r = 0.74; 95% confidence interval [CI] = 0.73-0.76), stationary steps (r = 0.71; 95% CI = 0.69-0.63), and total steps (r = 0.88; 95% CI = 0.87-0.89). The results of the Bland-Altman plot suggested limited bias between the pedometer step counts and visual observation of steps, independent of the type of steps. Numerical differences and several time-block differences outside of the 95% interval of agreement suggested an overestimation of step counts by the pedometer, which increased as the number of steps increased. The pedometer measured, on average, 97.6 ± 118.5 (28%), 249.2 ± 126.2 (125%), and 297.2 ± 205.4 (196%) steps/day more than the visual observed total steps, stationary steps, and walking steps, respectively. Our findings indicate that the pedometer counts all movement in which the pedometer leg is lifted off the floor without distinguishing if there was body movement of the animal.

The Development of Smart Dairy Farm System and Its Application in Nutritional Grouping and Mastitis Prediction

In order to study the smart management of dairy farms, this study combined Internet of Things (IoT) technology and dairy farm daily management to form an intelligent dairy farm sensor network and set up a smart dairy farm system (SDFS), which could provide timely guidance for dairy production. To illustrate the concept and benefits of the SDFS, two application scenarios were sampled: (1) Nutritional grouping (NG): grouping cows according to the nutritional requirements by considering parities, days in lactation, dry matter intake (DMI), metabolic protein (MP), net energy of lactation (NEL), etc. By supplying feed corresponding to nutritional needs, milk production, methane and carbon dioxide emissions were compared with those of the original farm grouping (OG), which was grouped according to lactation stage. (2) Mastitis risk prediction: using the dairy herd improvement (DHI) data of the previous 4 lactation months of the dairy cows, logistic regression analysis was applied to predict dairy cows at risk of mastitis in successive months in order to make suitable measurements in advance. The results showed that compared with OG, NG significantly increased milk production and reduced methane and carbon dioxide emissions of dairy cows (p < 0.05). The predictive value of the mastitis risk assessment model was 0.773, with an accuracy of 89.91%, a specificity of 70.2%, and a sensitivity of 76.3%. By applying the intelligent dairy farm sensor network and establishing an SDFS, through intelligent analysis, full use of dairy farm data would be made to achieve higher milk production of dairy cows, lower greenhouse gas emissions, and predict in advance the occurrence of mastitis of dairy cows.

Precision Livestock Farming: What Does It Contain and What Are the Perspectives?

Precision Livestock Farming (PLF) describes the combined use of sensor technology, the related algorithms, interfaces, and applications in animal husbandry. PLF technology is used in all animal production systems and most extensively described in dairy farming. PLF is developing rapidly and is moving beyond health alarms towards an integrated decision-making system. It includes animal sensor and production data but also external data. Various applications have been proposed or are available commercially, only a part of which has been evaluated scientifically; the actual impact on animal health, production and welfare therefore remains largely unknown. Although some technology has been widely implemented (e.g., estrus detection and calving detection), other systems are adopted more slowly. PLF offers opportunities for the dairy sector through early disease detection, capturing animal-related information more objectively and consistently, predicting risks for animal health and welfare, increasing the efficiency of animal production and objectively determining animal affective states. Risks of increasing PLF usage include the dependency on the technology, changes in the human-animal relationship and changes in the public perception of dairy farming. Veterinarians will be highly affected by PLF in their professional life; they nevertheless must adapt to this and play an active role in further development of technology.

Invited review: integration of technologies and systems for precision animal agriculture-a case study on precision dairy farming

Precision livestock farming (PLF) offers a strategic solution to enhance the management capacity of large animal groups, while simultaneously improving profitability, efficiency, and minimizing environmental impacts associated with livestock production systems. Additionally, PLF contributes to optimizing the ability to manage and monitor animal welfare while providing solutions to global grand challenges posed by the growing demand for animal products and ensuring global food security. By enabling a return to the "per animal" approach by harnessing technological advancements, PLF enables cost-effective, individualized care for animals through enhanced monitoring and control capabilities within complex farming systems. Meeting the nutritional requirements of a global population exponentially approaching ten billion people will likely require the density of animal proteins for decades to come. The development and application of digital technologies are critical to facilitate the responsible and sustainable intensification of livestock production over the next several decades to maximize the potential benefits of PLF. Real-time continuous monitoring of each animal is expected to enable more precise and accurate tracking and management of health and well-being. Importantly, the digitalization of agriculture is expected to provide collateral benefits of ensuring auditability in value chains while assuaging concerns associated with labor shortages. Despite notable advances in PLF technology adoption, a number of critical concerns currently limit the viability of these state-of-the-art technologies. The potential benefits of PLF for livestock management systems which are enabled by autonomous continuous monitoring and environmental control can be rapidly enhanced through an Internet of Things approach to monitoring and (where appropriate) closed-loop management. In this paper, we analyze the multilayered network of sensors, actuators, communication, networking, and analytics currently used in PLF, focusing on dairy farming as an illustrative example. We explore the current state-of-the-art, identify key shortcomings, and propose potential solutions to bridge the gap between technology and animal agriculture. Additionally, we examine the potential implications of advancements in communication, robotics, and artificial intelligence on the health, security, and welfare of animals.

Development of resilience indicator traits based on daily step count data for dairy cattle breeding

Background

Resilient animals are minimally affected by disturbances, such as diseases and heat stress, and quickly recover. Daily activity data can potentially indicate resilience, because resilient animals likely keep variations due to disturbances that threat animal homeostasis at a low magnitude. We used daily step count of cows to define resilience indicators based on theory, exploratory analysis and literature, and then investigated if they can be used to genetically improve resilience by estimating heritability and repeatability, and genetic associations with other resilience-related traits, i.e. health traits, longevity, fertility, and body condition score (BCS).

Results

Two groups of resilience indicators were defined: indicators describing (1) mean step count at different lactation stages for individual cows, and (2) fluctuations in step count from individual step count curves. Heritability estimates were highest for resilience indicators describing mean step count, from 0.22 for the 2-week period pre-partum to 0.45 for the whole lactation. High mean step count was consistently, but weakly, genetically correlated with good health, fertility, and longevity, and high BCS. Heritability estimates of resilience indicators describing fluctuations ranged from 0.01 for number of step count drops to 0.15 for the mean of negative residuals from individual curves. Genetic correlations with health traits, longevity, fertility, and BCS were mostly weak, but were moderate and favorable for autocorrelation of residuals (− 0.33 to − 0.44) and number of step count drops (− 0.44 to − 0.56) with hoof health, fertility, and BCS. Resilience indicators describing variability of residuals and mean of negative residuals showed strong genetic correlations with mean step count (0.86 to 0.95, absolute), which suggests that adjustment for step count level is needed. After adjustment, ‘mean of negative residuals’ was highly genetically correlated with hoof health, fertility, and BCS.

Conclusions

Mean step count, autocorrelation and mean of negative residuals showed most potential as resilience indicators based on resilience theory, heritability, and genetic associations with health, fertility, and body condition score. Other resilience indicators were heritable, but had unfavorable genetic correlations with several health traits. This study is an important first step in the exploration of the use of activity data to breed more resilient livestock.

Data Governance in the Dairy Industry

Simple Summary

There are no existing laws that regulate data usage in the dairy industry in the U.S. Therefore, challenges regarding data management, availability, use, and security are a growing concern. These concerns are especially important in the light of the growing dependency and monetization of such data. Although some codes of practices have been published, these are voluntary, which makes them legally vulnerable and without guarantees under the law. Thus, in this paper, we propose creating a Farmers Bill of Rights to standardize data governance and data regulations and to promote an equitable relationship of dairy data governance between farmers, industry professionals, and companies.

Abstract

Data governance is a growing concern in the dairy farm industry because of the lack of legal regulation. In this commentary paper, we discuss the status quo of the available legislation and codes, as well as some possible solutions. To our knowledge, there are currently four codes of practice that address agriculture data worldwide, and their objectives are similar: (1) raise awareness of diverse data challenges such as data sharing and data privacy, (2) provide data security, and (3) illustrate the importance of the transparency of terms and conditions of data sharing contracts. However, all these codes are voluntary, which limits their adoption. We propose a Farmers Bill of Rights for the dairy data ecosystem to address some key components around data ownership and transparency in data sharing. Our hope is to start the discussion to create a balanced environment to promote equity within the data economy, encourage proper data stewardship, and to foster trust and harmony between the industry companies and the farmers when it comes to sharing data.

Review: Genetic selection of high-yielding dairy cattle toward sustainable farming systems in a rapidly changing world

The massive improvement in food production, as a result of effective genetic selection combined with advancements in farming practices, has been one of the greatest achievements of modern agriculture. For instance, the dairy cattle industry has more than doubled milk production over the past five decades, while the total number of cows has been reduced dramatically. This was achieved mainly through the intensification of production systems, direct genetic selection for milk yield and a limited number of related traits, and the use of modern technologies (e.g., artificial insemination and genomic selection). Despite the great betterment in production efficiency, strong drawbacks have occurred along the way. First, across-breed genetic diversity reduced dramatically, with the worldwide use of few common dairy breeds, as well as a substantial reduction in within-breed genetic diversity. Intensive selection for milk yield has also resulted in unfavorable genetic responses for traits related to fertility, health, longevity, and environmental sensitivity. Moving forward, the dairy industry needs to continue refining the current selection indexes and breeding goals to put greater emphasis on traits related to animal welfare, health, longevity, environmental efficiency (e.g., methane emission and feed efficiency), and overall resilience. This needs to be done through the definition of criteria (traits) that (a) represent well the biological mechanisms underlying the respective phenotypes, (b) are heritable, and (c) can be cost-effectively measured in a large number of animals and as early in life as possible. The long-term sustainability of the dairy cattle industry will also require diversification of production systems, with greater investments in the development of genetic resources that are resilient to perturbations occurring in specific farming systems with lesser control over the environment (e.g., organic, agroecological, and pasture-based, mountain-grazing farming systems). The conservation, genetic improvement, and use of local breeds should be integrated into the modern dairy cattle industry and greater care should be taken to avoid further genetic diversity losses in dairy cattle populations. In this review, we acknowledge the genetic progress achieved in high-yielding dairy cattle, closely related to dairy farm intensification, that reaches its limits. We discuss key points that need to be addressed toward the development of a robust and long-term sustainable dairy industry that maximize animal welfare (fundamental needs of individual animals and positive welfare) and productive efficiency, while also minimizing the environmental footprint, inputs required, and sensitivity to external factors.

Unraveling the Relationship between Milk Yield and Quality at the Test Day with Rumination Time Recorded by a PLF Technology

Simple Summary

Precision livestock farming, by real time monitoring of dairy cows, has the potential to generate a huge amount of data to be used for farm management purposes, as well as in breeding programs. Daily rumination time (RT) recorded by commercial systems is promising in this context because it may be related to individual milk yield and composition. However, it is necessary to assess the ability of sensor data to be used in a predictive model, but also to evaluate and standardize the correct phenotypes, and how they are related to individual variability rather than from other sources. RT data and milk test day (TD) records collected from 691 cows, monitored for thirteen months, were analyzed for the already mentioned goals and to better characterize the effect of high-, medium- and low-level daily RT on milk yield and composition. Our results showed that “animal” in a farm major contributed to the RT total variability, confirming a possible use in breeding program. The higher RT class reported the best productive performance for milk and each solid yield, in spite of a small reduction in their contents, and appears to be related to a higher degree of saturation in the fatty acid profile.

Abstract

The study aimed to estimate the components of rumination time (RT) variability recorded by a neck collar sensor and the relationship between RT and milk composition. Milk test day (TD) and RT data were collected from 691 cows in three farms. Daily RT data of each animal were averaged for 3, 7, and 10 days preceding the TD date (RT_D). Variance component analysis of RT_D, considering the effects of farm, cow, parity, TD date, and lactation phase, showed that a farm, followed by a cow, had major contributions to the total variability. The RT₁₀ variable best performed on TD milk yield and quality records across models by a multi-model inference approach and was adopted to study its relationship with milk traits, by linear mixed models, through a 3-level stratification: low (LRT₁₀ ≤ 8 h/day), medium (8 h/day < MRT₁₀ ≤ 9 h/day), and high (HRT₁₀ > 9 h/day) RT. Cows with HRT₁₀ had greater milk, fat, protein, casein, and lactose daily yield, and lower fat, protein, casein contents, and fat to protein ratio compared to MRT₁₀ and LRT₁₀. Higher percentages of saturated fatty acid and lower unsaturated and monounsaturated fatty acid were found in HRT₁₀, with respect to LRT₁₀ and MRT₁₀ observations.

Short communication: Investigation of the temporal relationships between milk mid-infrared predicted biomarkers and lameness events in later lactation

This study reports on the exploration of temporal relationships between milk mid-infrared predicted biomarkers and lameness events. Lameness in dairy cows is an issue that can vary greatly in severity and is of concern for both producers and consumers. Metabolic disorders are often associated with lameness. However, lameness can arise weeks or even months after the metabolic disorder, making the detection of causality difficult. We already use mid-infrared technology to predict major milk components, such as fat or protein, during routine milk recording and for milk payment. It was recently shown that this technology can also be used to predict novel biomarkers linked to metabolic disorders in cows, such as oleic acid (18:1 cis-9), β-hydroxybutyrate, acetone, and citrate in milk. We used these novel biomarkers as proxies for metabolic issues. Other studies have explored the possibility of using mid-infrared spectra to predict metabolic diseases and found it (potentially) usable for indicating classes of metabolic problems. We wanted to explore the possible relationship between mid-infrared-based metabolites and lameness over the course of lactation. In total, data were recorded from 6,292 cows on 161 farms in Austria. Lameness data were recorded between March 2014 and March 2015 and consisted of 37,555 records. Mid-infrared data were recorded between July and December 2014 and consisted of 9,152 records. Our approach consisted of fitting preadjustments to the data using fixed effects, computing pair-wise correlations, and finally applying polynomial smoothing of the correlations for a given biomarker at a certain month in lactation and the lameness events scored on severity scale from sound or non-lame (lameness score of 1) to severely lame (lameness score of 5) throughout the lactation. The final correlations between biomarkers and lameness scores were significant, but not high. However, for the results of the present study, we should not look at the correlations in terms of absolute values, but rather as indicators of a relationship through time. When doing so, we can see that metabolic problems occurring in mo 1 and 3 seem more linked to long-term effects on hoof and leg health than those in mo 2. However, the quantity (only 1 pair-wise correlation exceeded 1,000 observations) and the quality (due to limited data, no separation according to more metabolic-related diseases could be done) of the data should be improved.