Dairy Farm Automation: Technologies for Monitoring and Management

Dairy farm automation covers the practical use of robotic milking systems, wearable and fixed sensors, herd management software, and connected barn equipment to reduce physical labor and improve the consistency of animal monitoring. This article reviews the main automation categories available to dairy farmers, explains how each technology fits into daily management, and provides a comparison framework for evaluating cost and benefit before purchase. The content is written for farmers, farm employees, veterinarians, advisers, students, and farm planners who need a working understanding of what automation can and cannot deliver on a commercial dairy operation.

The Current State of Dairy Farm Automation

Automation in dairy farming has moved beyond experimental adoption into mainstream commercial use. Precision livestock farming uses information and communication technology to continuously monitor, control, and improve productivity, reproduction, health, welfare, and environmental impact of livestock. The flow of information from animals to humans has become seamless enough that practical decisions about health, reproduction management, and calving surveillance can be made from data instead of observation alone. This shift matters because the number of livestock per farm has increased to the point where individual tracking of every animal by a person is no longer practical. Historically, cattle management decisions relied heavily on human observation, judgment, and experience, but a single individual cannot gather reliable audio-visual monitoring data around the clock. Dairy cows now show subtler indicators of estrus, which creates a substantial chance of missing an estrus cycle. Calving complications sometimes go unnoticed on farms, resulting in a higher number of culled cattle. Precision technologies enable the monitoring and tracking of an individual cow's physiological behavior and reproductive parameters, thereby optimizing management practices and farm performance. Common challenges remain, including battery lifespan, transmission range, specificity and sensitivity, storage capacity, and economic affordability. The demand for these systems continues to grow as farms expand and labor becomes harder to secure. The FAO Animal Production and Health program tracks these global shifts in livestock production systems and the role of technology in meeting food demand.

Core Automation Categories for Dairy Operations

Automation technologies for dairy farms fall into several functional groups. Understanding these categories helps a farmer identify which systems address the specific bottlenecks on their operation. The main categories are milking automation, feeding automation, environmental control, animal monitoring sensors, and herd management software. Each category serves a distinct purpose, and farms often combine multiple categories to achieve a higher overall level of automation.

Robotic and Automatic Milking Systems

Automatic milking systems, commonly called milking robots, have become popular worldwide, and the number of dairy farms adopting these systems has increased considerably over the past years. In each milking visit, an automatic milking system records the location of the four teats as Cartesian coordinates in an xyz plane, which can then be used to derive udder conformation traits. Because automatic milking systems generate a large amount of data for individual cows per milking visit, they contribute to an accurate assessment of important traits such as udder conformation without the addition of human classifier errors that occur in subjective scoring systems. The data generated by these systems also supports genetic evaluation. Udder conformation is directly related to milk yield, cow health, workability, and welfare. The increasing adoption of automatic milking systems enables repeated, objective measurement of teat and udder geometry at each milking, creating new opportunities to improve genetic evaluation of these traits under commercial conditions. Heritability estimates for udder conformation traits derived from automatic milking system data range from moderate to high, with udder depth showing particularly high heritability. Repeatability is high for udder conformation traits and moderate for daily milk yield. These findings indicate that automatic milking systems can support breeding decisions for cows that are more suitable for milking in robotic systems. Genome-wide association studies have identified a polygenic basis for teat placement traits, with numerous small-effect variants associated with teat spacing. The identified genomic regions and candidate genes contribute to understanding the genetic link between teat spacing and cow health and longevity.

Wearable Sensors and Collar Technologies

Wearable collar technologies provide real-time insights into cow health, behavior, and productivity. These collars, equipped with sensors, allow farmers to monitor key parameters non-invasively, improving animal welfare and farm efficiency. Despite their potential, challenges such as limited battery life and high costs hinder broader adoption. Future advancements should focus on integrating multiple sensors into energy-efficient designs, reducing costs, and simplifying management. Smart collars play a pivotal role in precision livestock farming, enabling sustainable practices and optimizing herd management. Accelerometers have the potential to monitor lying behavior, step activity, and rumination, which are useful to detect changes in behavior that may indicate disease, responses to painful procedures, or positive welfare behaviors such as play. The most frequent technologies adopted by producers in a survey of Brazilian dairy farms included milk meter systems, milking parlor smart gates, sensor systems to detect mastitis, cow activity meters, and body temperature sensors. Producers indicated that available technical support was the most important decision criterion involved in adopting technology, followed by return on investment, user-friendliness, and upfront investment cost. These findings suggest that farmers prioritize practical support and economic return over technical novelty when choosing sensor systems.

Automated Feeding Systems

Automated calf feeding systems can control delivery of nutritional plans to individualize feeding and weaning of calves. Changes in feeding behaviors such as milk intake, drinking speed, and unrewarded visits may be used to identify early onset of disease. For adult cows, automatic feeding systems are commercially available and form part of the broader automation trend in dairy cattle farming. The effects of these technologies on individual aspects of animal welfare have been explored to some extent, but studies analyzing the impact of increasing farm automation through various combinations of technologies are limited. A study of 32 trial farms in Northern and Central Germany categorized farms into varying automation levels using a newly developed classification system. No significant differences were observed in overall welfare scores, suggesting that the impact of automation does not exceed other farm-related factors influencing animal wellbeing, such as housing environment or management methods. However, significant effects of milking, feeding, and bedding systems on the appropriate behavior of cattle were observed. Higher levels of automation had a positive impact on the human-animal relationship and led to positive emotional states. Farms with higher automation levels had significantly lower scores for the prevalence of severe lameness and dirtiness of lower legs. The conclusion was that a higher degree of automation could help to improve animal welfare on dairy farms.

Environmental Monitoring and Automated Barn Systems

Environmental monitoring systems track temperature, humidity, light intensity, and harmful gas concentrations within the barn. These systems address common challenges in dairy farming such as poor barn hygiene, excessive ammonia accumulation, inadequate ventilation, and heat stress, all of which adversely affect animal health and productivity. Automated systems can regulate airflow and lighting conditions based on sensor feedback, and automated waste removal can direct manure to a biogas unit. These designs ensure a hygienic and safe environment for livestock while promoting sustainable waste-to-energy conversion, reducing manual labor and enhancing farm efficiency. The USDA Agricultural Research Service Animal Production and Protection program conducts research on livestock production systems, including environmental management and animal health interactions.

Herd Management Software and Data Integration

Herd management software integrates data from multiple sources into centralized platforms, enabling real-time health alerts and predictive diagnostics. Internet of Things frameworks collect data from wearable sensors, environmental monitors, and milking systems, then present it to the farmer through dashboards and alerts. The main enabling technologies of what has been termed Dairy 4.0 include robotics, 3D printing, artificial intelligence, the Internet of Things, big data, and blockchain. These advanced technologies are being progressively adopted in the dairy sector from farm to table, making significant and profound changes in the production of milk, cheese, and other dairy products. Artificial intelligence technologies, particularly computer vision, machine learning, and sensor-based systems, are enhancing core areas of dairy operations including cattle identification, health monitoring, disease detection, and reproductive management. Advanced image-based systems enable contactless identification, improving animal welfare and operational precision. AI-enabled health surveillance tools support early disease detection, reducing veterinary costs and improving herd productivity. In reproductive care, AI facilitates accurate estrus detection and pregnancy monitoring using data from wearable sensors and cameras, optimizing insemination timing and calving outcomes. Integration with smart farm platforms allows real-time decision-making for feeding, barn conditions, and logistics. Despite significant progress, challenges such as infrastructure gaps, high costs, and data governance remain.

At a Glance: Automation Technology Comparison

The following table compares the main automation technology categories across factors that matter for farm decision-making. Use this table as a starting point for discussions with equipment dealers, veterinarians, and financial advisers.

Labor Efficiency and Work Pattern Impacts

Milking requires significant labor input and influences the start and end times of the working day, affecting flexibility to suit employee needs or availability. The use of labor-saving technology and milking management strategies could help with this challenge. A telephone survey of 500 dairy farmers in New Zealand conducted during April and May 2018 asked questions about milking practices and technology use. Predictive analysis showed that at peak lactation, milking required between 17 and 24 hours per week per worker for farms milking twice a day, representing 43 to 58 percent of a conventional 40-hour work week, depending on parlor type, the number of clusters, and herd size. Using milking intervals of 8 and 16 hours compared with the more usual 10 and 14 hours largely avoided starting milking before 0500 hours. Eight percent of herds were milked once a day, which required between 7 and 14 hours per week per worker, representing 18 to 35 percent of a 40-hour week. For metrics that related to people, including labor efficiency and work routine, automatic teat spraying showed measurable benefits. To attract and retain quality employees, dairy farms must be competitive with other workplaces offering more conventional hours of work. Automation that reduces the fixed time demands of milking can make farm work more attractive to prospective employees.

Practical Implementation Steps for Automation Adoption

Adopting automation on a dairy farm requires a structured approach. The following steps provide a framework for evaluating, selecting, and implementing automation technologies.

Step 1: Identify the Specific Bottleneck

Before purchasing any technology, define the problem you are trying to solve. Common bottlenecks include labor shortages for milking, poor heat detection rates, delayed disease identification, or excessive time spent on feeding. A farm that struggles with missed estrus cycles needs a different solution than a farm that cannot find milking labor. Write down the specific operational problem, the frequency with which it occurs, and the estimated cost of the problem in lost production or labor hours.

Step 2: Evaluate Technical Support and Service Availability

Producers have indicated that available technical support is the most important decision criterion involved in adopting technology, followed by return on investment, user-friendliness, and upfront investment cost. Before committing to a system, ask the supplier about response times for service calls, availability of replacement parts, training provided to farm staff, and the expected lifespan of the equipment. A system that cannot be serviced quickly in your region will cause more downtime than a less advanced system with reliable local support.

Step 3: Calculate Return on Investment with Realistic Assumptions

Return on investment calculations should include the purchase price, installation costs, ongoing subscription fees, maintenance contracts, and the value of your time or labor savings. For automatic milking systems, consider the economic impact of grouping strategies. A study on a commercial dairy farm using a guided-flow automatic milking system evaluated revenue minus feed cost across management groups. The high-production group presented the highest feed efficiency and revenue minus feed cost, despite requiring higher nutritional investment. The low-production group had reduced economic performance, especially in the final months of lactation. Under the evaluated farm conditions, the grouped strategy was associated with more targeted feeding management and with differences in technical and economic performance among groups. This finding suggests that automation does not eliminate the need for good management decisions about grouping and feeding.

Step 4: Plan the Transition Period

Transitioning cows to automatic milking requires planning. Automatic milking systems allow cows to choose when and how often they visit the milking unit, but introduction to these systems can be fear inducing. Sometimes cows are habituated to an automatic milking system before milking is initiated, but there are no widely agreed upon training procedures for easing this transition. A study followed a single pen of 46 lactating cows during a herd-wide transition from parlor to automatic milking system milking. Cows were randomly assigned to either an acclimation training regimen followed by baseline training, or to just the baseline training. The acclimation regimen began 13 days before the switch from parlor to automatic milking system milking and consisted of a habituation phase that included exposure to a non-operational milking unit, with cows encouraged using positive reinforcement via a grain reward to enter the milking unit. The acclimation training ended 3 days before the switch, at which point 11 of 21 of the acclimation-trained cows had freely entered the automatic milking system and were included in the assessment of successfully trained cows. Baseline training was then applied to all cows in the pen once daily for the remaining 3 days, involving farm staff moving cows individually into the non-operational automatic milking system where they received a food reward. The behavioral responses assessed during the first 3 milkings showed measurable differences based on training method.

Step 5: Train Staff on Data Interpretation

Automation generates data, but data only improves farm performance when someone interprets it and acts on it. Staff need training on what alerts mean, how to verify an alert before treating an animal, and when to escalate concerns to a veterinarian. The USDA National Agricultural Library Animal Health and Welfare collection includes resources on livestock management practices and animal health monitoring that can support staff training programs.

Records and Measurements for Automation Decisions

Keeping accurate records before and after automation adoption allows a farmer to measure whether the investment delivered the expected benefits. The following measurements provide a baseline for comparison.

Pre-Adoption Baseline Records

Record the following for at least three months before installing new automation: daily milk yield per cow, milking frequency, somatic cell count or mastitis cases per month, heat detection rate, calving interval, labor hours spent on milking and feeding per week, and veterinary treatment costs per month. These records establish the current performance level against which the automation investment can be judged.

Post-Adoption Monitoring Records

After automation is installed, track the same metrics plus automation-specific data. For automatic milking systems, record milking frequency per cow per day, failed milking attempts, teat cup attachment success, and milk conductivity readings. For wearable sensors, record activity and rumination alerts, the number of alerts that were confirmed as true health events, and the time from alert to treatment. For feeding systems, record feed intake per cow, feeding behavior changes, and any correlation between feeding behavior alerts and disease diagnosis.

Economic Records

Maintain a ledger of automation-related costs including purchase price, installation, monthly subscriptions, maintenance and repair calls, replacement parts, and staff training time. Compare these costs against labor savings, reduced veterinary expenses, improved milk production, and any changes in reproductive performance. The U.S. Food and Drug Administration Animal and Veterinary resources provide regulatory context for animal health products and recordkeeping expectations on farms.

Common Failure Patterns in Automation Adoption

Understanding why automation projects fail helps farmers avoid the same mistakes. The following patterns appear repeatedly in commercial dairy operations.

Failure Pattern 1: Technology Purchased Without a Defined Problem

Some farms purchase automation because it is new or because a neighbor adopted it, without first identifying the specific operational bottleneck. The result is expensive equipment that does not address the farm's actual constraints. The technology generates data that no one uses, and the expected labor savings never materialize because the real problem was poor staff management or inadequate facilities.

Failure Pattern 2: Underestimating Training Requirements

Automatic milking systems require cows to learn a new behavior, and farm staff must learn to trust and interpret the data. Farms that skip the acclimation phase or rush the transition often see cows with low milking frequency, high failed attachment rates, and increased stress. The study on transitioning dairy cows to automatic milking found that cows subjected to an acclimation regimen showed different behavioral responses during their first 3 milkings compared with cows receiving only baseline training. Farms that do not allocate time for cow training and staff education struggle with adoption.

Failure Pattern 3: Ignoring Data Integration Challenges

Many farms purchase sensors from one manufacturer, a milking system from another, and herd management software from a third. These systems may not communicate with each other, forcing the farmer to check multiple platforms and manually reconcile data. Internet of Things frameworks can integrate these datasets into centralized platforms, but integration requires technical skill and ongoing maintenance. Farms that do not plan for data integration end up with fragmented information that is no more useful than paper records.

Failure Pattern 4: Overlooking Ongoing Costs

The purchase price of automation is only the beginning. Subscription fees, sensor replacement, battery costs, internet connectivity, and maintenance contracts add up over time. Farms that budget only for the initial purchase may find themselves unable to maintain the system properly, leading to degraded performance and eventual abandonment of the technology.

Failure Pattern 5: Expecting Automation to Replace Management

Automation provides information and performs repetitive tasks, but it does not make management decisions. A farm with poor grouping strategies, inadequate nutrition, or weak reproductive management will not be fixed by installing sensors or robots. The study on grouping strategies in automatic milking systems found that the high-production group had the highest feed efficiency and revenue minus feed cost, despite requiring higher nutritional investment. This result came from management decisions about grouping and feeding, not from the automation itself.

Welfare and Safety Context for Automation

Automation affects animal welfare and worker safety in ways that farmers should understand before adoption. The World Organisation for Animal Health Animal Health and Welfare program provides international standards for animal welfare that can guide farm automation decisions.

Animal Welfare Considerations

A study examining the impact of automation level on dairy cattle welfare in Northern and Central Germany found no significant differences in overall welfare scores across farms with differing automation levels. This finding suggests that the impact of automation does not exceed other farm-related factors influencing animal wellbeing, such as housing environment or management methods. However, significant effects of milking, feeding, and bedding systems on the appropriate behavior of cattle were observed. Higher levels of automation had a positive impact on the human-animal relationship and led to positive emotional states. Farms with higher automation levels had significantly lower scores for the prevalence of severe lameness and dirtiness of lower legs. The conclusion was that a higher degree of automation could help to improve animal welfare on dairy farms. Hair cortisol concentration of dairy cattle is unrelated to automation level of dairy farms, but it can reflect Welfare Quality measures. This finding suggests that automation level alone does not determine chronic stress in dairy cattle, and that other management factors play a larger role.

Worker Safety Considerations

Increased rates of automation in agriculture alongside new risks associated with climate change create the need for anticipatory governance and adaptive research to study novel mechanisms of worker health and safety. Research on agricultural health and safety has identified three themes in the literature: adoption outcomes, discrete cases of health risks, and an emphasis on care and wellbeing in literature on dairy automation. Current research tends to examine these forces separately instead of together, has not made robust examination of these forces as socially embedded, and has hesitated to examine broad, transferable themes for how these forces work across industries. Farmers implementing automation should consider how new technologies change the physical demands of farm work, the skills required of employees, and the potential for new hazards introduced by complex machinery and data systems.

Food Safety and Regulatory Context

Automation affects food safety through improved monitoring of milk quality and animal health. Milk conductivity measured during automatic milking serves as an indicator of mastitis, allowing earlier detection and treatment. Near-infrared spectroscopic sensing systems have been explored for cow milk quality determination in smart dairy farming applications. The U.S. Food and Drug Administration Animal and Veterinary resources provide regulatory information on animal health products, milk safety, and veterinary oversight. Farmers should ensure that automation systems for milk quality monitoring are validated and that any treatment decisions based on automated alerts follow veterinary guidance.

Limitations and Professional Escalation Criteria

Automation technologies have documented limitations that farmers should recognize. Sensor accuracy, data integration, and scalability persist as challenges across IoT frameworks in dairy farming. Battery lifespan, transmission range, specificity and sensitivity, storage capacity, and economic affordability remain common challenges for precision technologies. Automated lameness detection systems have been studied extensively at the sensor technique level, algorithm validation level, and performance for detection level, but there are no studies of decision support with early warning systems at the highest development level. The adoption rate of automated lameness detection systems by herd managers mainly yields returns on investment by the early identification of lame cows. Long-term studies using validated automated lameness detection systems aiming at early lameness detection are still needed to improve welfare and production under field conditions.

Professional escalation is required when automated systems generate alerts that indicate a condition requiring veterinary diagnosis or treatment. Farmers should establish protocols with their veterinarian for responding to automated alerts related to mastitis, lameness, calving, or other health conditions. Automated systems can identify potential problems, but they cannot replace veterinary examination and diagnosis. Similarly, automated feeding systems can adjust feed delivery, but nutritional decisions should be reviewed by a nutritionist. The USDA Agricultural Research Service Animal Production and Protection program conducts research on animal health and production systems that can inform these protocols.

Options and Tradeoffs in Automation Selection

Farms face different automation options depending on their size, housing system, labor availability, and financial capacity. The following considerations help frame the selection process.

Full Automation Versus Targeted Automation

Some farms adopt a full automation approach, installing robotic milking, automated feeding, environmental monitoring, and wearable sensors simultaneously. Other farms adopt targeted automation, addressing one bottleneck at a time. The study on automation levels in German dairy farms found that higher levels of automation were associated with positive welfare outcomes, but the study also noted that the impact of automation does not exceed other farm-related factors. A farm with excellent management and moderate automation may outperform a farm with extensive automation and poor management.

Pasture-Based Versus Confinement Systems

Automation technologies developed for confinement systems may not transfer directly to pasture-based systems. The New Zealand survey of pasture-based dairy farms found that milking labor requirements varied by parlor type, the number of clusters, and herd size. Automatic teat spraying showed measurable benefits for labor efficiency and work routine. Farms in pasture-based systems may benefit more from in-parlor automation than from robotic milking systems that require cows to be housed for voluntary milking visits.

Data Ownership and Governance

As farms adopt more connected technologies, questions of data ownership and governance become important. Farmers should understand who owns the data generated by their automation systems, how the data can be used by equipment manufacturers, and what happens to the data if the farm changes equipment suppliers. The FAO Animal Production and Health program addresses data governance issues in livestock production systems.

Frequently Asked Questions

What is the difference between precision livestock farming and conventional dairy management?

Precision livestock farming uses information and communication technology to continuously monitor, control, and improve productivity, reproduction, health, welfare, and environmental impact of livestock. Conventional management relies on human observation, judgment, and experience. Precision technologies enable the monitoring and tracking of an individual cow's physiological behavior and reproductive parameters, which is important because a single person cannot gather reliable audio-visual monitoring data around the clock as herd sizes increase.

How much labor can automation save on a dairy farm?

Milking requires significant labor input and influences the start and end times of the working day. A survey of 500 pasture-based dairy farms in New Zealand found that at peak lactation, milking required between 17 and 24 hours per week per worker for farms milking twice a day, representing 43 to 58 percent of a conventional 40-hour work week. Farms milking once a day required between 7 and 14 hours per week per worker. Automation that reduces milking labor or allows flexible milking intervals can make farm work more compatible with employee needs.

Do automated systems improve animal welfare?

A study of 32 dairy farms in Northern and Central Germany found no significant differences in overall welfare scores across farms with differing automation levels, suggesting that the impact of automation does not exceed other farm-related factors such as housing environment or management methods. However, higher levels of automation had a positive impact on the human-animal relationship, led to positive emotional states, and were associated with lower scores for severe lameness and dirtiness of lower legs. The study concluded that a higher degree of automation could help to improve animal welfare.

What are the main challenges with wearable sensors for dairy cows?

Wearable collar technologies face challenges such as limited battery life and high costs that hinder broader adoption. Common challenges across precision technologies include battery lifespan, transmission range, specificity and sensitivity, storage capacity, and economic affordability. Future advancements should focus on integrating multiple sensors into energy-efficient designs, reducing costs, and simplifying management.

How should cows be trained for automatic milking systems?

There are no widely agreed upon training procedures for easing the transition to automatic milking systems. A study comparing acclimation training followed by baseline training with baseline training alone found that cows subjected to the acclimation regimen began training 13 days before the switch from parlor to automatic milking system milking. The acclimation regimen included exposure to a non-operational milking unit with positive reinforcement via a grain reward. Behavioral responses during the first 3 milkings differed based on training method.

What factors should farmers consider when deciding whether to adopt precision technologies?

Producers have indicated that available technical support is the most important decision criterion involved in adopting technology, followed by return on investment, user-friendliness, and upfront investment cost. Farmers should also consider how the technology addresses a specific operational bottleneck, the ongoing costs of subscriptions and maintenance, data integration with existing systems, and the training required for staff and animals.

Can automation data be used for genetic improvement?

Yes. Automatic milking systems record the location of the four teats as Cartesian coordinates during each milking visit, which can be used to derive udder conformation traits. These traits are highly heritable in Holstein cattle, and genome-wide association studies have identified genomic regions and candidate genes associated with udder conformation and teat placement. This data supports genetic evaluation of cows for suitability in automatic milking systems.

What are the economic considerations for grouping cows in automatic milking systems?

A study on a commercial dairy farm using a guided-flow automatic milking system found that revenue minus feed cost was significantly affected by group type, feed costs, and milk price. The high-production group presented the highest feed efficiency and revenue minus feed cost, despite requiring higher nutritional investment. The low-production group had reduced economic performance, especially in the final months of lactation. Grouping strategies should be evaluated using technical and economic indicators such as revenue minus feed cost and feed efficiency.

Related Farming Guides

• Dairy Farm Transition to Robotic Milking
• Dairy Cow Ketosis Monitoring and Herd Review
• Dairy Farm Labor Management: Hiring, Training, and Retention
• Dairy Farm Mechanization: Automation and Smart Farming Technologies
• Dairy Farm Manure Management

References and Further Reading

• FAO Animal Production and Health. Food and Agriculture Organization of the United Nations.
• Animal Health and Welfare. USDA National Agricultural Library.
• Animal and Veterinary Resources. U.S. Food and Drug Administration.
• Animal Health and Welfare. World Organisation for Animal Health.
• Animal Production and Protection. USDA Agricultural Research Service.
• Precision technologies for the management of reproduction in dairy cows.. Tropical animal health and production, 2023.
• Impact of Automation Level of Dairy Farms in Northern and Central Germany on Dairy Cattle Welfare.. Animals : an open access journal from MDPI, 2024.
• Birth of dairy 4.0: Opportunities and challenges in adoption of fourth industrial revolution technologies in the production of milk and its derivatives.. Current research in food science, 2023.
• Automation, Climate Change, and the Future of Farm Work: Cross-Disciplinary Lessons for Studying Dynamic Changes in Agricultural Health and Safety.. International journal of environmental research and public health, 2023.
• Short communication: Technologies and milking practices that reduce hours of work and increase flexibility through milking efficiency in pasture-based dairy farm systems.. Journal of dairy science, 2020.
• Adoption of Precision Technologies by Brazilian Dairy Farms: The Farmer's Perception.. Animals : an open access journal from MDPI, 2021.
• Symposium review: Precision technologies for dairy calves and management applications.. Journal of dairy science, 2021.
• Automatic lameness detection in cattle.. Veterinary journal (London, England : 1997), 2019.
• Feed cost efficiency in robotic milking systems: an analysis of revenue minus feed cost across dairy cow groups in southern Brazil.. 2026.
• Genetic analyses of udder conformation traits and daily milk yield measured by robotic milking systems using repeatability and random regression models in American Holstein cattle.. 2026.
• Genome-wide association and functional genomic analyses of teat placement traits derived from robotic milking systems in American Holstein cattle.. 2026.
• Genome-wide association and functional genomic analyses for udder conformation traits derived from data recorded by robotic milking systems in American Holstein cattle.. 2025.
• Impact of different stall layouts with robotic milking systems on the behavioral pattern of multiparous cows.. 2024.
• Genetic parameters for udder conformation traits derived from Cartesian coordinates generated by robotic milking systems in North American Holstein cattle.. 2024.
• Transitioning dairy cows to automatic milking: Effects of different training methods on behavioral responses during the first 3 milkings.. 2026.
• Modeling the Adaptation of Dairy Cows to Automatic Milking Systems Using Statistical Methods and Machine Learning: Development of the Robotic Adaptability Index.. 2026.
• Education about smart dairy farming using artificial intelligence. Agricultural and Environmental Education, 2026.
• Cow Milk Quality Determination Using a Near-Infrared Spectroscopic Sensing System for Smart Dairy Farming. The 10th International Electronic Conference on Sensors and Applications, 2023.
• Enhancing Dairy Farming: An Analysis of IoT, Sensors, and GPS-based Technologies for Disease Detection and Health Monitoring. International Conference Intelligent Computing and Control Systems, 2025.
• IoT Based Fog and Cloud Analytics in Smart Dairy Farming. 2021 International Conference in Advances in Power, Signal, and Information Technology (APSIT), 2021.
• Environmental Monitoring and Smart Automated Cleaning for Sustainable Dairy Farming. 2025 International Conference on Electrical, Communication, and Computing Technologies (iCONECCT), 2025.
• Chain cooperation as a critical success factor in Smart Dairy Farming. 2015.
• Wearable Collar Technologies for Dairy Cows: A Systematized Review of the Current Applications and Future Innovations in Precision Livestock Farming. Animals, 2025.
• Hair cortisol concentration of dairy cattle is unrelated to automation level of dairy farms-however, it can reflect Welfare Quality® measures. Frontiers in Animal Science, 2025.
• Assessment of Production Technologies on Dairy Farms in Terms of Animal Welfare. Applied Sciences Switzerland, 2024.
• Research on Application Technology of 5G Internet of Things and Big Data in Dairy Farm. 2021 International Wireless Communications and Mobile Computing Iwcmc 2021, 2021.

This article is educational and is not a substitute for veterinary diagnosis, treatment, public-health guidance, or regulatory reporting.