Explore the vast range of titles available.

Recent research suggests that personality, defined as consistent individual behavioral variation, in farm animals could be an important factor when considering their health, welfare, and productivity. However, behavioral tests are often performed individually and they might not reflect the behavioral differences manifested in every-day social environments. Furthermore, the contextual and longer-term temporal stability of personality traits have rarely been investigated in adult dairy cattle. In this study, we tested three groups of lactating Holstein cows (40 cows) using an individual arena test and a novel object test in groups to measure the contextual stability of behavior. Among the recorded individual test parameters, we used seven in the final analysis, which were determined by a systematic parameter reduction procedure. We found positive correlations between novel object contact duration in the group test and individual test parameters object contact duration (Rs = 0.361, P = 0.026) and movement duration (Rs = 0.336, P = 0.039). Both tests were repeated 6 months later to investigate their temporal stability whereby four individual test parameters were repeatable. There was no consistency in the group test results for 25 cows tested twice, possibly due to group composition changes. Furthermore, based on the seven individual test parameters, two personality traits (activity/exploration and boldness) were identified by principal component analysis. We found a positive association between the first and second tests for activity/exploration (Rs = 0.334, P = 0.058) and for boldness (Rs = 0.491, P = 0.004). Our results support the multidimensional nature of personality in adult dairy cattle and they indicate a link between behavior in individual and within-group situations. The lack of stability according to the group test results implies that group companions might have a stronger influence on individual behavior than expected. We suggest repeating the within-group behavioral measurements to study the relationship between the social environment and the manifestation of personality traits in every-day situations.

An animal’s social position within a group can influence its ability to perform important behaviours like eating and resting, but little is known about how social position affects the ability to express what are arguably less important but still rewarding behaviors, such as grooming. We set out to assess if dominance measured at the feeder is associated with increased use of a mechanical brush. Over a 2-year period, 161 dry cows were enrolled in a dynamically changing group of 20 individuals with access to a mechanical brush. We determined dominance using agonistic behaviors at the feeder and retrospectively analyzed brush use for the 12 most, and 12 least dominant individuals during the week before calving. Cows that were more dominant at the feeder used the brush more, especially during peak feeding times. Agonistic interactions at the brush did not differ between dominants and subordinates and were not related to brushing duration. These findings indicate that social position, calculated using competition for feed, affects mechanical brush access such that subordinates use the brush less than dominant cows independent of competition or time of day.

Access to brushes allows for natural scratching behaviors in cattle, especially in confined indoor settings. Cattle are motivated to use brushes, but brush use varies with multiple factors including social hierarchy and health. Brush use might serve an indicator of cow health or welfare, but practical application of these measures requires accurate and automated monitoring tools. This study describes a machine learning approach to monitor brush use by dairy cattle. We aimed to capture the daily brush use by integrating data on the rotation of a mechanical brush with data on cow identify derived from either 1) low-frequency radio frequency identification or 2) a computer vision system using fiducial markers. We found that the computer vision system outperformed the RFID system in accuracy, and that the machine learning algorithms enhanced the precision of the brush use estimates. This study presents the first description of a fiducial marker-based computer vision system for monitoring individual cattle behavior in a group setting; this approach could be applied to develop automated measures of other behaviors with the potential to better assess welfare and improve the care for farm animals.

Mechanical brushes are often provided on dairy farms to facilitate grooming. However, current brush designs do not provide data on their use, and thus little is known about the effects of group size and placement of brushes within the pen. The objectives of this study were to automatically detect brush use in cow groups and to investigate the influence of (1) group size and the corresponding cow-to-brush ratio and (2) brush placement in relation to the lying stalls and the feeding and drinking areas. We measured brush use in groups of 60, 48, 36, and 24 cows, with the brush placed either in the alley adjacent to the feed bunk and water trough or in the back alley. Cows used the brush for longer when it was placed in the feed/water alley compared to when placed in the back alley. Average brush use per cow increased when cows were housed in smaller groups, but the brush was never in use more than 50% of the day, regardless of group size. We conclude that brush use increases when availability is increased and when the brush is placed closer to the feed and water.

The increasing use of artificial intelligence (AI) in livestock farming is accelerating the development of automated welfare assessment tools, particularly with advancement in generative AI such as large multimodal models (LMMs). Yet, animal welfare scientists have rarely been involved in the development process of these tools or their subsequent adaptation within the field. Here, we discuss possible roles for animal welfare scientists in the development and validation of AI-based welfare assessment tools. We first examine key uncertainties that emerge during development, including the selection of relevant, valid and reliable welfare indicators and gold standards, hardware and software solutions for data collection, methods for integrating multiple welfare indicators, and the real-world impact of automated welfare assessment tools. Second, we demonstrate the use of LMMs to assess welfare based on a case study using dairy cow cleanliness. Finally, we consider the practical implementation of AI-based welfare assessment and discuss potential tensions around (1) embedded values in LMMs, (2) AI’s influence on decision-making on farms, (3) the integration of AI in current knowledge systems by human-AI collaboration, and (4) the economics of AI-based welfare assessment and improvement. We conclude that LMMs could help automate welfare assessment and communicate results to humans in accessible formats, but outcomes depend on which stakeholders are involved in the development process. We advocate for developing AI-based welfare assessment tools through the One Welfare framework, recognizing that AI deployment affects humans, animals, and the environment simultaneously, and suggest potential pathways for animal welfare scientists to engage in the process.

Our study aimed to characterize social competition strategies in transition cows, and determine how these varied with health status. We retrospectively followed 52 cows during 3 periods (PRE: d −6 to −1 prepartum, POST1: d 1 to 3 postpartum, POST2: d 4 to 6 postpartum). Cows diagnosed with metritis on d 6 postpartum (n = 26) were match paired with healthy cows (n = 26). Measures of agonistic behavior (i.e., replacements at the feeder) and feeding synchrony were determined by an algorithm based on electronic feed bin data, and used to calculate competition strategies via principal component analysis. We found consistent strategies, defined by two components (asynchrony and competitiveness; explaining 82% of the total variance). We observed no differences in strategies when comparing healthy and metritic cows, but metritic cows tended to change their strategies more between PRE and POST1, and between POST1 and POST2, indicating that strategies change in association with parturition and metritis. We conclude that cows show individual variation in competition strategies, and that automated measures of strategy change may help in detecting metritis.

Access to brushes allows for natural scratching behaviors in cattle, especially in confined indoor settings. Cattle are motivated to use brushes, but brush use varies with multiple factors including social hierarchy and health. Brush use might serve an indicator of cow health or welfare, but practical application of these measures requires accurate and automated monitoring tools. This study describes a machine learning approach to monitor brush use by dairy cattle. We aimed to capture the daily brush use by integrating data on the rotation of a mechanical brush with data on cow identify derived from either 1) low-frequency radio frequency identification or 2) a computer vision system using fiducial markers. We found that the computer vision system outperformed the RFID system in accuracy, and that the machine learning algorithms enhanced the precision of the brush use estimates. This study presents the first description of a fiducial marker-based computer vision system for monitoring individual cattle behavior in a group setting; this approach could be applied to develop automated measures of other behaviors with the potential to better assess welfare and improve the care for farm animals.