Exploring longitudinal associations between farmer wellbeing and the welfare of their livestock. The HUNT Study, Norway

The One Welfare approach acknowledges the interrelationships between human wellbeing and animal welfare. Early research has suggested associations between stockperson wellbeing and livestock welfare, however these scenarios are complex and challenging to untangle. In this study, we utilised merged data from over 700 farms to explore associations between farmer wellbeing and livestock welfare. The farms were engaged in cattle, sheep, and/or swine production in Norway between 2017 and 2020. The farmers participated in a general population-based health survey, and livestock welfare was measured using routinely collected, animal-based abattoir observations of over 480,000 animals. We determined a farm's overall livestock welfare relative to the other farms and calculated within-farm differences in this relative welfare level over time. A subset of enterprises (n=328) with sufficient and non-ambiguous farmer wellbeing information were then used to explore differences in these within-farm differences by farmer wellbeing status. We found that poor farmer wellbeing - whether it was defined by anxiety symptoms, depression symptoms, symptoms of psychological distress, or life satisfaction - was associated with a deterioration in overall livestock welfare level (in terms of the mean of the farm's abattoir observed welfare indicators). There was evidence that this association persisted for at least two years. Given societal concerns regarding sustainable food production, farmer wellbeing, and livestock welfare, further research is indicated to explore the complex farmer-livestock relationship within the One Welfare framework. This study suggests that using within-farm changes in relative livestock welfare derived from routinely collected information can be a useful approach.

Active walking in broiler chickens: a flagship for good welfare, a goal for smart farming and a practical starting point for automated welfare recognition

Automated assessment of broiler chicken welfare poses particular problems due to the large numbers of birds involved and the variety of different welfare measures that have been proposed. Active (sustained, defect-free) walking is both a universally agreed measure of bird health and a behavior that can be recognized by existing technology. This makes active walking an ideal starting point for automated assessment of chicken welfare at both individual and flock level.

Unlocking insights: text mining analysis on the health, welfare, and behavior of cows in automated milking systems

Automated Milking Systems (AMS) have undergone significant evolution over the past 30 yr, and their adoption continues to increase, as evidenced by the growing scientific literature. These systems offer advantages such as a reduced milking workload and increased milk yield per cow. However, given concerns about the welfare of farmed animals, studying the effects of AMS on the health and welfare of animals becomes crucial for the overall sustainability of the dairy sector. In the last few years, some analysis conducted through text mining (TM) and topic analysis (TA) approaches have become increasingly widespread in the livestock sector. The aim of the study was to analyze the scientific literature on the impact of AMS on dairy cow health, welfare, and behavior: the paper aimed to produce a comprehensive analysis on this topic using TM and TA approaches. After a preprocessing phase, a dataset of 427 documents was analyzed. The abstracts of the selected papers were analyzed by TM and a TA using Software R 4.3.1. A Term Frequency-Inverse Document Frequency (TFIDF) technique was used to assign a relative weight to each term. According to the results of the TM, the ten most important terms, both words and roots, were feed, farm, teat, concentr, mastiti, group, SCC (somatic cell count), herd, lame and pasture. The 10 most important terms showed TFIDF values greater than 3.5, with feed showing a value of TFIDF of 5.43 and pasture of 3.66. Eight topics were selected with TA, namely: 1) Cow traffic and time budget, 2) Farm management, 3) Udder health, 4) Comparison with conventional milking, 5) Milk production, 6) Analysis of AMS data, 7) Disease detection, 8) Feeding management. Over the years, the focus of documents has shifted from cow traffic, udder health and cow feeding to the analysis of data recorded by the robot to monitor animal conditions and welfare and promptly identify the onset of stress or diseases. The analysis reveals the complex nature of the relationship between AMS and animal welfare, health, and behavior: on one hand, the robot offers interesting opportunities to safeguard animal welfare and health, especially for the possibility of early identification of anomalous conditions using sensors and data; on the other hand, it poses potential risks, which requires further investigations. TM offers an alternative approach to information retrieval in livestock science, especially when dealing with a substantial volume of documents.

How do grazing beef and dairy cattle respond to virtual fences? A review

Virtual fencing (VF) is a modern fencing technology that requires the animal to wear a device (e.g., a collar) that emits acoustic signals to replace the visual cue of traditional physical fences (PF) and, if necessary, mild electric signals. The use of devices that provide electric signals leads to concerns regarding the welfare of virtually fenced animals. The objective of this review is to give an overview of the current state of VF research into the welfare and learning behavior of cattle. Therefore, a systematic literature search was conducted using two online databases and reference lists of relevant articles. Studies included were peer-reviewed and written in English, used beef or dairy cattle, and tested neck-mounted VF devices. Further inclusion criteria were a combination of audio and electrical signals and a setup as a pasture trial, which implied that animals grazed in groups on grassland for 4 h minimum while at least one fence side was virtually fenced. The eligible studies (n = 13) were assigned to one or two of the following categories: animal welfare (n studies = 8) or learning behavior (n studies = 9). As data availability for conducting a meta-analysis was not sufficient, a comparison of the means of welfare indicators (daily weight gain, daily lying time, steps per hour, daily number of lying bouts, and fecal cortisol metabolites [FCM]) for virtually and physically fenced animals was done instead. In an additional qualitative approach, the results from the welfare-related studies were assembled and discussed. For the learning behavior, the number of acoustic and electric signals and their ratio were used in a linear regression model with duration in days as a numeric predictor to assess the learning trends over time. There were no significant differences between VF and PF for most welfare indicators (except FCM with lower values for VF; P = 0.0165). The duration in days did not have a significant effect on the number of acoustic and electric signals. However, a significant effect of trial duration on the ratio of electric-to-acoustic signals (P = 0.0014) could be detected, resulting in a decreasing trend of the ratio over time, which suggests successful learning. Overall, we conclude that the VF research done so far is promising but is not yet sufficient to ensure that the technology could not have impacts on the welfare of certain cattle types. More research is necessary to investigate especially possible long-term effects of VF.

Artificial Intelligence and Sensor Technologies in Dairy Livestock Export: Charting a Digital Transformation

This technical note critically evaluates the transformative potential of Artificial Intelligence (AI) and sensor technologies in the swiftly evolving dairy livestock export industry. We focus on the novel application of the Internet of Things (IoT) in long-distance livestock transportation, particularly in livestock enumeration and identification for precise traceability. Technological advancements in identifying behavioral patterns in 'shy feeder' cows and real-time weight monitoring enhance the accuracy of long-haul livestock transportation. These innovations offer benefits such as improved animal welfare standards, reduced supply chain inaccuracies, and increased operational productivity, expanding market access and enhancing global competitiveness. However, these technologies present challenges, including individual animal customization, economic analysis, data security, privacy, technological adaptability, training, stakeholder engagement, and sustainability concerns. These challenges intertwine with broader ethical considerations around animal treatment, data misuse, and the environmental impacts. By providing a strategic framework for successful technology integration, we emphasize the importance of continuous adaptation and learning. This note underscores the potential of AI, IoT, and sensor technologies to shape the future of the dairy livestock export industry, contributing to a more sustainable and efficient global dairy sector.

Multiview Monitoring of Individual Cattle Behavior Based on Action Recognition in Closed Barns Using Deep Learning

Cattle behavior recognition is essential for monitoring their health and welfare. Existing techniques for behavior recognition in closed barns typically rely on direct observation to detect changes using wearable devices or surveillance cameras. While promising progress has been made in this field, monitoring individual cattle, especially those with similar visual characteristics, remains challenging due to numerous factors such as occlusion, scale variations, and pose changes. Accurate and consistent individual identification over time is therefore essential to overcome these challenges. To address this issue, this paper introduces an approach for multiview monitoring of individual cattle behavior based on action recognition using video data. The proposed system takes an image sequence as input and utilizes a detector to identify hierarchical actions categorized as part and individual actions. These regions of interest are then inputted into a tracking and identification mechanism, enabling the system to continuously track each individual in the scene and assign them a unique identification number. By implementing this approach, cattle behavior is continuously monitored, and statistical analysis is conducted to assess changes in behavior in the time domain. The effectiveness of the proposed framework is demonstrated through quantitative and qualitative experimental results obtained from our Hanwoo cattle video database. Overall, this study tackles the challenges encountered in real farm indoor scenarios, capturing spatiotemporal information and enabling automatic recognition of cattle behavior for precision livestock farming.

As if you were hiring a new employee: on pig veterinarians' perceptions of professional roles and relationships in the context of smart sensing technologies in pig husbandry in the Netherlands and Germany

Veterinarians are increasingly confronted with new technologies, such as Precision Livestock Farming (PLF), which allows for automated animal monitoring on commercial farms. At the same time, we lack information on how veterinarians, as stakeholders who may play a mediating role in the public debate on livestock farming, perceive the use and the impact of such technologies. This study explores the meaning veterinarians attribute to the application of PLF in the context of public concerns related to pig production. Semi-structured interviews were carried out with pig veterinarians located in the Netherlands and Germany. By using an inductive and semantic approach to reflexive thematic analysis, we developed four main themes from the interview data: (1) the advisory role of the veterinarian, which is characterized by a diverse scope, including advice on PLF, generally positive evaluations and financial dependencies; (2) the delineation of PLF technologies as supporting tools, which are seen as an addition to human animal care; (3) the relationship between veterinarian and farmer, which is context-related, ranging from taking sides with to distancing oneself from farmers; and (4) the distance between agriculture and society, in the context of which PLF has both a mitigating and reinforcing potential. The present findings indicate that veterinarians play an active role in the emerging field of PLF in livestock farming. They are aware of and reflect on competing interests of different groups in society and share positions with different stakeholders. However, the extent to which they are able to mediate between stakeholder groups in practice seems to be constrained by external factors, such as financial dependencies.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10460-023-10450-6.

Perceptions of farming stakeholders towards automating dairy cattle mobility and body condition scoring in farm assurance schemes

Animal welfare standards are used within the food industry to demonstrate efforts in reaching higher welfare on farms. To verify compliance with those standards, inspectors conduct regular on-farm animal welfare assessments. Conducting these welfare assessments can, however, be time-consuming and prone to human bias. The emergence of Digital Livestock Technologies (DLTs) offers new ways of monitoring farm animal welfare and can alleviate some of the challenges related to animal welfare assessments by collecting data automatically and more frequently. Whilst automating welfare assessments with DLTs may be promising, little attention has been paid to farmers' perceptions of the challenges that could prevent successful implementation. This study aims to address this gap by focusing on the trial of a DLT (a 3D machinelearning camera) to automate mobility and body condition scoring on 11 dairy cattle farms. Semi-structured, in-depth interviews were conducted with farmers, technology developers and a stakeholder involved in a farm assurance scheme (N14). Findings suggest that stakeholders perceived important benefits to the use of the camera in this context, from building consumer trust by increasing transparency to improved management efficiency. There was also a potential for greater consistency in data collection and thus for enhanced fairness across the UK dairy sector, particularly on the issue of lameness prevalence. However, stakeholders also raised important concerns, such as a lack of clarity around data ownership, reliability, and use, and the possibility of some farmers being penalised (e.g., if the technology failed to work). More clarity should thus be given to farmers in relation to data governance and evidence provided in terms of technical performance and accuracy. The findings of this study highlighted the need for more inclusive approaches to ensure farmers' concerns are adequately identified and addressed. These approaches can help minimise negative consequences to farmers and animal welfare, whilst maximising the potential benefits of automating welfare-related data collection.

Digital Livestock Technologies as boundary objects: Investigating impacts on farm management and animal welfare

Digital Livestock Technologies (DLTs) can assist farmer decision-making and promise benefits to animal health and welfare. However, the extent to which they can help improve animal welfare is unclear. This study explores how DLTs may impact farm management and animal welfare by promoting learning, using the concept of boundary objects. Boundary objects may be interpreted differently by different social worlds but are robust enough to share a common identity across them. They facilitate communication around a common issue, allowing stakeholders to collaborate and co-learn. The type of learning generated may impact management and welfare differently. For example, it may help improve existing strategies (single-loop learning), or initiate reflection on how these strategies were framed initially (double-loop learning). This study focuses on two case studies, during which two DLTs were developed and tested on farms. In-depth, semi-structured interviews were conducted with stakeholders involved in the case studies (n = 31), and the results of a separate survey were used to complement our findings. Findings support the important potential of DLTs to help enhance animal welfare, although the impacts vary between technologies. In both case studies, DLTs facilitated discussions between stakeholders, and whilst both promoted improved management strategies, one also promoted deeper reflection on the importance of animal emotional well-being and on providing opportunities for positive animal welfare. If DLTs are to make significant improvements to animal welfare, greater priority should be given to DLTs that promote a greater understanding of the dimensions of animal welfare and a reframing of values and beliefs with respect to the importance of animals' well-being.

Digital livestock systems and probiotic mixtures can improve the growth performance of swine by enhancing immune function, cecal bacteria, short-chain fatty acid, and nutrient digestibility

In response to climate change, the use of digital livestock systems and probiotic mixtures as technological strategies to improve animal health and production is driving new innovations in the farm animal industry. However, there is little information available regarding the effects of digital livestock systems and probiotic mixtures (consisting of Bacillus subtillus, Streptomyces galilaeus, and Sphingobacteriaceae) on the growth performance of the growth-finishing swine. Thus, the objective of this study was to investigate the effects of digital livestock systems and probiotic mixtures on the immune function, cecal bacteria, short-chain fatty acids, nutrient digestibility, and growth performance of growth-finishing swine. A total of 64 crossbred male swine (Duroc × Landrace × Yorkshire, average body weight: 60.17 ± 1.25 kg) were randomly assigned to four treatment groups: CON (control group with a conventional livestock system without a probiotic mixture), CON0.4 (a conventional livestock system with a 0.4% probiotic mixture), DLSC (a digital livestock system without a probiotic mixture), and DLS0.4 (a digital livestock system with a 0.4% probiotic mixture). The swine were reared under standard environmental conditions until their average body weight reached 110 kg. The results indicated that the growth performance of the swine improved with an increase in nutrient digestibility and immune function via modulation of blood immune markers in the group with a digital livestock system compared to the CON group, although the growth performance of the swine was similar between the DLSC and CON0.4 groups. Moreover, the application of the digital livestock system and the probiotic mixture maintained higher levels of Lactobacillus and balanced short-chain fatty acid profiles compared to the CON group. These results suggest that a digital livestock system and a probiotic mixture can improve the growth performance of swine by enhancing their nutrient digestibility, improving their immune function, and maintaining balanced cecal bacteria and short-chain fatty acids. Therefore, this study provides insights into the application of digital livestock systems and probiotic mixtures as a climate change response strategy to improve swine production.

Perspectives of digital agriculture in diverse types of livestock supply chain systems. Making sense of uses and benefits

Digital technology is being introduced to global agriculture in a wide variety of forms that are collectively known as digital agriculture. In this paper we provide opportunities and value propositions of how this is occurring in livestock production systems, with a consistent emphasis on technology relating to animal health, animal welfare, and product quality for value creation. This is achieved by organizing individual accounts of digital agriculture in livestock systems according to four broad types-commodity-based; value seeking; subsistence and nature-based. Each type presents contrasting modes of value creation in downstream processing; as well as from the perspective of One Health. The ideal result of digital technology adoption is an equitable and substantial diversification of supply chains, increased monetization of animal product quality, and more sensitive management to meet customer demands and environmental threats. Such changes have a significance beyond the immediate value generated because they indicate endogenous growth in livestock systems, and may concern externalities imposed by the pursuit of purely commercial ends.

Welfare Through Competence: A Framework for Animal-Centric Technology Design

Digital technologies offer new ways to ensure that animals can lead a good life in managed settings. As interactive enrichment and smart environments appear in zoos, farms, shelters, kennels and vet facilities, it is essential that the design of such technologies be guided by clear, scientifically-grounded understandings of what animals need and want, to be successful in improving their wellbeing. The field of Animal-Computer Interaction proposes that this can be achieved by centering animals as stakeholders in technology design, but there remains a need for robust methods to support interdisciplinary teams in placing animals' interests at the heart of design projects. Responding to this gap, we present the Welfare through Competence framework, which is grounded in contemporary animal welfare science, established technology design practices and applied expertise in animal-centered design. The framework brings together the “Five Domains of Animal Welfare” model and the “Coe Individual Competence” model, and provides a structured approach to defining animal-centric objectives and refining them through the course of a design project. In this paper, we demonstrate how design teams can use this framework to promote positive animal welfare in a range of managed settings. These much-needed methodological advances contribute a new theoretical foundation to debates around the possibility of animal-centered design, and offer a practical agenda for creating technologies that support a good life for animals.

Animal Welfare and Resistance to Disease: Interaction of Affective States and the Immune System

Good management and improved standards of animal welfare are discussed as important ways of reducing the risk of infection in farm animals without medication. Increasing evidence from both humans and animals suggests that environments that promote wellbeing over stress and positive over negative emotions can reduce susceptibility to disease and/or lead to milder symptoms. We point out, however, that the relationship between welfare, immunity, and disease is highly complex and we caution against claiming more than the current evidence shows. The accumulating but sometimes equivocal evidence of close links between the brain, the gut microbiome, immunity, and welfare are discussed in the context of the known links between mental and physical health in humans. This evidence not only provides empirical support for the importance of good welfare as preventative medicine in animals but also indicates a variety of mechanisms by which good welfare can directly influence disease resistance. Finally, we outline what still needs to be done to explore the potential preventative effects of good welfare.

Twelve Threats of Precision Livestock Farming (PLF) for Animal Welfare

Research and development of Precision Livestock Farming (PLF) is booming, partly due to hopes and claims regarding the benefits of PLF for animal welfare. These claims remain largely unproven, however, as only few PLF technologies focusing on animal welfare have been commercialized and adopted in practice. The prevailing enthusiasm and optimism about PLF innovations may be clouding the perception of possible threats that PLF may pose to farm animal welfare. Without claiming to be exhaustive, this paper lists 12 potential threats grouped into four categories: direct harm, indirect harm via the end-user, via changes to housing and management, and via ethical stagnation or degradation. PLF can directly harm the animals because of (1) technical failures, (2) harmful effects of exposure, adaptation or wearing of hardware components, (3) inaccurate predictions and decisions due to poor external validation, and (4) lack of uptake of the most meaningful indicators for animal welfare. PLF may create indirect effects on animal welfare if the farmer or stockperson (5) becomes under- or over-reliant on PLF technology, (6) spends less (quality) time with the animals, and (7) loses animal-oriented husbandry skills. PLF may also compromise the interests of the animals by creating transformations in animal farming so that the housing and management are (8) adapted to optimize PLF performance or (9) become more industrialized. Finally, PLF may affect the moral status of farm animals in society by leading to (10) increased speciesism, (11) further animal instrumentalization, and (12) increased animal consumption and harm. For the direct threats, possibilities for prevention and remedies are suggested. As the direction and magnitude of the more indirect threats are harder to predict or prevent, they are more difficult to address. In order to maximize the potential of PLF for improving animal welfare, the potential threats as well as the opportunities should be acknowledged, monitored and addressed.

Extensive Sheep and Goat Production: The Role of Novel Technologies towards Sustainability and Animal Welfare

Simple Summary

New technologies have been recognized as valuable in controlling, monitoring, and managing farm animal activities. It makes it possible to deepen the knowledge of animal behavior and improve animal welfare and health, which has positive implications for the sustainability of animal production. In recent years, successful technological developments have been applied in intensive farming systems; however, due to challenging conditions that extensive pasture-based systems show, technology has been more limited. Nevertheless, awareness of the available technological solutions for extensive conditions can increase the implementation of their adoption among farmers and researchers. In this context, this review addresses the role of different technologies applied to sheep and goat production in extensive systems. Examples related to precision livestock farming, omics, thermal stress, colostrum intake, passive immunity, and newborn survival are presented; biomarkers of metabolic diseases and parasite resistance breeding are discussed.

Abstract

Sheep and goat extensive production systems are very important in the context of global food security and the use of rangelands that have no alternative agricultural use. In such systems, there are enormous challenges to address. These include, for instance, classical production issues, such as nutrition or reproduction, as well as carbon-efficient systems within the climate-change context. An adequate response to these issues is determinant to economic and environmental sustainability. The answers to such problems need to combine efficiently not only the classical production aspects, but also the increasingly important health, welfare, and environmental aspects in an integrated fashion. The purpose of the study was to review the application of technological developments, in addition to remote-sensing in tandem with other state-of-the-art techniques that could be used within the framework of extensive production systems of sheep and goats and their impact on nutrition, production, and ultimately, the welfare of these species. In addition to precision livestock farming (PLF), these include other relevant technologies, namely omics and other areas of relevance in small-ruminant extensive production: heat stress, colostrum intake, passive immunity, newborn survival, biomarkers of metabolic disease diagnosis, and parasite resistance breeding. This work shows the substantial, dynamic nature of the scientific community to contribute to solutions that make extensive production systems of sheep and goats more sustainable, efficient, and aligned with current concerns with the environment and welfare.

Detecting Ultra- and Circadian Activity Rhythms of Dairy Cows in Automatic Milking Systems Using the Degree of Functional Coupling—A Pilot Study

Ultra- and circadian activity rhythms of animals can provide important insights into animal welfare. The consistency of behavioral patterns is characteristic of healthy organisms, while changes in the regularity of behavioral rhythms may indicate health and stress-related challenges. This pilot study aimed to examine whether dairy cows in free-stall barns with an automatic milking system (AMS) and free cow traffic can develop ultra- and circadian activity rhythms. On 4 dairy farms, pedometers recorded the activity of 10 cows each over 28 days. Based on time series calculation, the Degree of Functional Coupling (DFC) was used to determine the cows' activity rhythms. The DFC identified significant rhythmic patterns in sliding 7-day periods and indicated the percentage of activity (0–100%) that was synchronized with the 24-h day-night rhythm. As light is the main factor influencing the sleep-wake cycle of organisms, light intensity was recorded in the AMS, at the feed alley and in the barn of each farm. In addition, feeding and milking management were considered as part of the environmental context. Saliva samples of each cow were taken every 3 h for 1 day to determine the melatonin concentration. The DFC approach was successfully used to detect activity rhythms of dairy cows in commercial housing systems. However, large inter- and intra-individual variations were observed. Due to a high frequency of 0 and 100%, a median split was used to dichotomize into “low” (<72.34%) and “high” (≥72.34%) DFC. Forty percent of the sliding 7-day periods corresponded to a low DFC and 50% to a high DFC. No DFC could be calculated for 10% of the periods, as the cows' activity was not synchronized to 24 h. A generalized linear mixed-effects model revealed that the DFC levels were positively associated with a longer milking interval and a higher amount of daytime activity and negatively associated with higher number of lactations. The DFC is a novel approach to animal behavior monitoring. Due to its automation capability, it represents a promising tool in its further development for the purpose of longitudinal monitoring of animal welfare.

Applied Animal Ethics in Industrial Food Animal Production: Exploring the Role of the Veterinarian

Industrial food animal production practices are efficient for producing large quantities of milk, meat, and eggs for a growing global population, but often result in the need to alter animals to fit a more restricted environment, as well as creating new animal welfare and health problems related to animal confinement in high densities. These practices and methods have become normalized, to the extent that veterinarians and others embedded in these industries rarely question the ethical challenges associated with raising animals in this fashion. Moral ‘lock-in’ is common with those working in food animal industries, as is the feeling that it is impossible to effect meaningful change. Animal welfare issues associated with the industrialization of food animal production are ‘wicked problems’ that require a multi- and transdisciplinary approach. We argue that veterinarians, as expert animal health and welfare advocates, should be critical stakeholders and leaders in discussions with producers and the food animal sector, to look for innovative solutions and technology that will address current and future global sustainability and food security needs. Solutions will necessarily be different in different countries and regions, but ethical issues associated with industrial food animal production practices are universal.

Automated Individual Cattle Identification Using Video Data: A Unified Deep Learning Architecture Approach

Individual cattle identification is a prerequisite and foundation for precision livestock farming. Existing methods for cattle identification require radio frequency or visual ear tags, all of which are prone to loss or damage. Here, we propose and implement a new unified deep learning approach to cattle identification using video analysis. The proposed deep learning framework is composed of a Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) with a self-attention mechanism. More specifically, the Inception-V3 CNN was used to extract features from a cattle video dataset taken in a feedlot with rear-view. Extracted features were then fed to a BiLSTM layer to capture spatio-temporal information. Then, self-attention was employed to provide a different focus on the features captured by BiLSTM for the final step of cattle identification. We used a total of 363 rear-view videos from 50 cattle at three different times with an interval of 1 month between data collection periods. The proposed method achieved 93.3% identification accuracy using a 30-frame video length, which outperformed current state-of-the-art methods (Inception-V3, MLP, SimpleRNN, LSTM, and BiLSTM). Furthermore, two different attention schemes, namely, additive and multiplicative attention mechanisms were compared. Our results show that the additive attention mechanism achieved 93.3% accuracy and 91.0% recall, greater than multiplicative attention mechanism with 90.7% accuracy and 87.0% recall. Video length also impacted accuracy, with video sequence length up to 30-frames enhancing identification performance. Overall, our approach can capture key spatio-temporal features to improve cattle identification accuracy, enabling automated cattle identification for precision livestock farming.