Invited review: sensors to support health management on dairy farms

Precision Detection of Real-Time Conditions of Dairy Cows Using an Advanced Artificial Intelligence Hub

One of the main challenges in the adoption of artificial intelligence-based tools, such as integrated decision support systems, is the complexities of their application. This study aimed to define the relevant parameters that can be used as indicators for real-time detection of heat stress and subclinical mastitis in dairy cows. Moreover, this study aimed to demonstrate the use of a developed data-mining hub as an artificial intelligence-based tool that integrates the defined relevant information (parameters or traits) in accurately identifying the condition of the cow. A comprehensive theoretical framework of the data-mining hub is demonstrated, the selection of the parameters that were used for the data-mining hub is listed, and the relevance of the traits is discussed. The practical application of the data-mining hub has shown that using 21 parameters instead of 13 and 8 parameters resulted in a high overall accuracy of detecting heat stress and subclinical mastitis in dairy cows with a high precision effect reflecting a low percentage of misclassifying the conditions of the dairy cows. This study has developed an innovative approach in which combined information from different independent data was used to accurately detect the health and wellness status of the dairy cows. It can also be implied that an artificial intelligence-based tool such as the proposed theoretical data-mining hub of dairy cows could maximize the use of continuously generated and underutilized data in farms, thus ultimately simplifying repetitive and difficult decision-making tasks in dairy farming.

A Systematic Review of Automatic Health Monitoring in Calves: Glimpsing the Future From Current Practice

Infectious diseases, particularly bovine respiratory disease (BRD) and neonatal calf diarrhea (NCD), are prevalent in calves. Efficient health-monitoring tools to identify such diseases on time are lacking. Common practice (i.e., health checks) often identifies sick calves at a late stage of disease or not at all. Sensor technology enables the automatic and continuous monitoring of calf physiology or behavior, potentially offering timely and precise detection of sick calves. A systematic overview of automated disease detection in calves is still lacking. The objectives of this literature review were hence: to investigate previously applied sensor validation methods used in the context of calf health, to identify sensors used on calves, the parameters these sensors monitor, and the statistical tools applied to identify diseases, to explore potential research gaps and to point to future research opportunities. To achieve these objectives, systematic literature searches were conducted. We defined four stages in the development of health-monitoring systems: (1) sensor technique, (2) data interpretation, (3) information integration, and (4) decision support. Fifty-four articles were included (stage one: 26; stage two: 19; stage three: 9; and stage four: 0). Common parameters that assess the performance of these systems are sensitivity, specificity, accuracy, precision, and negative predictive value. Gold standards that typically assess these parameters include manual measurement and manual health-assessment protocols. At stage one, automatic feeding stations, accelerometers, infrared thermography cameras, microphones, and 3-D cameras are accurate in screening behavior and physiology in calves. At stage two, changes in feeding behaviors, lying, activity, or body temperature corresponded to changes in health status, and point to health issues earlier than manual health checks. At stage three, accelerometers, thermometers, and automatic feeding stations have been integrated into one system that was shown to be able to successfully detect diseases in calves, including BRD and NCD. We discuss these findings, look into potentials at stage four, and touch upon the topic of resilience, whereby health-monitoring system might be used to detect low resilience (i.e., prone to disease but clinically healthy calves), promoting further improvements in calf health and welfare.

Adoption of Precision Technologies by Brazilian Dairy Farms: The Farmer's Perception

The use of precision farming technologies, such as milking robots, automated calf feeders, wearable sensors, and others, has significantly increased in dairy operations over the last few years. The growing interest in farming technologies to reduce labor, maximize productivity, and increase profitability is becoming noticeable in several countries, including Brazil. Information regarding technology adoption, perception, and effectiveness in dairy farms could shed light on challenges that need to be addressed by scientific research and extension programs. The objective of this study was to characterize Brazilian dairy farms based on technology usage. Factors such as willingness to invest in precision technologies, adoption of sensor systems, farmer profile, farm characteristics, and production indexes were investigated in 378 dairy farms located in Brazil. A survey with 22 questions was developed and distributed via Google Forms from July 2018 to July 2020. The farms were then classified into seven clusters: (1) top yield farms; (2) medium-high yield, medium-tech; (3) medium yield and top high-tech; (4) medium yield and medium-tech; (5) young medium-low yield and low-tech; (6) elderly medium-low yield and low-tech; and (7) low-tech grazing. The most frequent technologies adopted by producers were milk meters systems (31.7%), milking parlor smart gate (14.5%), sensor systems to detect mastitis (8.4%), cow activity meter (7.1%), and body temperature (7.9%). Based on a scale containing numerical values (1-5), producers indicated "available technical support" (mean; σ²) (4.55; 0.80) as the most important decision criterion involved in adopting technology, followed by "return on investment-ROI" (4.48; 0.80), "user-friendliness" (4.39; 0.88), "upfront investment cost" (4.36; 0.81), and "compatibility with farm management software" (4.2; 1.02). The most important factors precluding investment in precision dairy technologies were the need for investment in other sectors of the farm (36%), the uncertainty of ROI (24%), and lack of integration with other farm systems and software (11%). Farmers indicated that the most useful technologies were automatic milk meters systems (mean; σ²) (4.05; 1.66), sensor systems for mastitis detection (4.00; 1.57), automatic feeding systems (3.50; 2.05), cow activity meter (3.45; 1.95), and in-line milk analyzers (3.45; 1.95). Overall, the concerns related to data integration, ROI, and user-friendliness of technologies are similar to those of dairy farms located in other countries. Increasing available technical support for sensing technology can have a positive impact on technology adoption.

Control of sheep flystrike: what's been tried in the past and where to from here

Flystrike remains a serious financial and animal welfare issue for the sheep industry in Australia despite many years of research into control methods. The present paper provides an extensive review of past research on flystrike, and highlights areas that hold promise for providing long-term control options. We describe areas where the application of modern scientific advances may provide increased impetus to some novel, as well as some previously explored, control methods. We provide recommendations for research activities: insecticide resistance management, novel delivery methods for therapeutics, improved breeding indices for flystrike-related traits, mechanism of nematode-induced scouring in mature animals. We also identify areas where advances can be made in flystrike control through the greater adoption of well-recognised existing management approaches: optimal insecticide-use patterns, increased use of flystrike-related Australian Sheep Breeding Values, and management practices to prevent scouring in young sheep. We indicate that breeding efforts should be primarily focussed on the adoption and improvement of currently available breeding tools and towards the future integration of genomic selection methods. We describe factors that will impact on the ongoing availability of insecticides for flystrike control and on the feasibility of vaccination. We also describe areas where the blowfly genome may be useful in providing impetus to some flystrike control strategies, such as area-wide approaches that seek to directly suppress or eradicate sheep blowfly populations. However, we also highlight the fact that commercial and feasibility considerations will act to temper the potential for the genome to act as the basis for providing some control options.

Integrating diverse data sources to predict disease risk in dairy cattle-a machine learning approach

Livestock farming is currently undergoing a digital revolution and becoming increasingly data-driven. Yet, such data often reside in disconnected silos making them impossible to leverage their full potential to improve animal well-being. Here, we introduce a precision livestock farming approach, bringing together information streams from a variety of life domains of dairy cattle to study whether including more and diverse data sources improves the quality of predictions for eight diseases and whether using more complex prediction algorithms can, to some extent, compensate for less diverse data. Using three machine learning approaches of varying complexity (from logistic regression to gradient boosted trees) trained on data from 5,828 animals in 165 herds in Austria, we show that the prediction of lameness, acute and chronic mastitis, anestrus, ovarian cysts, metritis, ketosis (hyperketonemia), and periparturient hypocalcemia (milk fever) from routinely available data gives encouraging results. For example, we can predict lameness with high sensitivity and specificity (F1 = 0.74). An analysis of the importance of individual variables to prediction performance shows that disease in dairy cattle is a product of the complex interplay between a multitude of life domains, such as housing, nutrition, or climate, that including more and diverse data sources increases prediction performance, and that the reuse of existing data can create actionable information for preventive interventions. Our findings pave the way toward data-driven point-of-care interventions and demonstrate the added value of integrating all available data in the dairy industry to improve animal well-being and reduce disease risk.

Validation of a Commercial Collar-Based Sensor for Monitoring Eating and Ruminating Behaviour of Dairy Cows

The use of sensor technologies to monitor cows' behavior is becoming commonplace in the context of dairy production. This study aimed at validating a commercial collar-based sensor system, the AFICollar^® (Afimilk, Kibbutz Afikim, Israel), designed to monitor dairy cattle feeding and ruminating behavior. Additionally, the performances of two versions of the software for behavior classification, the current software AFIfarm^® 5.4 and the updated version AFIfarm^® 5.5, were compared. The study involved twenty Holstein-Friesian cows fitted with the collars. To evaluate the sensor performance under different feeding scenarios, the animals were divided into four groups and fed three different types of feed (total mixed ration, long hay, animals allowed to graze). Recordings of hourly rumination and feeding time produced by the sensor were compared with visual observation by scan sampling at 1 minute intervals using Spearman correlation, concordance correlation coefficient (CCC), Bland-Altman plots and linear mixed models for assessing the precision and accuracy of the system. The analyses confirmed that the updated software version V5.5 produced better detection performance than the current V5.4. The updated software version produced high correlations between visual observations and data recorded by the sensor for both feeding (r = 0.85, CCC = 0.86) and rumination (r = 0.83, CCC = 0.86). However, the limits of agreement for both behaviors remained quite wide (feeding: -19.60 min/h, 17.46 min/h; rumination: -15.80 min/h, 15.00 min/h). Type of feed did not produce significant effects on the agreement between visual observations and sensor recordings. Overall, the results indicate that the system can provide farmers with adequately accurate data on feeding and rumination time, and can be used to support herd management decisions. Despite all this, the precision of the system remained relatively limited, and should be improved with further developments in the classification algorithm.

Wearable Wireless Biosensor Technology for Monitoring Cattle: A Review

The review aimed to collect information about the wearable wireless sensor system (WWSS) for cattle and to conduct a systematic literature review on the accuracy of predicting the physiological parameters of these systems. The WWSS was categorized as an ear tag, halter, neck collar, rumen bolus, leg tag, tail-mounted, and vaginal mounted types. Information was collected from a web-based search on Google, then manually curated. We found about 60 WWSSs available in the market; most sensors included an accelerometer. The literature evaluating the WWSS performance was collected through a keyword search in Scopus. Among the 1875 articles identified, 46 documents that met our criteria were selected for further meta-analysis. Meta-analysis was conducted on the performance values (e.g., correlation, sensitivity, and specificity) for physiological parameters (e.g., feeding, activity, and rumen conditions). The WWSS showed high performance in most parameters, although some parameters (e.g., drinking time) need to be improved, and considerable heterogeneity of performance levels was observed under various conditions (average I² = 76%). Nevertheless, some of the literature provided insufficient information on evaluation criteria, including experimental conditions and gold standards, to confirm the reliability of the reported performance. Therefore, guidelines for the evaluation criteria for studies evaluating WWSS performance should be drawn up.

Moving towards sustainable breeding objectives and cow welfare in dairy production: a South African perspective

Genetic advancements have resulted in improved dairy production over many decades, due to the focus of breeding objectives on production as the driving force for genetic progress and overall farm profitability. Major advancements were made in the easy-to-measure traits with moderate to high heritability, which resulted in unintended consequences on herd fertility, health, and welfare of cows. In addition, climate change and animal welfare concerns demanded balanced breeding objectives and selection approaches for sustainable production-including health and longevity. The inclusion of genomic information into genetic evaluations has been proved to benefit traits associated with welfare and sustainable production. Cow welfare traits remain complex and suitable phenotypes are not always easy to measure or readily available for genetic evaluations. The challenge for improvement of cow welfare often lies within implementation of sensitive and measurable parameters. The aim of this review was to explore the reconsideration of breeding objectives in the dairy industry towards sustainable dairy production and cow welfare with reference to selection of dairy animals in South Africa.

Efficacy of statistical process control procedures to identify deviations in continuously measured physiological and behavioral variables in beef heifers resulting from an experimentally combined viral-bacterial challenge

The objective of this experiment was to determine if statistical process control (SPC) procedures coupled with remote continuous data collection could accurately differentiate between animals experimentally inoculated with a viral-bacterial (VB) challenge or phosphate buffer solution (PBS). Crossbred heifers (N = 38; BW = 230 ± 16.4 kg) were randomly assigned to treatments by initial weight, average daily gain (ADG), bovine herpes virus 1, and Mannheimia haemolytica serum titers. Feeding behavior, dry matter intake (DMI), animal activity, and rumen temperature were continuously monitored remotely prior to and following VB challenge. VB-challenged heifers exhibited decreased (P < 0.01) ADG and DMI, as well as increased (P < 0.01) neutrophils and rumen temperature consistent with a bovine respiratory disease (BRD) infection. However, none of the heifers displayed overt clinical signs of disease. Shewhart and cumulative summation (CUSUM) charts were evaluated, with sensitivity and specificity computed on the VB-challenged heifers (n = 19) and PBS-challenged heifers (n = 19), respectively, and the accuracy was determined as the average of sensitivity and specificity. To address the diurnal nature of rumen temperature responses, summary statistics (mean, minimum, and maximum) were computed for daily quartiles (6-h intervals), and these quartile temperature models were evaluated separately. In the Shewhart analysis, DMI was the most accurate (95%) at deciphering between PBS- and VB-challenged heifers, followed by rumen temperature (94%) collected in the 2nd and 3rd quartiles. Rest was most the accurate accelerometer-based traits (89%), and meal duration (87%) and bunk visit (BV) frequency (82%) were the most accurate feeding behavior traits. Rumen temperature collected in the 3rd quartile signaled the earliest (2.5 d) of all the variables monitored with the Shewhart, followed by BV frequency (2.8 d), meal duration (2.8 d), DMI (3.0 d), and rest (4.0 d). Rumen temperature and DMI remained the most accurate variables in the CUSUM at 80% and 79%, respectively. Meal duration (58%), BV frequency (71%), and rest (74%) were less accurate when monitored with the CUSUM analysis. Furthermore, signal day was greater for DMI, rumen temperature, and meal duration (4.4, 5.0, and 3.7 d, respectively) in the CUSUM compared to Shewhart analysis. These results indicate that Shewhart and CUSUM charts can effectively identify deviations in feeding behavior, activity, and rumen temperature patterns for the purpose of detecting sub-clinical BRD in beef cattle.

Lameness in dairy cows: farmer perceptions and automated detection technology

This Research Reflection provides an overview of three interrelated topics: (i) lameness in dairy cows, demonstrating the underpinning importance of the condition, (ii) dairy farmer detection, diagnosis and treatment of lameness and associated foot lesions as well as dairy farmer perceptions towards the condition and (iii) lameness detection technologies, and their potential application on farm to automate the detection of lameness in commercial dairy herds. The presented literature clearly demonstrates that lameness is a major health issue in dairy herds, compromising dairy cow welfare and productivity, and resulting in significant economic implications for dairy farmers. Despite this, dairy farmers fail to perceive lameness as a serious threat to their dairy business. This restricted perception of the importance of lameness may be a product of limited ability to detect lame cows. Many automated lameness detection technologies have been proposed to assist dairy farmers in managing their herds. However, limitations such as cost, performance and dairy farmer perception of the usefulness of these technologies, has lead to poor uptake. It can, therefore, be concluded that there is a need to more thoroughly evaluate the effectiveness of these technologies under on-farm conditions, potentially in the form of a demonstration farm network. This will allow generation of the necessary data required to show dairy farmers that these technologies are reliable and are economically rational for their dairy business.

New Technology Tools and Life Cycle Analysis (LCA) Applied to a Sustainable Livestock Production

Agriculture 4.0, a combination of mechanical innovation and information and communication technologies (ICT) using precision farming, omics technologies and advanced waste treatment techniques, can be used to enhance the biological potential of animal and crop productions and reduce livestock gaseous emissions. In addition to animal proteins being excellent nutritional ingredients for the human diet, there is a growing concern regarding the amount of energy spent converting vegetable crops into animal protein and the relevant environmental impacts. Using the value chain analysis derived from the neoclassic production theory extended to industrial processing and the market, the hypothesis to be tested concerns the sustainability and convenience of different protein sources. The methodology implies the use of life cycle analysis (LCA) to evaluate the efficiency of different livestock diet ingredients. The use of feeding products depend upon various factors, including cost reduction, consumer acceptance, incumbent industry response, civil society support, policy consensus, lower depletion of natural resources, improved sustainable agri-food supply chain and LCA. EU policy makers should be aware of these changes in livestock and market chains and act proactively to encourage the use of alternative animal proteins.

Novel ways to use sensor data to improve mastitis management

Current sensor systems are used to detect cows with clinical mastitis. Although, the systems perform well enough to not negatively affect the adoption of automatic milking systems, the performance is far from perfect. An important advantage of sensor systems is the availability of multiple measurements per day. By clearly defining the need for detection of subclinical mastitis (SCM) and clinical mastitis (CM) from the farmers' management perspective, detection and management of SCM and CM may be improved. Sensor systems may also be used for other aspects of mastitis management. In this paper we have defined 4 mastitis situations that could be managed with the support of sensor systems. Because of differences in the associated management and the epidemiology of these specific mastitis situations, the required demands for performance of the sensor systems do differ. The 4 defined mastitis situations with the requirements of performance are the following: (1) Cows with severe CM needing immediate attention. Sensor systems should have a very high sensitivity (>95% and preferably close to 100%) and specificity (>99%) within a narrow time window (maximum 12 h) to ensure that close to all cows with true cases of severe CM are detected quickly. Although never studied, it is expected that because of the effects of severe CM, such a high detection performance is feasible. (2) Cows with mastitis that do not need immediate attention. Although these cows have a risk of progressing into severe CM or chronic mastitis, they should get the chance to cure spontaneously under close monitoring. Sensor alerts should have a reasonable sensitivity (>80%) and a high specificity (>99.5%). The time window may be around 7 d. (3) Cows needing attention at drying off. For selective dry cow treatment, the absence or presence of an intramammary infection at dry-off needs to be known. To avoid both false-positive and false-negative alerts, sensitivity and specificity can be equally high (>95%). (4) Herd-level udder health. By combining sensor readings from all cows in the herd, novel herd-level key performance indicators can be developed to monitor udder health status and development over time and raise alerts at significant deviances from predefined thresholds; sensitivity should be reasonably high, >80%, and because of the costs for further analysis of false-positive alerts, the specificity should be >99%. The development and validation of sensor-based algorithms specifically for these 4 mastitis situations will encourage situation-specific farmer interventions and operational udder health management.

Invited review: Toward a common language in data-driven mastitis detection research

Sensor technologies for mastitis detection have resulted in the collection and availability of a large amount of data. As a result, scientific publications reporting mastitis detection research have become less driven by approaches based on biological assumptions and more by data-driven modeling. Most of these approaches try to predict mastitis events from (combinations of) raw sensor data to which a wide variety of methods are applied originating from machine learning and classical statistical approaches. However, an even wider variety in terminologies is used by researchers for methods that are similar in nature. This makes it difficult for readers from other disciplines to understand the specific methods that are used and how these differ from each other. The aim of this paper was to provide a framework (filtering, transformation, and classification) for describing the different methods applied in sensor data-based clinical mastitis detection research and use this framework to review and categorize the approaches and underlying methods described in the scientific literature on mastitis detection. We identified 40 scientific publications between 1992 and 2020 that applied methods to detect clinical mastitis from sensor data. Based on these publications, we developed and used the framework and categorized these scientific publications into the 2 data processing techniques of filtering and transformation. These data processing techniques make raw data more amendable to be used for the third step in our framework, that of classification, which is used to distinguish between healthy and nonhealthy (mastitis) cows. Most publications (n = 34) used filtering or transformation, or a combination of these 2, for data processing before classification, whereas the remaining publications (n = 6) classified the observations directly from raw data. Concerning classification, applying a simple threshold was the most used method (n = 19 publications). Our work identified that within approaches several different methods and terminologies for similar methods were used. Not all publications provided a clear description of the method used, and therefore it seemed that different methods were used between publications, whereas in fact just a different terminology was used, or the other way around. This paper is intended to serve as a reference for people from various research disciplines who need to collaborate and communicate efficiently about the topic of sensor-based mastitis detection and the methods used in this context. The framework used in this paper can support future research to correctly classify approaches and methods, which can improve the understanding of scientific publication. We encourage future research on sensor-based animal disease detection, including that of mastitis detection, to use a more coherent terminology for methods, and clearly state which technique (e.g., filtering) and approach (e.g., moving average) are used. This paper, therefore, can serve as a starting point and further stimulates the interdisciplinary cooperation in sensor-based mastitis research.

2019 Survey of Antimicrobial Drug Use and Stewardship Practices in Adult Cows on California Dairies: Post Senate Bill 27

Antimicrobial resistance (AMR) is a global issue for both human and animal health. Antimicrobial drug (AMD) use in animals can contribute to the emergence of AMR. In January 2018, California (CA) implemented legislation (Senate Bill 27; SB 27) requiring veterinary prescriptions for medically important AMD use in food animals. The objective of our survey was to characterize AMD use, health management, and AMD stewardship practices of adult cows on CA dairies since the implementation of SB 27. In 2019, we mailed a questionnaire to 1282 California dairies. We received a total of 131 (10.2%) survey responses from 19 counties in CA. Our results showed that 45.6% of respondents included a veterinarian in their decision on which injectable AMD to purchase. Additionally, 48.8% of dairy producers included a veterinarian in their decision on which AMDs were used to treat sick cows. The majority (96.8%) of dairy producers were aware that all uses of medically important AMDs require a prescription. Approximately 49% of respondents agreed or strongly agreed that AMD use in livestock does not cause problems in humans. The survey documents antimicrobial use and stewardship practices in CA's dairy industry and focus areas for future research and education.

Predictive models to identify Holstein cows at risk of metritis and clinical cure and reproductive/productive failure following antimicrobial treatment

Precision dairy farming, specifically the design of management strategies according to the animal's needs, may soon become the norm since automated technologies that generate large amounts of data for each individual are becoming more affordable. Our objectives were to determine whether the use of behavioral changes could improve the accuracy of prediction of the risk of metritis and the risk of clinical cure of cows diagnosed with metritis. Addition of behavioral data to the algorithms to predict the outcomes of interest increased their accuracy by 7 to 32%. The incidence of metritis in postpartum dairy cows ranges from 20 to 40%. Unfortunately, approximately 30% of cows treated with antimicrobials following the diagnosis of metritis fail to cure and have impaired reproductive performance. Automated behavior monitoring devices have become more affordable and accessible. In the current study, we investigated whether behavioral changes recorded by automated devices improve models for the prediction, within 42 h of calving, of metritis and acute metritis. Furthermore, we determined whether behavioral changes aid on the prediction, 24 h before the diagnosis of metritis, of cure in response to antimicrobial treatments and the reproductive (failure to become pregnant)/productive (bottom quartile of milk yield) success within 200 d in milk (DIM). At enrollment, Holstein cows (n = 555) from two farms were fitted with an automated device (HR-LDn tag, SCR Engineers Ltd., Netanya, Israel) 21 d before the expected calving date. Cows were examined for metritis (fetid, watery, red/brown uterine discharge) and were randomly assigned to receive ampicillin trihydrate or ceftiofur crystalline free acid treatments. Contemporary cows with no clinical diseases (NoCD = 362) were paired with cows with metritis. Cure from metritis was defined as the absence of fetid, watery, pink/brown uterine discharge and rectal temperature < 39.5 °C, 11 d after diagnosis. In addition, cows in the lowest quartile of milk production, within lactation and farm, and that were not pregnant by 200 DIM were classified as failure. We built models containing: routinely-available data [lactation number (1, 2, ≥3), calf sex, still birth, twining, dystocia, vaginal laceration score, days on the close-up diets], body condition score (BCS) and BCS change from enrollment to calving (ΔBCS), behavior (feeding, rumination, idle, and active time), and their interactions. The area under the curve (AUC) of the models containing routinely-available data, ΔBCS, and behavior data at 2 DIM to predict metritis [AUC = 0.82, 95% confidence interval (CI) = 0.78, 0.85] and acute metritis (AUC = 0.87, 95% CI = 0.83, 0.89) were (P < 0.01) excellent; whereas the models predicting cure (AUC = 0.92, 95% CI = 0.85, 0.95) and failure (AUC = 0.90, 95% CI = 0.84, 0.94) were outstanding. Behavioral changes peripartum contribute for the identification of cows at risk for metritis, allowing the development of preventive strategies. In addition, predicting whether cows will respond to antimicrobial treatment and succeed during lactation may allow for earlier decision-making regarding treatment and culling.

Disentangling data dependency using cross-validation strategies to evaluate prediction quality of cattle grazing activities using machine learning algorithms and wearable sensor data

Wearable sensors have been explored as an alternative for real-time monitoring of cattle feeding behavior in grazing systems. To evaluate the performance of predictive models such as machine learning (ML) techniques, data cross-validation (CV) approaches are often employed. However, due to data dependencies and confounding effects, poorly performed validation strategies may significantly inflate the prediction quality. In this context, our objective was to evaluate the effect of different CV strategies on the prediction of grazing activities in cattle using wearable sensor (accelerometer) data and ML algorithms. Six Nellore bulls (average live weight of 345 ± 21 kg) had their behavior visually classified as grazing or not-grazing for a period of 15 days. Elastic Net Generalized Linear Model (GLM), Random Forest (RF), and Artificial Neural Network (ANN) were employed to predict grazing activity (grazing or not-grazing) using 3-axis accelerometer data. For each analytical method, three CV strategies were evaluated: holdout, leave-one-animal-out (LOAO), and leave-one-day-out (LODO). Algorithms were trained using similar dataset sizes (holdout: n = 57,862; LOAO: n = 56,786; LODO: n = 56,672). Overall, GLM delivered the worst prediction accuracy (53%) compared to the ML techniques (65% for both RF and ANN), and ANN performed slightly better than RF for LOAO (73%) and LODO (64%) across CV strategies. The holdout yielded the highest nominal accuracy values for all three ML approaches (GLM: 59%, RF: 76%, and ANN: 74%), followed by LODO (GLM: 49%, RF: 61%, and ANN: 63%) and LOAO (GLM: 52%, RF: 57%, and ANN: 57%). With a larger dataset (i.e., more animals and grazing management scenarios), it is expected that accuracy could be increased. Most importantly, the greater prediction accuracy observed for holdout CV may simply indicate a lack of data independence and the presence of carry-over effects from animals and grazing management. Our results suggest that generalizing predictive models to unknown (not used for training) animals or grazing management may incur poor prediction quality. The results highlight the need for using management knowledge to define the validation strategy that is closer to the real-life situation, i.e., the intended application of the predictive model.

Use of a real-time location system to detect cows in distinct functional areas within a barn

•

The RTLS achieved high accuracy in locating cows in alleys, feed bunk and cubicles.

•

Location and time spent in important barn areas can be automatically determined and used as indicators of health.

•

The potential of combining RTLS with other sensors technologies was discussed.

Automated sensor-based monitoring of cows has become an important tool in herd management to improve or maintain animal health and welfare. Location systems offer the ability to locate animals within the barn for, for example, artificial insemination. Furthermore, they have the potential to measure the time cows spend in important areas of the barn, which might indicate need for improvement in the management of the herd or individuals. In this study, we tested the sensor-based real-time location system (RTLS) Smartbow (SB, Smartbow GmbH) under field conditions. The objectives of this study were (1) to determine the accuracy of the system to predict the location of the cow and the agreement between visual observations and RTLS observations for the total time spent by cows in relevant areas of the barn and (2) to compare the performance of 2 different algorithms (Alg1 and Alg2) for cow location. The study was conducted on a commercial Austrian dairy farm. In total, 35 lactating cows were video recorded for 3 consecutive days. From these recordings, approximately 1 h was selected randomly each day for every cow (3 d × 35 cows). Simultaneously, location data were collected and classified by the RTLS system as dedicated to the alley, feed bunk, or cubicle on a 1-min resolution. A total of 6,030 paired observations were derived from visual observations (VO) and the RTLS and used for the final data analysis. Substantial agreement of categorical data between VO and SB was obtained by Cohen's kappa for both algorithms (Alg1 = 0.76 and Alg2 = 0.78). Similar results were achieved by both algorithms throughout the study, with a slight improvement for Alg2. The ability of the system to locate the cows in the predefined areas was assessed, and the results from Alg2 showed sensitivity, specificity, and positive predictive value of alley (74.0, 91.2, and 76.9%), feed bunk (93.5, 86.2, and 89.1%), and cubicle (90.5, 83.3, and 95.4%) and an overall accuracy of 87.6%.The correlation coefficient (r) between VO and SB for the total time cows spent (within 1 h) in the predefined areas was good to strong (r = 0.82, 0.98, and 0.92 for alley, feed bunk, and cubicle, respectively). These results show the potential of the system to automatically assess total time spent by cows in important areas of the barn for indoor settings. Future studies should focus on evaluating 24-h periods to assess time budgets and to combine technologies such as accelerometers and location systems to improve the performance of behavior prediction in dairy cows.

Prediction of cow's fertility based on data recorded by automatic milking system during the periparturient period

The results of most studies show the beneficial effect of milking automation on production parameters of dairy cows, but its effect on fertility traits is debatable. Therefore, a study was undertaken to predict cow fertility - services per conception (SC) and calving interval (CI) - based on automatic milking system (AMS) data collected in the periparturient period subdivided into the second and first week before calving, 1-4, 5-7, 8-14, 15-21 and 22-28 days of lactation. SC and CI were predicted using daily indicators such as concentrate intake, number of milkings, cow box time, milking time, milking speed, colostrum and milk yield, composition, temperature and electrical conductivity. The study material was derived from the AMS management system and from the SYMLEK milk recording system. The analysis covered data for 16,329 milkings of 398 Polish Holstein-Friesian (PHF) cows, which were used in three AMS herds. The collected numerical data were statistically analysed by correlation analysis in parallel with decision tree technique (SAS statistical package). The present study showed that due to the low, mostly non-significant coefficients of correlation between AMS data collected between 2 weeks before and 4 weeks after calving, it is not possible to predict cow fertility based on single traits. It has been established that the decision tree method may help breeders, already during the postcalving period, to choose the level of factors associated with AMS milking, which will ensure good fertility of cows in a herd. The most favourable number of services per conception is to be expected from cows that were milked <1.6 times per day from 1 to 4 days of lactation and electrical conductivity of their colostrum did not exceed 69 mS during that time. In turn, shortest CI (366 days) will be characteristic of the cows whose average daily colostrum yield did not exceed 20.2 kg and their daily concentrate intake from 8 to 14 days of lactation was at least 5.0 kg.

The Influence of Environmental Conditions on Intake Behavior and Activity by Feedlot Steers Fed Corn or Barley-Based Diets

Simple Summary

Cattle wintered at northern latitudes are often exposed to periods of severe cold. Cattle likely alter feed intake and behavior to combat environmental challenges. This study evaluated the influence of diet and environmental changes on intake behavior and activity (lying time) of feedlot steers. Short-term temperature changes impacted both beef feedlot cattle intake behavior and activity. The steers’ diet, whether they were fed corn or barley, interacted with short term environmental changes to influence animal feeding behavior, but diet had limited impact on cattle lying behavior. Lying behavior was influenced by short-term temperature changes in which cattle spent more time lying down on relatively cold days. Overall, environmental shifts and cold temperature conditions could result in greater energetic needs and ultimately impact feedlot steer intake behavior and activity. By providing information related to beef cattle feedlot behavior, we can more effectively manage cattle feeding systems at northern latitudes to improve feed efficiency.

Abstract

This study evaluated the influence of diet and environmental conditions on intake behavior and activity of feedlot steers. Feedlot rations used were comprised of a main concentrate: (1) corn or (2) barley. A GrowSafe system measured individual animal intake and behavior and HOBO accelerometers measured steer standing time. An Onset weather station collected on site weather data. Steer daily intake displayed a diet by temperature class interaction (p ≤ 0.05). Relative temperature change had no effect on variation in intake (p = 0.60); however, diet influenced variation of intake (p < 0.01), where corn-fed steers had a greater coefficient of variation (CV) than barley-fed steers (21.89 ± 1.46 vs. 18.72 ± 1.46%). Time spent eating (min d⁻¹) and eating rate (g min⁻¹) both displayed a diet by temperature class interaction (p ≤ 0.05). Diet did not affect steer lying activity (p ≥ 0.12), however, time spent lying (min d⁻¹) and frequency of lying bouts (bouts d⁻¹) increased on relatively cold days while the duration of lying bouts (min bout⁻¹; p < 0.01) decreased. Short-term environmental temperature changes interacted with diet influencing feedlot beef cattle intake behavior; however, they did not interact with basal diet in respect to steer activity.

Herd health and production management visits on Canadian dairy cattle farms: Structure, goals, and topics discussed

Regular veterinary visits to improve herd health and production management (HHPM) are important management components on many dairy cattle farms. These visits provide opportunities for constructive conversations between veterinarians and farmers and for shifting management from a reactionary approach to proactively optimizing health and welfare. However, little is known about the structure of HHPM farm visits and to what extent veterinarians provide assistance beyond purely technical services. Therefore, our aims in this cross-sectional study were to describe HHPM farm visit structure, determine which dairy-specific topics were discussed, and assess whether the focus of the visits aligned with farmers' priorities. Veterinary practitioners (n = 14) were recruited to record audio and video of regularly scheduled HHPM farm visits (n = 70) using an action camera attached to their chest or head. A questionnaire was distributed to farmers containing closed- and open-ended questions to assess their goals and perceptions related to farm management and HHPM farm visits. Descriptive statistics and negative binomial and Poisson regression models were used to study dairy-specific topics initiated by the farmer or veterinarian during various activities. A mean of 51% of the visit duration was dedicated to transrectal pregnancy and fertility diagnostics, and a considerable amount of time (30%) was spent on visit preparation, transitions between tasks, and leaving. A total of 488 discussions were initiated by either the veterinarian (55%) or the farmer (45%). Mean length of discussions was 2 min, and only 17% of the HHPM visit duration was spent discussing dairy-specific topics. Veterinarians initiated 62% of their discussions about herd issues, whereas farmer-initiated discussions revolved around herd health in 39% of the discussions. Discussion topics most frequently raised by participants included fertility, udder health, calf health and management, and transition diseases. Consistently, farmers' answers to a rank question regarding their main HHPM farm visit goals indicated that their priorities were to have transrectal pregnancy and fertility diagnostics performed and to improve herd fertility and general herd health. Answers to an open-ended question revealed that additional aims of many farmers were to receive information, have questions answered, and identify and discuss problems. A farmer's belief that HHPM farm visits were "absolutely" tailored toward his or her goals was positively associated with number of discussions during the visit and their conviction that they "always" voiced their wishes and needs to the veterinarian. Opportunities to broaden the focus of HHPM farm visits and improve communication between farmers and veterinarians should be identified and veterinarians should be trained accordingly, which would increase veterinarians' ability to add value during HHPM farm visits.

The Dispensable Surplus Dairy Calf: Is This Issue a "Wicked Problem" and Where Do We Go From Here?

Surplus dairy calves consist of all dairy bull calves and any heifer calves not needed as replacements for the milking herd. The fate of these surplus calves varies by region; for example, in Australia and New Zealand they are often sold as "bobby" calves and slaughtered within the first weeks of life; whereas, in North America they are normally sold within the first weeks of life but reared for 16-18 weeks as veal or longer as dairy beef. Regardless of region, demand for these calves is often very low, driving down prices and in some cases leaving farmers with no alternative options other than on-farm euthanasia. The notion that dairy cows must give birth to produce milk and that the calves are immediately separated from the dam, many of which will end up immediately being sold as surplus calves, has become a topic of public concern. These concerns have increased given the growing number of pictures and stories in the media of on-farm euthanasia, dairy calves being transported at very young ages and frequently receiving sub-standard levels of care. In this paper we describe the status quo of this complex, value-laden issue that without transformative change is at great risk for continued criticism from the public. Moreover, despite many attempts at refinement of the existing approach (i.e., the pursuit of technical improvements), little has changed in terms of how these surplus dairy calves are managed and so we predict that on its own, this approach will likely fail in the long run. We then set out how the current surplus calf management practices could be viewed to fit the definition of a "wicked problem." We conclude by calling for new research using participatory methodologies that include the voice of all stakeholders including the public, as a first step in identifying sustainable solutions that resonate with both society and the livestock industry. We briefly discuss three participatory methodologies that have successfully been used to develop sustainable solutions for other complex problems. Adoption of these types of methodologies has the potential to help position the dairy industry as a leader in sustainable food production.

Variable selection for monitoring sickness behavior in lactating dairy cattle with the application of control charts

The present observational study investigated the application of multivariate cumulative sum (MCUSUM) control charts by including variables selected by principal component analysis and partial least squares (PLS) regression to identify sickness behavior in dairy cattle. Therefore, sensor information (24 variables) was collected from 480 milking cows on a German dairy farm between September 2018 and December 2019. These variables were gathered in potentially different scenarios on farm. In total, data from 749 animals were available for evaluation. Variables were chosen based on the information of 499 cows (62 healthy; 437 sick) with 93,598 observations. The available diagnoses were collected together to form 1,025 sickness events. Hence, the different numbers of selected variables were included into the MCUSUM control charts. The performance of the MCUSUM control charts was evaluated by a 10-fold cross validation; hence, 90% of the original data set (749 cows) represented the training data, and the remaining 10% was used to test the training results. On average, the 10 training data sets included 124,871 observations with 1,392 sickness events, and the 10 testing data sets included, on average, 13,704 observations with 153 sickness events. The MCUSUM generated from the variables selected by principal component analysis showed comparable results in training and testing in all scenarios; therefore, 70.0 to 97.4% of the sickness events were detected. The false-positive rates ranged from 8.5 to 29.6%, and thus they created at least 2.6 false-positive alerts per day in testing. The variables selected by the PLS regression approach showed comparable sickness detection rates (70.0-99.9%) as well as false-positive rates (8.2-62.8%) in most scenarios. The best performing scenario produced 2.5 false-positive alerts in testing. Summarizing, both approaches showed potential for practical implementation; however, the PLS variable selection approach showed fewer false positives. Therefore, the PLS regression approach could generate a more reliable sickness detection algorithm, if combined with MCUSUM control charts, and considered for practical implementation.

Animal Welfare Implications of Digital Tools for Monitoring and Management of Cattle and Sheep on Pasture

The opportunities for natural animal behaviours in pastures imply animal welfare benefits. Nevertheless, monitoring the animals can be challenging. The use of sensors, cameras, positioning equipment and unmanned aerial vehicles in large pastures has the potential to improve animal welfare surveillance. Directly or indirectly, sensors measure environmental factors together with the behaviour and physiological state of the animal, and deviations can trigger alarms for, e.g., disease, heat stress and imminent calving. Electronic positioning includes Radio Frequency Identification (RFID) for the recording of animals at fixed points. Positioning units (GPS) mounted on collars can determine animal movements over large areas, determine their habitat and, somewhat, health and welfare. In combination with other sensors, such units can give information that helps to evaluate the welfare of free-ranging animals. Drones equipped with cameras can also locate and count the animals, as well as herd them. Digitally defined virtual fences can keep animals within a predefined area without the use of physical barriers, relying on acoustic signals and weak electric shocks. Due to individual variations in learning ability, some individuals may be exposed to numerous electric shocks, which might compromise their welfare. More research and development are required, especially regarding the use of drones and virtual fences.

A history of antimicrobial drugs in animals: Evolution and revolution

The evolutionary process of antimicrobial drug (AMD) uses in animals over a mere eight decades (1940-2020) has led to a revolutionary outcome, and both evolution and revolution are ongoing, with reports on a range of uses, misuses and abuses escalating logarithmically. As well as veterinary therapeutic perspectives (efficacy, safety, host toxicity, residues, selection of drug, determination of dose and measurement of outcome in treating animal diseases), there are also broader, nontherapeutic uses, some of which have been abandoned, whilst others hopefully will soon be discontinued, at least in more developed countries. Although AMD uses for treatment of animal diseases will continue, it must: (a) be sustainable within the One Health paradigm; and (b) devolve into more prudent, rationally based therapeutic uses. As this review on AMDs is published in a Journal of Pharmacology and Therapeutics, its scope has been made broader than most recent reviews in this field. Many reviews have focused on negative aspects of AMD actions and uses, especially on the question of antimicrobial resistance. This review recognizes these concerns but also emphasizes the many positive aspects deriving from the use of AMDs, including the major research-based advances underlying both the prudent and rational use of AMDs. It is structured in seven sections: (1) Introduction; (2) Sulfonamide history; (3) Nontherapeutic and empirical uses of AMDs (roles of agronomists and veterinarians); (4) Rational uses of AMDs (roles of pharmacologists, clinicians, industry and regulatory controls); (5) Prudent use (residue monitoring, antimicrobial resistance); (6) International and inter-disciplinary actions; and (7) Conclusions.

A Review: Development of Computer Vision-Based Lameness Detection for Dairy Cows and Discussion of the Practical Applications

The computer vision technique has been rapidly adopted in cow lameness detection research due to its noncontact characteristic and moderate price. This paper attempted to summarize the research progress of computer vision in the detection of lameness. Computer vision lameness detection systems are not popular on farms, and the accuracy and applicability still need to be improved. This paper discusses the problems and development prospects of this technique from three aspects: detection methods, verification methods and application implementation. The paper aims to provide the reader with a summary of the literature and the latest advances in the field of computer vision detection of lameness in dairy cows.

Slightly and Moderately Lame Cows in Tie Stalls Behave Differently From Non-lame Controls. A Matched Case-Control Study

Lameness affects dairy cows worldwide and is usually associated with pain. Behavioral differences in lame compared to non-lame tie-stall-housed dairy cows might be less pronounced than in free-stall-housed, since the principle demands to a cow's locomotor system and thus the impact of lameness on behavior seem to be lower in tie stalls. Behavioral differences between lame and non-lame cows might be used to estimate the impact of lameness on the well-being of tied dairy cows. In the current study, lame cows were categorized as locomotion scoring between 2.25 and 3.25 on a 1–5 scale. The aim was to compare the eating, rumination and lying behavior of lame cows against non-lame tied dairy cows, in order to draw conclusions on the association of lameness, behavior and well-being in tied dairy cows. The eating and rumination behavior of 26, the lying behavior of 30, and the relative upright and lying activities of 25 matched case-control pairs were analyzed, considering the matching criteria farm, breed-type, and parity-group. Lame cows had fewer [mean of the pairwise differences (case–control) (mean_diff) = −2.6 bouts, CI_95% (−3.8–−1.4) bouts, p = 0.001], but longer lying bouts [mean_diff = 26.7 min per bout, CI_95% (10.1–43.4) min per bout, p = 0.006]. The lying time was shorter [mean_diff = −64.7 min, CI_95% (−104.4–−24.9) min, p = 0.006] in lame cows compared to their non-lame controls. Lame cows had a shorter eating time [mean_diff = −27.7 min, CI_95% (−51.5–−4.0) min, p = 0.042] and spent a larger proportion of their upright time ruminating [mean_diff = 7.2%, CI_95% (3.2–11.1)%, p = 0.001] instead of eating. The results of the current study indicate that the eating, rumination, and lying behavior of lame tied dairy cows is altered. These findings indicate that slight and moderate lameness (locomotion score between 2.25 and 3.25 on a 1–5 scale) are likely to be associated with an impaired well-being in affected tied dairy cows. This underlines the need to continuously reduce the lameness prevalence and severity in tied dairy herds.

Relation of Subclinical Ketosis of Dairy Cows with Locomotion Behaviour and Ambient Temperature

Simple Summary

The use of innovative tools and the registration of new biomarkers can help with identification of certain diseases in fresh dairy cows earlier and more accurately, thus improving the quality of treatment and reducing the losses incurred. One of the most often diagnosed diseases of postpartum cows is subclinical ketosis. According to our knowledge there exists limited information about how subclinical ketosis is related to locomotion behaviour (walking activity, feeding time with head position down, feeding time with head position up, change between activities) and average, minimal and maximal ambient temperature. We hypothesized that continuous maximal monitoring of cow locomotion behaviour (in combination with measuring the ambient temperature) could identify cows with subclinical ketosis. In addition, we hoped that changes of the above-mentioned parameters prior to clear clinical signs of subclinical ketosis would aid in earlier detection of the disease.

Abstract

Rumination time, chewing time and drinking time are indicators that can be assessed in case of cow disease. In this research, two groups of cows were formed: cows with subclinical ketosis (SCK; n = 10) and healthy cows (HG; n = 10). Behaviour such as walking activity, feeding time with head position up, feeding time with head position down, change of activity and average, minimal and maximal ambient temperature of cows were recorded by the RumiWatch noseband system (RWS; RumiWatch System, Itin+Hoch GmbH, Liestal, Switzerland). The RWS comprises a noseband halter with a built-in pressure sensor and a liquid-filled pressure tube. Data from each studied cow were recorded for 420 h. According to the results of our study, it was determined that cows diagnosed with subclinical ketosis showed a tendency to change their activity more frequently. Our data indicates that minimal and maximal ambient temperatures are related with SCK.

Influence of Subclinical Ketosis in Dairy Cows on Ingestive-Related Behaviours Registered with a Real-Time System

Simple Summary

Earlier disease detection may benefit cows by improving responses to treatment. We expected that changes in rumination before evident clinical signs of subclinical ketosis would result in the earlier identification of disease. Cows with subclinical ketosis showed lesser average values for the following parameters: rumination time and rumination chews (1.48 and 1.68 times respectively; p < 0.001), drinking time (1.50 times; p < 0.001), chews per minute, bolus and chews per bolus (1.12, 1.45 and 1.51 times; p < 0.001). From the 15th day before the diagnosis of ketosis, rumination time in the healthy group was greater than that in subclinical ketosis cows from −0.96% (−17 day) to 187.79% (0 days, p < 0.001). Eating time at the beginning of the experiment in healthy cows was 48.92% and at the end of the period was −91.97% lesser compared to subclinical ketosis (p < 0.001).

Abstract

According to the literature, rumination time can be used as biomarker in the diagnosis of subclinical ketosis (SCK). We hypothesized that SCK in cows influences ingestive-related behaviours registered with the real-time system. The aim of the current study was to determine the influence of SCK on dairy cows’ ingestive-related behaviours registered with a real-time system. Twenty Lithuanian Black and White breed dairy cows were selected based on the following criteria: First day after calving, having two or more lactations (on average 3.0 ± 0.13 lactations), and being clinically healthy. The experiment lasted 18 days. Cows were tested 24 h a day for 17.5 days. On the day of diagnosis (day 0), data were recorded for 12 h. During the experimental period, one cow was studied for a total of 420 h. For the registration of rumination behaviour, the RumiWatch system (RWS) was used. It was found that cows with SCK showed lesser average values for the following parameters: rumination time and rumination chews (1.48 and 1.68 times respectively; p < 0.001), drinking time (1.50 times; p < 0.001), chews per minute, bolus and chews per bolus (1.12, 1.45 and 1.51 times; p < 0.001). From the 15th day before the diagnosis of SCK, rumination time in health cows was greater than that in SCK cows from −0.96% (−17 day) to 187.79% (0 days, < 0.001). We estimated the greater average value of drinking time in healthy cows compared with SCK cows from 34.22% on day −17 to −121.67% on day 0 (p < 0.001). Decrease in rumination time was associated with a significant increase in the probability of risk of SCK. Further studies are needed with a larger number of cows with SCK.

Symposium review: Linking activity-sensor data and physiology to improve dairy cow fertility

Several studies have demonstrated that the intensity of estrous expression is associated with ovulation, ovarian and uterine function, and fertility, and is dependent on social hierarchy and the housing system used. Data from recent studies involving spontaneous and induced estrus have shown that a greater relative increase and longer estrus (captured by different automated activity monitors; AAM) are both associated with improved pregnancy per artificial insemination (AI; around 10 to 14% increase) and decreased pregnancy losses. Intensity and duration of estrus were surprisingly weakly associated with preovulatory follicle diameter and concentrations of plasma estradiol at estrus, whereas ovulation failure was associated with low estrus intensity. Studies have also shown that the display of estrous behavior near AI was associated with the modification of expression of genes related to the immune system, adhesion molecules, and prostaglandin synthesis in the endometrium. Transcripts in leukocytes and in the conceptus tissue associated with maternal recognition of pregnancy as well as conceptus elongation were all associated with differences in the intensity of estrous expression. Most recently, studies from the United States and Canada have demonstrated that reproductive programs emphasizing detection of estrus using AAM can be successful and comparable to intensive timed AI protocol-based programs that incorporate GnRH and PGF_2α treatments. Further, one study concluded that the administration of GnRH at AI for spontaneous estrus events greatly improved pregnancy per AI, but only for cows with reduced intensity of estrous expression, showing the potential to use AAM data as a tool in targeted reproductive programs. Quantitative information from estrus events could be used to improve estrus detection and develop decision-making strategies at the farm level. Future studies in this field should aim to better understand ovarian, conceptus, and endometrial mechanisms associated with either the expression or the intensity of estrus, and to refine the identification of phenotypes related to estrus (relative increase, absolute increase, baseline levels, duration, and repeatability within cow) to improve data usage, estrus detection, and possibly genetic selection.

Predictive equations for early-life indicators of future body weight in Holstein dairy heifers

It takes an approximate 2-yr investment to raise a replacement heifer from birth to first calving, and selecting the most productive heifers earlier in life could reduce input costs. Daily milk consumption, serum total protein, pneumonia and scours incidences, body size composite, birth weights, and incremental body weights were collected on a commercial dairy farm from October 1, 2015, to January 1, 2019. Holstein calves (n = 5,180) were fed whole pasteurized nonsalable milk with a 30% protein and 5% fat enhancer added at 20 g/L of milk through an automated calf feeding system (feeders = 8) for 60 d on average. Calves were weighed at birth and several other times before calving. Average birth weight of calves was 40.6 ± 4.9 kg (mean ± standard deviation), serum total protein was 6.7 ± 0.63 mg/dL, and cumulative 60-d milk consumption was 508.1 ± 67.3 L with a range of 179.9 to 785.1 L. Daily body weights were predicted for individual animals using a third-order orthogonal polynomial to model body weight curves. The linear and quadratic effects of cumulative 60-d milk consumption, birth weight, feeder, year born, season born, respiratory incidence, scours incidence, and body size composite score were significant when predicting heifer body weight at 400 d (pBW₄₀₀) of age. There was up to a 263-kg difference in pBW₄₀₀ between the heaviest and lightest animal. Birth weight had a significant effect on predicted weights up to 400 d, and for every 1-kg increase in birth weight, there was a 2.5-kg increase in pBW₄₀₀. Quadratic effect of cumulative 60-d milk consumption was significant up to 400 d. We divided 60-d milk consumption into quartiles, and heifers had the highest pBW₄₀₀ in the third quartile when 60-d consumption was between 507.8 and 552.5 L. Body size composite score showed a 21.5-kg difference in pBW₄₀₀ between the top and bottom 25th percentile of heifers. Heifers were 4.2 kg lighter at 400 d if treated for respiratory disease 3+ times during the first 60 d of life compared with heifers not treated for respiratory disease. Measurements that can be obtained in the early life of dairy calves continue to influence heifer growth up to 400 d of age.

Analysis of adoption trends of in-parlor technologies over a 10-year period for labor saving and data capture on pasture-based dairy farms

The use of precision technology is increasingly seen as an option to improve productivity, animal welfare, resource use efficiency, and workplace features on dairy farms. There is limited research related to longitudinal adoption patterns of precision dairy technologies and reasons for any patterns. The aim of this analysis was to investigate trends in technology adoption regarding both the amount (number of farms with a technology) and intensity (number of technologies per farm) of adoption. Surveys of parlor technology adoption were conducted on New Zealand dairy farms in 2008, 2013, and 2018, with 532, 500, and 500 respondents, respectively. Technologies were grouped into labor-saving (LS, such as automatic cluster removers) or data-capture (DC, such as in-line milk meters) categories. Trends were examined for farms that had only LS, only DC, or LS+DC technologies. Technology adoption increased over time; the likelihood of technology adoption in 2018 (and 2013 in parentheses) increased by 21 (22), 7 (68), and 378% (165) for LS, DC, and LS+DC technology groups, respectively, compared to 2008. Farms with LS+DC technologies also had a greater proportion of LS technologies compared to non-LS+DC farms, although this relationship declined over the 10-yr period. The use of a rotary versus herringbone parlor was estimated to be associated with 356 and 470% increase in the likelihood of adopting LS technologies and LS+DC, respectively, from 2008 to 2018. Regional differences in adoption were also found, with the likelihood of adopting DC and LS+DC technologies found to be 46 and 59% greater, respectively, in the South Island of New Zealand, compared to the base region of Waikato. The results highlight the importance of understanding spatial and temporal farm characteristics when considering future effect and adoption of precision dairy technologies. For example, the analysis indicates the occurrence of 2 trajectories to technology investment on farms, where larger farms are able to take advantage of technology opportunities, but smaller farms may be constrained by factors such as lack of economies of scale, limited capital to invest, and inability to retrofit technology into aging parlor infrastructure.

Priorities for science to overcome hurdles thwarting the full promise of the 'digital agriculture' revolution

The world needs to produce more food, more sustainably, on a planet with scarce resources and under changing climate. The advancement of technologies, computing power and analytics offers the possibility that 'digitalisation of agriculture' can provide new solutions to these complex challenges. The role of science is to evidence and support the design and use of digital technologies to realise these beneficial outcomes and avoid unintended consequences. This requires consideration of data governance design to enable the benefits of digital agriculture to be shared equitably and how digital agriculture could change agricultural business models; that is, farm structures, the value chain and stakeholder roles, networks and power relations, and governance. We argue that this requires transdisciplinary research (at pace), including explicit consideration of the aforementioned socio-ethical issues, data governance and business models, alongside addressing technical issues, as we now have to simultaneously deal with multiple interacting outcomes in complex technical, social, economic and governance systems. The exciting prospect is that digitalisation of science can enable this new, and more effective, way of working. The question then becomes: how can we effectively accelerate this shift to a new way of working in agricultural science? As well as identifying key research areas, we suggest organisational changes will be required: new research business models, agile project management; new skills and capabilities; and collaborations with new partners to develop 'technology ecosystems'. © 2018 The Authors. © 2018 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Graduate Student Literature Review: Evaluating the appropriate use of wearable accelerometers in research to monitor lying behaviors of dairy cows

Until recently, animal behavior has been studied through close and extensive observation of individual animals and has relied on subjective assessments. Wearable technologies that allow the automation of dairy cow behavior recording currently dominate the precision dairy technology market. Wearable accelerometers provide new opportunities in animal ethology using quantitative measures of dairy cow behavior. Recent research developments indicate that quantitative measures of behavior may provide new objective on-farm measures to assist producers in predicting, diagnosing, and managing disease or injury on farms and allowing producers to monitor cow comfort and estrus behavior. These recent research developments and a large increase in the availability of wearable accelerometers have led to growing interest of both researchers and producers in this technology. This review aimed to summarize the studies that have validated lying behavior derived from accelerometers and to describe the factors that should be considered when using leg-attached accelerometers and neck-worn collars to describe lying behavior (e.g., lying time and lying bouts) in dairy cows for research purposes. Specifically, we describe accelerometer technology, including the instrument properties and methods for recording motion; the raw data output from accelerometers; and methods developed for the transformation of raw data into meaningful and interpretable information. We highlight differences in validation study outcomes for researchers to consider when developing their own experimental methodology for the use of accelerometers to record lying behaviors in dairy cows. Finally, we discuss several factors that may influence the data recorded by accelerometers and highlight gaps in the literature. We conclude that researchers using accelerometers to record lying behaviors in dairy cattle should (1) select an accelerometer device that, based on device attachment and sampling rate, is appropriate to record the behavior of interest; (2) account for cow-, farm-, and management-related factors that could affect the lying behaviors recorded; (3) determine the appropriate editing criteria for the accurate interpretation of their data; (4) support their chosen method of recording, editing, and interpreting the data by referencing an appropriately designed and accurate validation study published in the literature; and (5) report, in detail, their methodology to ensure others can decipher how the data were captured and understand potential limitations of their methodology. We recommend that standardized protocols be developed for collecting, analyzing, and reporting lying behavior data recorded using wearable accelerometers for dairy cattle.

Review: Application and Prospective Discussion of Machine Learning for the Management of Dairy Farms

Dairy farmers use herd management systems, behavioral sensors, feeding lists, breeding schedules, and health records to document herd characteristics. Consequently, large amounts of dairy data are becoming available. However, a lack of data integration makes it difficult for farmers to analyze the data on their dairy farm, which indicates that these data are currently not being used to their full potential. Hence, multiple issues in dairy farming such as low longevity, poor performance, and health issues remain. We aimed to evaluate whether machine learning (ML) methods can solve some of these existing issues in dairy farming. This review summarizes peer-reviewed ML papers published in the dairy sector between 2015 and 2020. Ultimately, 97 papers from the subdomains of management, physiology, reproduction, behavior analysis, and feeding were considered in this review. The results confirm that ML algorithms have become common tools in most areas of dairy research, particularly to predict data. Despite the quantity of research available, most tested algorithms have not performed sufficiently for a reliable implementation in practice. This may be due to poor training data. The availability of data resources from multiple farms covering longer periods would be useful to improve prediction accuracies. In conclusion, ML is a promising tool in dairy research, which could be used to develop and improve decision support for farmers. As the cow is a multifactorial system, ML algorithms could analyze integrated data sources that describe and ultimately allow managing cows according to all relevant influencing factors. However, both the integration of multiple data sources and the obtainability of public data currently remain challenging.

A survey on sensor systems used in Italian dairy farms and comparison between performances of similar herds equipped or not equipped with sensors

Sensor systems (SS) were developed over the last few decades to help dairy farmers manage their herds. Such systems can provide both data and alerts to several productive, behavioral, and physiological indicators on individual cows. Currently, there is still a lack of knowledge on both the proportion of dairy farms that invested in SS and type of SS installed. Additionally, it is still unclear whether the performances of herds equipped with SS differ from those of similar herds managed without any technological aid. Therefore, the aims of this study were (1) to provide an insight into SS spread among Italian dairy farms and (2) to analyze the performances of similar herds equipped or not equipped with SS. To reach the former goal, a large survey was carried out on 964 dairy farms in the northeast of Italy. Farmers were interviewed by the technicians of the regional breeders association to collect information on the type of SS installed on farms and the main parameters recorded. Overall, 42% of the surveyed farms had at least 1 SS, and most of them (72%) reared more than 50 cows. Sensors for measuring individual cow milk yield were the most prevalent type installed (39% of the surveyed farms), whereas only 15% of farms had SS for estrus detection. More sophisticated parameters, such as rumination, were automatically monitored in less than 5% of the farms. To reach the latter goal of the study, a subset of 100 Holstein dairy farms with similar characteristics was selected: half of them were equipped with SS for monitoring at least individual milk yield and estrus, and the other half were managed without any SS. Average herd productive and reproductive data from official test days over 3 yr were analyzed. The outcomes of the comparison showed that farms with SS had higher mature-equivalent milk production. Further clustering analysis of the same 100 farms partitioned them into 3 clusters based on herd productive and reproductive data. Results of the Chi-squared test showed that the proportion of farms equipped with SS was greater in the cluster with the best performance (e.g., higher milk yield and shorter calving interval). However, the presence of a few farms equipped with SS in the least productive cluster for the same parameters pointed out that although the installation of SS may support farmers in time- and labor-saving or in data recording, it is not a guarantee of better herd performance.

A Review of Welfare Indicators of Indoor-Housed Dairy Cow as a Basis for Integrated Automatic Welfare Assessment Systems

Simple Summary

Many techniques have been developed to measure single indicators of reduced welfare in farm animals, such as changes in the walking pattern to detect lameness in dairy cows. However, there is still a need to combine these single measurements to get a more complete picture of the wellbeing of an animal. Based on a literature review on dairy cow welfare, this review provides a basis for the development of an integrated automatic system to assess the welfare of dairy cows on the farm. It provides an overview of the main welfare issues for dairy cows, such as lameness, heat stress, or pain and of the most established indicators that could help to detect these welfare issues on the farm. We found that there are several indicators, such as reduced feed intake, that are common to most welfare issues and that are therefore suitable to detect reduced welfare in general, while other indicators mainly identify one welfare issue, such as increased respiratory rate, as an indicator of heat stress. Combining these different types of indicators would provide a good basis to develop an integrated automatic system that could assist farmers in the detection of reduced welfare on their farms.

Abstract

For on-farm welfare assessment many automatic methods have been developed to detect indicators of reduced welfare. However, there is still a need to integrate data from single sources to obtain a complete picture of the welfare of an animal. This review offers a basis for developing integrated automatic systems to assess dairy cow welfare by providing an overview of the main issues that challenge cow welfare (e.g., lameness) and of well-established indicators that could detect these issues on the farm. Based on a literature review of 4 reviews on cow welfare in general and 48 reviews on single welfare issues, we identified 18 different major welfare issues and 76 matching indicators that could be detected automatically on the farm. Several indicators, e.g., feed intake, showed a consistent association with welfare across many different issues. Although some of these indicators are discussed critically, this means there are many indicators that potentially could detect reduced welfare in general. Other types of indicators could detect one specific welfare issue, e.g., increased respiratory rate for heat stress. These different types of indicators combined provide a basis to develop integrated automatic systems that ultimately would help farmers to detect welfare problems at an early stage.

Preliminary Experiment Using Sensors for Cow Health Monitoring after Surgical Treatment for the Left Displacement of the Abomasum

The aim of the current study was to determine the effectiveness of two surgical techniques regarding cow respiratory rates, heart rates, and rumination time using two sensors: an experimental device created by the Institute of Biomedical Engineering of Kaunas University of Technology (Lithuania) and the Hi-Tag rumination monitoring system (SCR) produced by SCR Engineers Ltd., Netanya, Israel. The cows were divided into two groups: the PA1 group, containing cows treated by percutaneous abomasopexy (n = 10), and the RSO2 group, containing cows treated by right side omentopexy (n = 8). For the control group (KH), according to the principle of analogs (number of lactations, breed, and days in milk), we selected clinically healthy cows (n = 9). After the surgical treatment for the abomasal displacement, the experimental device was applied for the recording of the heart and breathing rates, 12 h tracking of the rumination time was implemented using the SCR, and the body temperature was measured. After 12 h, the blood was taken for biochemical and morphological tests. With the help of experimental sensors, we found that the more efficient abomasal displacement surgical method was the right side omentopexy: During the first 12 h after right side omentopexy, we found a 5.19 beats/min lower (1.10 times lower) average value of the respiratory rate, a 1.13 times higher level of the heart rate, a 0.15 °C higher temperature, and a 3.29 times lower rumination time compared to the clinically healthy cows. During the first 12 h after percutaneous abomasopexy, we found a 5.19 beats/min higher (1.07 times) average value of heart rate, a 0.02 °C higher temperature, a 6.21 times lower rumination time, and a 0.12 beats/min lower (1.01 times lower) average value of respiratory rate compared to the clinically healthy cows.

Large-Scale Phenotyping of Livestock Welfare in Commercial Production Systems: A New Frontier in Animal Breeding

Genomic breeding programs have been paramount in improving the rates of genetic progress of productive efficiency traits in livestock. Such improvement has been accompanied by the intensification of production systems, use of a wider range of precision technologies in routine management practices, and high-throughput phenotyping. Simultaneously, a greater public awareness of animal welfare has influenced livestock producers to place more emphasis on welfare relative to production traits. Therefore, management practices and breeding technologies in livestock have been developed in recent years to enhance animal welfare. In particular, genomic selection can be used to improve livestock social behavior, resilience to disease and other stress factors, and ease habituation to production system changes. The main requirements for including novel behavioral and welfare traits in genomic breeding schemes are: (1) to identify traits that represent the biological mechanisms of the industry breeding goals; (2) the availability of individual phenotypic records measured on a large number of animals (ideally with genomic information); (3) the derived traits are heritable, biologically meaningful, repeatable, and (ideally) not highly correlated with other traits already included in the selection indexes; and (4) genomic information is available for a large number of individuals (or genetically close individuals) with phenotypic records. In this review, we (1) describe a potential route for development of novel welfare indicator traits (using ideal phenotypes) for both genetic and genomic selection schemes; (2) summarize key indicator variables of livestock behavior and welfare, including a detailed assessment of thermal stress in livestock; (3) describe the primary statistical and bioinformatic methods available for large-scale data analyses of animal welfare; and (4) identify major advancements, challenges, and opportunities to generate high-throughput and large-scale datasets to enable genetic and genomic selection for improved welfare in livestock. A wide variety of novel welfare indicator traits can be derived from information captured by modern technology such as sensors, automatic feeding systems, milking robots, activity monitors, video cameras, and indirect biomarkers at the cellular and physiological levels. The development of novel traits coupled with genomic selection schemes for improved welfare in livestock can be feasible and optimized based on recently developed (or developing) technologies. Efficient implementation of genetic and genomic selection for improved animal welfare also requires the integration of a multitude of scientific fields such as cell and molecular biology, neuroscience, immunology, stress physiology, computer science, engineering, quantitative genomics, and bioinformatics.

Sensing solutions for improving the performance, health and wellbeing of small ruminants

Diversity of production systems and specific socio-economic barriers are key reasons explaining why the implementation of new technologies in small ruminants, despite being needed and beneficial for farmers, is harder than in other livestock species. There are, however, helpful peculiarities where small ruminants are concerned: the compulsory use of electronic identification created a unique scenario in Europe in which all small ruminant breeding stock became searchable by appropriate sensing solutions, and the largest small ruminant population in the world is located in Asia, close to the areas producing new technologies. Notwithstanding, only a few research initiatives and literature reviews have addressed the development of new technologies in small ruminants. This Research Reflection focuses on small ruminants (with emphasis on dairy goats and sheep) and reviews in a non-exhaustive way the basic concepts, the currently available sensor solutions and the structure and elements needed for the implementation of sensor-based husbandry decision support. Finally, some examples of results obtained using several sensor solutions adapted from large animals or newly developed for small ruminants are discussed. Significant room for improvement is recognized and a large number of multiple-sensor solutions are expected to be developed in the relatively near future.

Sensor technology to support herd health monitoring: Using rumination duration and activity measures as unspecific variables for the early detection of dairy cows with health deviations

A significant number of lactating dairy cows are affected by health disorders in the early postpartum period. Precision dairy farming technologies have tremendous potential to support farmers in detecting disordered cows before clinical manifestation of a disease. The objective of this study was to evaluate if activity and rumination measures obtained by a commercial 3D-accelerometer system, i.e. "lying", "high active", "inactive", and "rumination" times, can be used for early identification of cows with health deviations before the clinical manifestation of disease. A total of 312 Holstein cows equipped with an ear attached accelerometer (Smartbow GmbH, Weibern, Austria) were monitored and analyzed from 14 days prior to parturition to eight days in milk (DIM). Animals were checked daily for clinical disorders from zero to eight DIM using standard operating procedures and by blood β-hydroxybutyrate measurements at three, five, and eight DIM. Cows that presented no symptoms of health problems and with BHB concentrations <1.2 mmol/L in the first eight DIM were classified as healthy (n = 156) and used as the reference in this study. Cows with disorders were allocated in groups with one disorder (n = 65) and >1 disorders (n = 91). "Rumination" durations per day were already shorter five days before the clinical diagnosis (D0) in diseased cows (401.9 ± 147.4 min/day) compared with healthy controls (434.6 ± 140.3 min/day). "Rumination" time decreased before the diagnosis, with a nadir at Day -1 for healthy cows and cows with >1 disorder (392.0 ± 147.9 vs. 313.4 ± 162.6 min/day). Cows with one disorder reached a nadir on Day -3 (388.8 ± 158.6 min/day). Similarly, the "high active" time started to become shorter three days before the clinical diagnosis in diseased cows compared to healthy cows (164.1 ± 119.1 vs. 200.3 ± 111.5 min/day). The times cows spent "inactive" were significantly longer three days before clinical diagnosis in diseased cows compared to healthy cows (421.7 ± 168.3 vs. 362.8 ± 117.6 min/day). "Lying" time started to become significantly longer one day before the diagnosis of disorders in disordered cows compared to healthy cows (691.8 ± 183.3 vs. 627.3 ± 158.0 min/day). On average, these results indicated a strong disturbance of physiological parameters before the clinical onset of disease. In summary, it was possible to show differences between disordered and healthy cows based on activity and "rumination" data recorded by a 3D-accelerometer.

Economic Viability of Adoption of Automated Oestrus Detection Technologies on Dairy Farms: A Review

Simple Summary

The accurate and timely detection of oestrus is a central element of good dairy herd management as it ultimately determines the level of milk production and is core to the economic viability of the farm business. However, the traditional method of oestrus detection, which occurs by observing the dairy cows standing immobile while being mounted, is usually time-consuming, repetitive and requires considerable skill and experience on the part of the farmer to attain a reasonable level of efficiency. Given the limitation of the traditional method of oestrus detection, a number of automated oestrus detection (AOD) technologies have been developed. However, the rate of adoption of these technologies remains low. One reason that has been proposed for farmers’ low adoption of such technologies has been their lack of knowledge around the potential economic returns from investing in AOD technologies. In this paper, we review the empirical literature on the viability of investment in AOD technologies from an economic perspective. The conclusion of this study provides evidence from which farmers can make more informed decisions in relation to investing in AOD technologies. The review and analysis is also of importance for informing policy, as it provides an examination of the incentives and levers that could improve productivity on dairy farms.

Abstract

The decision for dairy farmers to invest in automated oestrus detection (AOD) technologies involves the weighing up of the costs and benefits of implementation. In this paper, through a review of the existing literature, we examine the impacts of investment in AOD technologies in relation to the profitability and technical performance of dairy farms. Peer-reviewed articles published between 1970 and 2019 on the investment viability of AOD technologies were collated and analysed. We capture the different measures used in assessing the economic performance of investment in AOD technologies over time which include net present value (NPV), milk production, Benefit-Cost Ratio (BCR), internal rate of return (IRR) and payback period (PBP). The study concludes that investment in AOD technologies is not only worthwhile but also contributes to farm profitability.