Duration: 10/01/2026 to 09/30/2031

Administrative Advisor(s):

NIFA Reps:

Non-Technical Summary

Precision Management of Animals (PMA) integrates sensors, automation, and data analytics to modernize livestock management. Producers now work amid changing welfare expectations, reduced antibiotic use, recurring disease threats, climate variability, environmental pressures, and persistent labor shortages. As livestock and poultry systems consolidate, operations manage more animals with fewer, often less-experienced staff, making early detection of illness or declining performance increasingly difficult. Many behavioral and physiological cues are subtle and easily missed during routine observation.

PMA technologies, such as wearable sensors, computer-vision systems, audio monitoring, and environmental sensing platforms, provide continuous, real-time information. These tools enable earlier identification of health challenges, more targeted interventions, improved facility management, and reduced reliance on antimicrobials. The resulting datasets also reveal behavioral and physiological traits that form new phenotypes important for long-term genetic improvement, including thermotolerance, social behavior, and maternal performance. Collaboration among engineers, computer scientists, veterinarians, and animal scientists continues to grow as these data streams are translated into practical decision-support tools.

Continued progress in PMA requires coordinated multistate efforts, as the challenges facing producers have intensified. The North Central Region produces more than one-third of U.S. livestock and poultry and has strong Experiment Station and Cooperative Extension capacity to lead this work. Since this initiative began, national conferences, expanded training programs, and new faculty appointments have strengthened the field’s research foundation. The PMA multistate committee remains essential for setting priorities, sharing knowledge, engaging with industry partners, and advancing technologies that can be applied across species and production systems.

Statement of Issues and Justification

Precision Management of Animals (PMA) integrates sensors, data analytics, and automation within livestock environments. These tools are reshaping how producers monitor animals in systems that face increasing pressure from changing welfare expectations, limitations on antibiotic use, recurring and emerging diseases, environmental regulations, climate variability, and chronic labor shortages. Consolidation has expanded the number of animals under the care of a relatively small workforce. Under these conditions, it becomes difficult to recognize early signs of illness or performance decline. Subtle changes in behavior or physiology are often missed during routine observation, especially in species with minimal individual identifiers such as broilers, laying hens, or pigs.

The concept of PMA aligns closely with the broader field of precision livestock farming (PLF), which focuses on continuous, automated monitoring of animals and their environments. PLF and PMA share the goal of improving management by leveraging sensor-based information to inform timely, informed decisions. PMA emphasizes the integration of these tools into management practices across U.S. production systems, and PLF provides the technological foundation that enables these practices to function at a commercial scale.

Labor availability continues to be one of the most persistent constraints. Producers struggle to recruit and retain employees in sufficient numbers, and turnover rates remain high. Fewer caretakers are responsible for more animals, often across multiple barns or sites. This situation limits the ability to identify individual animals that are beginning to experience health or welfare issues and can introduce safety risks for both animals and workers. Production losses and welfare challenges increase when minor changes in activity, posture, or performance are overlooked.

Commercial livestock systems have traditionally relied on herd- or flock-level assessment. Although caretakers observe animals daily, time constraints make it nearly impossible to consistently identify individuals that need attention. Rapid and reliable individual-level monitoring is therefore essential. PMA technologies, such as wearable sensors, machine-vision systems, microphones, environmental monitors, and integrated data platforms, support continuous observation of groups and individuals. These tools detect subtle behavioral patterns that signal stress, disease, or injury and support targeted care that improves individual outcomes. They also enable more responsive management practices, including adjustments to feeding, ventilation, and lighting that better align with natural animal behavior.

To reach their full value, PMA systems must integrate production, environmental, health, and behavioral data into outputs that are clear, reliable, and useful for producers. Individual-level information accelerates detection and treatment of clinical and subclinical disease. Earlier intervention reduces animal suffering, prevents disease spread, lowers antimicrobial use, and decreases medication and treatment costs. Benefits extend to workers through improved safety and more predictable workflows, and to facilities through improved efficiency and reduced environmental variability.

PMA also creates opportunities to define novel phenotypes that cannot be measured through traditional observation. Continuous digital monitoring provides information related to maternal behavior, disease resilience, thermotolerance, activity patterns, social interactions, feeding behavior, gait characteristics, and responses to environmental stressors. These novel phenotypes have immediate relevance for management and long-term value for genetic improvement. Breeding programs increasingly incorporate sensor-derived phenotypes to identify animals that are adaptable, productive, and robust. Engineers use these digital data streams to evaluate how design, ventilation, lighting, stocking density, and environmental conditions shape behavior and performance, which supports innovation in barn design and climate adaptation.

The rapid growth of PMA has accelerated the shift from primarily manual animal care to an integrated, data-driven management model. This work requires collaboration across engineering, data science, animal science, veterinary medicine, and genetics. Electrical engineers contribute to sensor development, computer scientists design machine-learning models, animal scientists interpret behavior and welfare, veterinarians guide health-related applications, and agricultural and biological engineers integrate these components into functional systems.

Livestock production practices vary across regions, which reinforces the need for coordinated multistate efforts. The North Central Region represents more than one-third of U.S. livestock and poultry production and supports a large agricultural economy. Its Experiment Stations and Cooperative Extension networks are positioned to advance PMA research and guide deployment. Since the initial formation of this multistate project, interest and capacity in PMA and PLF have expanded significantly. The U.S. Precision Livestock Farming Conferences held in 2023 (Knoxville, TN) and 2025 (Lincoln, NE) demonstrate national and international engagement in this area. Universities across the region continue to add faculty positions that support PMA research, reflecting recognition of the need for long-term investment in this discipline.

The PMA multistate committee remains essential for maintaining coordinated progress. It brings together expertise from engineering, animal behavior, genetics, veterinary medicine, and data science to address problems that exceed the capacity of individual institutions. Shared knowledge, aligned research priorities, cross-station collaboration, and industry engagement strengthen the development and evaluation of PMA tools. This coordinated structure ensures that research outcomes are practical, scalable, and applicable across livestock species and production systems, and it underscores the continued relevance of renewing this project.

Related, Current and Previous Work

NC1211 Precision Livestock Farming for Sustainable Animal Systems will continue to advance sensing systems, machine learning tools for data summarization, and the development and deployment of integrated monitoring technologies. A review of CRIS data indicates that the work proposed in NC1211 does not duplicate activities in other multistate projects. NC1211 combines engineering, animal science, and data science, and its focus on individual-animal monitoring distinguishes it from projects that concentrate on production systems or management strategies. According to the CRIS database, four multistate projects include components related to this proposal, although each has a distinct scope. 

S1074: Fostering Technologies, Metrics, and Behaviors for Sustainable Advances in Animal Agriculture

S1074 concentrates on sustainable intensification at the farm and system level. Its activities emphasize management practices, sustainability metrics, and decision-support tools that support whole-farm resilience and environmental outcomes. NC1211 differs in its focus on precision livestock farming technologies that generate individual-level information. These technologies support identification, monitoring, and management of animals through sensing and data analytics. S1074 addresses system-wide sustainability, and NC1211 provides the sensing and analytic tools that can contribute animal-level information for those broader evaluations.

NC1181: Optimizing Forage and Grazing Cattle Management

NC1181 focuses on grazing and forage systems and seeks to improve beef production efficiency through better forage resource use, grazing strategies, and seasonal management. Its activities support expansion of forage supply, extension of grazing periods, reduction of feed costs, and improvement of sustainability and profitability in cow–calf and stocker enterprises. NC1211 differs by concentrating on technologies that operate at the individual-animal level, including sensors, analytics, and automation for real-time monitoring of behavior, health, and welfare. NC1181 advances forage and grazing management, and NC1211 advances engineering and data-driven tools used across many production environments. 

NC1029: Animal Behavior and Welfare Committee

NC1029 emphasizes methods for measuring animal behavior and welfare. Objective 1 focuses on the development of behavioral and physiological indicators of welfare, including the validation of automated methods for measuring individual animals. Objective 2 focuses on strengthening the scientific basis of welfare assessment and auditing programs, including the use of precision dairy technologies already in commercial use. In its current rewrite, NC1211 concentrates on automated collection of behavioral information and the use of PMA data to support welfare assessment. Although these activities relate to aspects of NC1029, NC1211 includes welfare but also addresses performance, management, and environmental monitoring across species and production systems, while NC1029 is centered on welfare-specific measures only.

NE-2442: Enhancing Poultry Production Systems through Emerging Technologies and Husbandry Practices

NE-2442 incorporates emerging technologies within poultry systems. Objective 1 centers on integrating technological advances into poultry operations through collaborative and translational research. One area of emphasis is the development of blockchain-based production infrastructure. NC1211 differs in both scope and focus. NE-2442 targets poultry systems specifically and includes technologies outside the core of precision livestock farming. NC1211 addresses engineering and data-driven tools used across livestock species and concentrates on individual-animal monitoring through sensing and analytics.

Objectives

1. Develop, integrate, and validate sensing and automation technologies
   Comments: Develop, integrate, and validate sensing and automation technologies that improve animal health, welfare, environmental sustainability, and production efficiency across livestock and poultry species.
2. Advance data science and artificial intelligence approaches for multimodal PMA/PLF datasets
   Comments: Advance data science and artificial intelligence approaches for multimodal PMA/PLF datasets to support real-time decision making, prediction, and automation in commercial settings
3. Evaluate adoption, usability, and the economic and welfare impacts of PLF systems
   Comments: Evaluate adoption, usability, and the economic and welfare impacts of precision systems in commercial and research environments to ensure scalability, robustness, and producer trust.
4. Promote data interoperability, cybersecurity, and workforce development for PLF systems
   Comments: Promote data interoperability, cybersecurity, and workforce development through the integration of sensing tools, engineering designs, and phenotypic measurements, generating reliable data streams that support scalable livestock management systems.

Methods

There is a continued shift toward housing animals in larger social groups across commercial livestock and poultry industries. These production environments make animal monitoring more difficult for caretakers, particularly in systems affected by labor shortages and high turnover. Precision management approaches provide tools that help address these challenges through integrated sensing, automation, and data analytics that support timely decision making. This project aligns with the USDA Science and Research Strategy, 2023–2026: Cultivating Scientific Innovation, with emphasis on the priorities of Accelerating Innovative Technologies and Translating Research into Action. Research within this framework will address labor constraints, strengthen illness surveillance in group-housed animals, and advance technologies for capturing, quantifying, and analyzing behavior through the development, validation, and application of modern sensing systems and data-driven methodologies.

 

Objective 1. Development and Integration of Sensing Technologies

Because no single technology can capture the complexity of modern livestock and poultry systems, this objective focuses on advancing and integrating vision-based platforms, wearable and identification sensors, and environmental and air-quality monitors. These systems will support continuous and accurate assessment of animals and their surroundings. Research will refine individual sensor technologies and develop multimodal systems that can be applied across species and production settings.

 

Vision-based systems

Digital, depth, and thermal imaging provide complementary information for monitoring posture, gait, behavior, welfare, and body composition in commercial environments. Digital imaging has been used to detect feeding, drinking, aggression, resting, exploration, and individual animals within visually similar groups (Bello and Olubummo, 2024; Chen et al., 2019; Li et al., 2020; Zhang et al., 2022). Depth cameras provide 3D information that supports estimation of body shape, weight, lying and standing postures, and gait asymmetry associated with lameness or discomfort (Chen et al., 2025; Condotta et al., 2020; Ma et al., 2024; Pacheco et al., 2024; Ruchay et al., 2020). Thermal imaging identifies patterns linked to heat stress, fever, inflammation, and localized injury (Brown-Brandl et al., 2023; Mota-Rojas et al., 2021; Orman and Endres, 2016; Whittaker et al., 2023). These modalities support extraction of locomotion trajectories, detection of altered activity, assessment of social interactions, and evaluation of body composition. When combined with other sensors, vision-based platforms strengthen multimodal PMA systems capable of monitoring individuals and groups in large commercial herds and flocks where continuous human observation is not feasible (Mora et al., 2024; Zhao et al., 2025). Work at Auburn University (AU), Clemson University , Iowa State University (ISU), Michigan State University (MSU), North Carolina State University (NCSU), North Dakota State University (NDSU), the University of Georgia (UGA), the University of Illinois (UofI), the University of Minnesota (UMN), the University of Missouri (MU), the University of Nebraska–Lincoln (UNL), the University of Tennessee (UT), and the University of Wisconsin (UW) will continue advancing digital and depth-based imaging to quantify behavior, activity patterns, body condition, and animal movement across species and production environments.

 

Wearable and identification sensors

Wearable and identification sensors, including RFID, ultrawideband (UWB), Bluetooth Low Energy (BLE), accelerometers, inertial measurement units (IMUs), and physiological devices, provide continuous tracking of movement, feeding behavior, physiology, and interactions with the environment. RFID supports individual identification and records feeding and drinking events, visit duration, intake patterns, and competitive interactions that can indicate early illness or social stress (Brown-Brandl et al., 2019; Funk et al., 2024). UWB and BLE systems provide real-time 2D and 3D information on position, movement trajectories, resting locations, and social-contact networks in groups where visual tracking is challenging (Benaissa et al., 2023; Du et al., 2021; Homer et al., 2013; Paszynski et al., 2021; Walker et al., 2024). Accelerometers and IMUs generate high-frequency data on movement, posture transitions, lying behavior, and gait symmetry, supporting automated detection of thermal strain, lameness, maternal activity, and early disease indicators (Chapa et al., 2020; Fan et al., 2022; Ferguson et al., 2025; Macon et al., 2021; Oczak et al., 2022; Pereira et al., 2020). Physiological wearables, including skin or rumen temperature sensors, respiration monitors, and heart-rate devices, provide additional measures related to heat load, metabolic status, and stress physiology (Ding et al., 2025; Du et al., 2021; Sharma, 2025; Yu et al., 2024). Integrating these systems creates detailed digital profiles that support early detection of welfare impairments, real-time health alerts, and more precise management across swine, cattle, poultry, and small ruminants. Combined datasets also strengthen the development of behavior- and physiology-based phenotypes used in genetic programs (Brito et al., 2020; Neethirajan and Kemp, 2021; Silva et al., 2021). Work at AU, ISU, KU Leuven (KU), MSU, UGA, UofI, UNL, UT, University of Vermont (UV), and UW will continue refining wearable, identification, and physiological sensors for use in production environments.

 

Environmental and air-quality sensors

Environmental and air-quality sensors measure temperature, humidity, airspeed, lighting, particulate matter, and gases such as NH₃, CO₂, CH₄, H₂S, and VOCs to characterize microclimates that influence animal comfort, health, and emissions. Accurate sensing supports ventilation management, heat-stress prevention, and environmental control strategies (Avery et al., 1975; Ni et al., 2012). Validation will occur in experimental and commercial facilities to confirm reliability under field conditions. Modern systems often use multi-sensor and IoT-based networks that combine metal-oxide gas sensors, NDIR modules, electrochemical detectors, dust counters, and microclimate sensors to generate real-time datasets. Data-fusion methods improve estimation of gases and microclimate parameters compared with single-sensor systems (Chen and Shen, 2023). Foundational livestock air-quality studies established techniques for measuring emissions and ventilation relationships (Anthony et al., 2017). Recent work continues to refine automated gas-measurement and calibration systems for poultry, swine, and dairy operations (Cardador et al., 2022; Hu et al., 2014). Environmental sensing also provides insight into animal responses to microclimate. Mapping THI, airflow, and lighting in dairy barns shows linkages with lying behavior, activity, rumination, and milk performance (Nienaber and Hahn, 2007; Samer et al., 2011). In extensive beef systems, networks that integrate weather, soil, thermal imaging, and remote weighing describe relationships among forage, microclimate, and movement across large landscapes (Iwasaki et al., 2019; Mishra and Sharma, 2023). Pollutant concentrations vary across species, seasons, housing systems, and ventilation strategies, which reinforces the need for multi-point monitoring (Childers et al., 2001; Li et al., 2022). Integrating environmental, behavioral, physiological, and video data improves early-warning capabilities and supports emission-reduction strategies (Menendez et al., 2022). Work at ISU, NDSU, UofI, UMN, MU, UNL, and UW will continue environmental monitoring and quantification of CO₂ and CH₄ emissions.

  

Objective 2. Data Science and AI for Precision Livestock Farming

PLF data are characterized by large volume, high dimensionality, and heterogeneity. Researchers will apply advanced data analytics, including:

• Machine learning and deep learning for classification, prediction, and anomaly detection
• Enhanced data-labeling methodologies to rapidly generate ground-truth datasets for model development
• Unsupervised and self-supervised learning for automated feature discovery
• Edge-AI and federated learning for on-farm, privacy-preserving data processing
• Explainable AI (XAI) and visualization tools to enhance producer interpretation and trust

Data standardization and FAIR (Findable, Accessible, Interoperable, Reusable) principles will guide all data-handling efforts. Shared repositories will support multi-institutional collaboration and reproducibility.

Objective 2 focuses on advancing data science and artificial intelligence to extract actionable insight from the high-volume and heterogeneous data produced by precision livestock farming (PLF) systems. Recent developments in machine learning and deep learning provide opportunities to detect patterns, classify behaviors, predict biological outcomes, and identify anomalies across species and production environments (Riaboff et al., 2022). Integrating these techniques with diverse data streams, including accelerometer files, images, environmental data, and feeding and weighing records, supports development of predictive models capable of real-time decision making (Brennan et al., 2023). PLF data pipelines continue to face challenges related to inconsistent data structures, manual labeling requirements, and limited computational training among animal science professionals (Tedeschi, 2019). Enhanced data-labeling methodologies, including semi-automated video annotation and open-source pipelines for processing accelerometer data, can reduce the time needed to curate ground-truth datasets and improve reproducibility (Andriamandroso et al., 2017). Unsupervised and self-supervised learning methods support automated feature discovery and allow detection of emerging behaviors or health concerns without extensive labeled data (Wolfert et al., 2017). As edge computing becomes more accessible, on-animal and near-sensor processing will enable private, low-latency analytics suitable for remote production systems (Alonso et al., 2020; Menendez III et al., 2022). Federated learning will allow collaboration across institutions while preserving data privacy and ownership, which is important for producer-level datasets (Torky and Hassanein, 2020). To ensure interpretability and producer trust, Objective 2 incorporates explainable AI methods that link model outputs with biological mechanisms and management actions (Tedeschi et al., 2021). Visualization tools and decision-support interfaces will make model outputs accessible to researchers and producers and will help support adoption. All workflows will follow FAIR principles to strengthen data interoperability and build shared repositories that support long-term innovation in PLF ((Bahlo and Dahlhaus, 2021; Morota et al., 2018). Researchers at AU, ISU, MSU, NCSU, NDSU, UofI, UMN, MU, UNL, UT, UV, and UW are developing AI models to summarize digital data into novel phenotypes and insights to improve engineering design and support decision-making.

 

Objective 3. Adoption, Usability, and Impact Assessment

This objective will assess adoption barriers and economic, welfare, and social outcomes. Key areas include:

• Economic feasibility analyses of emerging PLF systems
• Assessment of user experience and data literacy among caretakers and managers
• Measurement of welfare improvements and labor efficiency gains; integration of producer feedback into system design

Adoption of precision livestock farming (PLF) systems is influenced by economic, practical, and social factors that extend beyond technical performance. Evaluating the economic feasibility of PLF technologies, including cost structures, labor reallocation, return on investment, and long-term operational impacts, will clarify their potential value to producers (Akinyemi et al., 2025; Kopler et al., 2023). Because the effectiveness of PLF tools depends on how caretakers and managers interact with sensor-derived information, this objective will also assess user experience, data literacy, and the compatibility of decision-support outputs with routine management workflows (Guarino et al., 2017). Measures of animal welfare, early illness detection, and labor efficiency associated with automated sensing and analytics will help quantify outcomes that matter to producers and the broader supply chain (Khan et al., 2025). Producer perceptions, preferences, and practical feedback will be incorporated into design and deployment processes to ensure that PLF systems address on-farm needs, reduce adoption barriers, and align with production, welfare, and sustainability goals (Kaur et al., 2023; Papakonstantinou et al., 2024). Participating institutions include AU, Clemson University, ISU, MSU, NCSU, NDSU, South Dakota State University (SDSU), UGA, UofI, UMN, MU, UNL, and UT.

 

Objective 4. Interoperability, Cybersecurity, and Workforce Development

The committee will support open-data initiatives, API-based integration frameworks, and cloud-edge architectures that ensure interoperability across hardware and software platforms. A new emphasis will be placed on:

• Interoperability of data systems to follow FAIR guidelines and create road maps to achieve effective tools, phenotyping, and engineering design
• Cybersecurity for farm data
• Digital workforce training through hands-on and virtual platforms such as mobile PLF trailers, AI chatbots, and VR-based training
• Educational materials and graduate student mentorship to prepare the next generation of engineers and scientists

Objective 4 addresses the foundational digital infrastructure needed to support the next generation of precision livestock farming (PLF). As sensing platforms, data pipelines, and decision-support tools become more interconnected, the livestock industry must prioritize interoperability, cybersecurity, and workforce capacity to ensure that data can be reliably exchanged, protected, and applied across commercial settings. Interoperability remains a major challenge because systems often rely on proprietary formats and incompatible workflows, creating fragmentation across institutions and limiting the scalability of analytics (Bahlo and Dahlhaus, 2021; Brennan et al., 2023). To address this issue, the committee will promote open-data initiatives, standardized APIs, and cloud-edge architectures that follow FAIR (Findable, Accessible, Interoperable, Reusable) principles and allow seamless integration of feeding, weighing, emissions, environmental, and behavioral data across PLF platforms (Brennan et al., 2024). Work will also include development of engineering roadmaps for tool design, phenotyping frameworks, and model-ready datasets that reduce duplication of effort and strengthen cross-institutional research.

Cybersecurity has become increasingly important as livestock operations adopt cloud-connected systems, automated data transfers, IoT devices, and wireless communication technologies. PLF systems generate high-value data related to animal performance, management strategies, and operational efficiency, which creates vulnerabilities when information moves across Wi-Fi, LPWAN, cellular networks, and cloud servers (Barreto and Amaral, 2018; Neethirajan, 2025; Nikander et al., 2020). Analyses have identified risks associated with data breaches, unauthorized access, and cyber-physical disruption in automated feeding, weighing, and ventilation systems, which highlights the need for encrypted communication protocols, multi-factor authentication, secure APIs, and strong data-governance policies (Adams‐Progar et al., 2017; Kjønås, 2023; Van Der Linden et al., 2020). Practical cybersecurity guidelines that can be implemented across farms of different sizes will help protect producer privacy, maintain equipment reliability, and strengthen confidence in digital tools.

Workforce development is the final component of this objective. Current gaps in data-science training among students and professionals in animal science indicate the need for hands-on and accessible training programs (Cosby et al., 2022; Ramirez et al., 2019). The committee will support digital workforce development through mobile PLF trailers, interactive cloud-based tutorials, VR-based training modules, and AI-driven educational tools that introduce students and producers to data pipelines, coding workflows, open-source tools, and decision-support interfaces (Brennan et al., 2023). Graduate mentorship, cross-institutional workshops, and open-source learning repositories will complement these efforts and help broaden participation in PLF while addressing the computational skill gaps identified across the industry (Estrella and Renee Ching, 2024). Researchers at AU, ISU, KU, NDSU, UofI, UNL, UT, and UW will contribute to work in this area.

Measurement of Progress and Results

Outputs

• Automated Tools for Animal Behavior, Health, and Welfare Assessment Comments: Researchers will develop, refine, and validate improved vision-based, wearable, identification, and environmental sensors capable of reliably monitoring individual animals and their surroundings under real-world production conditions. Efforts will focus on robust system performance, field deployability, and cross-species applicability.
• Integrated Data Pipelines for Real-Time Decision Support Comments: Researchers will create real-time algorithms using advanced modeling techniques, including deep learning, computer vision, multimodal data fusion, and time-series analytics. These pipelines will support automated decision-support tools that interpret behavior, health status, body condition, movement patterns, and environmental variables.
• Shared Annotated Datasets Comments: The project will generate shared datasets ranging from single-sensor data streams to fully synchronized multimodal datasets that incorporate vision, wearable, identification, environmental, and physiological sensors. Standardized metadata, annotation guidelines, and benchmarking protocols will accompany these datasets to support reproducible research, graduate training, and cross-institutional model development.
• Publications, Workshops, and Outreach Programs Comments: NC-1211 will produce peer-reviewed articles, conference papers, technical reports, and extension resources. The committee will organize producer workshops, hands-on training opportunities, graduate learning sessions, and presentations at regional and national conferences such as USPLF. These activities will help transfer NC-1211 technologies to commercial partners, Extension faculty, and the broader research community.

Outcomes or Projected Impacts

• More Accurate and Reliable PMA Technologies Engineering refinement and validation activities will produce sensing systems capable of generating consistent, high-quality measurements in commercial settings. Improved reliability will support broader use of PMA technologies across livestock and poultry species.
• Real-Time Decision-Making and Earlier Intervention Algorithms and software developed under NC-1211 will provide real-time alerts and dashboards that allow producers to detect issues earlier, such as illness, heat stress, lameness, aggression, or maternal problems, leading to timely intervention, reduced animal suffering, and improved productivity.
• New Digital Phenotypes for Genetics and Precision Management Continuous data streams will enable the development of novel phenotypes—resilience, thermotolerance, mobility, maternal behavior, social interaction, and health indicators—that were previously difficult to measure. These phenotypes can be used by breeders, geneticists, and producers to enhance selection programs and improve long-term robustness
• Validated Systems Ready for Deployment in Commercial Operations Tools developed under NC-1211 will be validated in barns, feedlots, dairies, and poultry houses. Field validation will ensure the systems are practical, scalable, and positioned for on-farm implementation.

Milestones

(1):Establish subcommittees and data-sharing frameworks; conduct inventory of active PLF research and datasets.

(2):Conduct multi-institutional trials; share initial datasets for collaborative validation.

(3):Publish standardized algorithms and protocols for multimodal data analysis; host cross-institutional workshops.

(4):Evaluate field adoption and producer engagement; disseminate results via conferences and training programs.

(5):Publish final synthesis of findings and best-practice guidelines for data-driven livestock management.

Projected Participation

View Appendix E: Participation

Outreach Plan

The committee will disseminate results through:

• Conferences: ASABE, USPLF, ECPLF, ASAS, ADSA, PSA, and AIM for Climate events.
• Publications: Frontiers in Animal Science, Biosystems Engineering, Computers and Electronics in Agriculture, Journal of ASABE, Applied Engineering in Agriculture
• Digital Platforms: Webinars, AI-enabled chatbots, and open-access datasets.
• Workforce Training: Graduate workshops, Extension curricula, and immersive VR/AR modules for caretakers and students.

Organization/Governance

Organization and Governance

The Executive Committee will consist of a Chair, Vice-Chair, and Secretary. Subcommittees will oversee:

• Data governance and ethics.
• Education and workforce development.
• Industry partnerships and outreach.

Officers will serve one-year terms with rotation. Virtual participation and shared digital platforms will ensure equitable collaboration across institutions.

Literature Cited

Adams‐Progar, A., Fink, G.A., Walker, E., Llewellyn, D., 2017. Security and Privacy Issues in the Internet of Cows, in: Song, H., Fink, G.A., Jeschke, S. (Eds.), Security and Privacy in Cyber‐Physical Systems. Wiley, pp. 375–398. https://doi.org/10.1002/9781119226079.ch18

Akinyemi, B.E., Jessiman, L., Turner, S.P., Siegford, J., 2025. Beyond the Farm: Stakeholder Perspectives on Precision Livestock Farming in the Swine Industry. https://doi.org/10.2139/ssrn.5193279

Alonso, R.S., Sittón-Candanedo, I., García, Ó., Prieto, J., Rodríguez-González, S., 2020. An intelligent Edge-IoT platform for monitoring livestock and crops in a dairy farming scenario. Ad Hoc Networks 98, 102047.

Andriamandroso, A.L.H., Lebeau, F., Beckers, Y., Froidmont, E., Dufrasne, I., Heinesch, B., Dumortier, P., Blanchy, G., Blaise, Y., Bindelle, J., 2017. Development of an open-source algorithm based on inertial measurement units (IMU) of a smartphone to detect cattle grass intake and ruminating behaviors. Computers and electronics in agriculture 139, 126–137.

Anthony, T.R., Yang, A.Y., Peters, T.M., 2017. Assessment of interventions to improve air quality in a livestock building. Journal of agricultural safety and health 23, 247–263.

Avery, G.L., Merva, J.B., Gerrish, J.B., 1975. Hydrogen Sulfide Production in Swine Confinement Units. Transactions of the ASAE 149–151.

Bahlo, C., Dahlhaus, P., 2021. Livestock data–Is it there and is it FAIR? A systematic review of livestock farming datasets in Australia. Computers and Electronics in Agriculture 188, 106365.

Barreto, L., Amaral, A., 2018. Smart farming: Cyber security challenges, in: 2018 International Conference on Intelligent Systems (IS). IEEE, pp. 870–876.

Bello, R.-W., Olubummo, D.A., 2024. Computer Vision-Based Precision Livestock Farming: An Overview of The Challenges and Opportunities. SSRN Journal. https://doi.org/10.2139/ssrn.4770855

Benaissa, S., Tuyttens, F.A.M., Plets, D., Martens, L., Vandaele, L., Joseph, W., Sonck, B., 2023. Improved cattle behaviour monitoring by combining Ultra-Wideband location and accelerometer data. animal 17, 100730. https://doi.org/10.1016/j.animal.2023.100730

Brennan, J., Johnson, P., Olson, K., 2021. Classifying season long livestock grazing behavior with the use of a low-cost GPS and accelerometer. Computers and Electronics in Agriculture 181, 105957.

Brennan, J.R., L. Parsons, I., Harrison, M., Menendez III, H.M., 2024. Development of an application programming interface to automate downloading and processing of precision livestock data. Translational Animal Science 8, txae092.

Brennan, J.R., Menendez III, H.M., Ehlert, K., Tedeschi, L.O., 2023. ASAS-NANP symposium: Mathematical modeling in animal nutrition—Making sense of big data and machine learning: How open-source code can advance training of animal scientists. Journal of Animal Science 101, skad317.

Brito, L.F., Oliveira, H.R., McConn, B.R., Schinckel, A.P., Arrazola, A., Marchant-Forde, J.N., Johnson, J.S., 2020. Large-Scale Phenotyping of Livestock Welfare in Commercial Production Systems: A New Frontier in Animal Breeding. Front. Genet. 11, 793. https://doi.org/10.3389/fgene.2020.00793

Brown-Brandl, T.M., Adrion, F., Maselyne, J., Kapun, A., Hessel, E.F., Saeys, W., Van Nuffel, A., Gallmann, E., 2019. A Review of Passive Radio Frequency Identification Systems for Animal Monitoring in Livestock Facilities. Applied Engineering in Agriculture 35, 579–591. https://doi.org/10.13031/aea.12928

Brown-Brandl, T.M., Hayes, M.D., Rohrer, G.A., Eigenberg, R.A., 2023. Thermal comfort evaluation of three genetic lines of nursery pigs using thermal images. Biosystems Engineering 225, 1–12.

F. S. Condotta, I., Brown-Brandl, T.M., Rohrer, G.A., O. Silva-Miranda, K., 2020. Development of method for lameness detection based on depth image analysis, in: 2020 ASABE Annual International Virtual Meeting, July 13-15, 2020. Presented at the 2020 ASABE Annual International Virtual Meeting, July 13-15, 2020, American Society of Agricultural and Biological Engineers. https://doi.org/10.13031/aim.202001082

Cardador, M.J., Reyes-Palomo, C., Díaz-Gaona, C., Arce, L., Rodríguez-Estévez, V., 2022. Review of the Methodologies for Measurement of Greenhouse Gas Emissions in Livestock Farming: Pig Farms as a Case of Study. Critical Reviews in Analytical Chemistry 52, 1029–1047. https://doi.org/10.1080/10408347.2020.1855410

Chapa, J.M., Maschat, K., Iwersen, M., Baumgartner, J., Drillich, M., 2020. Accelerometer systems as tools for health and welfare assessment in cattle and pigs – A review. Behavioural Processes 181, 104262. https://doi.org/10.1016/j.beproc.2020.104262

Chen, C., Shen, C., 2023. Multi‐sensor data fusion for swine house environment evaluation and control. Agronomy Journal 115, 2731–2746. https://doi.org/10.1002/agj2.21274

Chen, C., Zhu, W., Liu, D., Steibel, J., Siegford, J., Wurtz, K., Han, J., Norton, T., 2019. Detection of aggressive behaviours in pigs using a RealSence depth sensor. Computers and Electronics in Agriculture 166, 105003. https://doi.org/10.1016/j.compag.2019.105003

Chen, Z., Huang, Q., Zhang, S., Tian, X., Yin, L., 2025. Multimodal sow lameness classification method integrating spatiotemporal features. Computers and Electronics in Agriculture 235, 110363. https://doi.org/10.1016/j.compag.2025.110363

Childers, J.W., Thompson Jr, E.L., Harris, D.B., Kirchgessner, D.A., Clayton, M., Natschke, D.F., Phillips, W.J., 2001. Multi-pollutant concentration measurements around a concentrated swine production facility using open-path FTIR spectrometry. Atmospheric Environment 35, 1923–1936.

Cosby, A.M., Fogarty, E.S., Power, D.A., Manning, J.K., 2022. Data, decision-making and demand: the importance of education and training opportunities with precision livestock farming technologies for Australian producers, in: Practical Precision Livestock Farming. Wageningen Academic, pp. 397–417.

Ding, L., Zhang, C., Yue, Y., Yao, C., Li, Z., Hu, Y., Yang, B., Ma, W., Yu, L., Gao, R., Li, Q., 2025. Wearable Sensors-Based Intelligent Sensing and Application of Animal Behaviors: A Comprehensive Review. Sensors 25, 4515. https://doi.org/10.3390/s25144515

Du, Y., Sun, G., Zheng, B., Qu, Y., 2021. Design and Implementation of Intelligent Gateway System for Monitoring Livestock and Poultry Feeding Environment Based on Bluetooth Low Energy. Information 12, 218. https://doi.org/10.3390/info12060218

Estrella, M.B., Renee Ching, M.D., 2024. Development of an Adoption Framework for Precision Livestock Farming (PLF): A Case in a Developing Economy, in: Thiruchelvam, V., Alfred, R., Ismail, Z.I.B.A., Haviluddin, H., Baharum, A. (Eds.), Proceedings of the 4th International Conference on Advances in Computational Science and Engineering, Lecture Notes in Electrical Engineering. Springer Nature Singapore, Singapore, pp. 567–585. https://doi.org/10.1007/978-981-97-2977-7_36

Fan, B., Bryant, R., Greer, A., 2022. Behavioral Fingerprinting: Acceleration Sensors for Identifying Changes in Livestock Health. J 5, 435–454. https://doi.org/10.3390/j5040030

Ferguson, H.J., Davison, C., Lima, J., Haskell, M.J., Dewhurst, R.J., Michie, C., Andonovic, I., Tachtatzis, C., Swan, A., Brooking, M., Truelove, L., Carter, L.S., 2025. Use of animal-mounted accelerometers to identify positive welfare in dairy cattle. Dairy Sci. Manag. 2, 15. https://doi.org/10.1186/s44363-025-00018-6

Funk, T.H., Rohrer, G.A., Brown-Brandl, T.M., Keel, B.N., 2024. Online feeding behavior monitoring of individual group-housed grow-finish pigs using a low-frequency RFID electronic feeding system. Translational Animal Science 8, txae051. https://doi.org/10.1093/tas/txae051

Guarino, M., Norton, T., Berckmans, Dries, Vranken, E., Berckmans, Daniel, 2017. A blueprint for developing and applying precision livestock farming tools: A key output of the EU-PLF project. Animal Frontiers 7, 12–17. https://doi.org/10.2527/af.2017.0103

Homer, E.M., Gao, Y., Meng, X., Dodson, A., Webb, R., Garnsworthy, P.C., 2013. Technical note: A novel approach to the detection of estrus in dairy cows using ultra-wideband technology. Journal of Dairy Science 96, 6529–6534. https://doi.org/10.3168/jds.2013-6747

Hu, E., Babcock, E.L., Bialkowski, S.E., Jones, S.B., Tuller, M., 2014. Methods and Techniques for Measuring Gas Emissions from Agricultural and Animal Feeding Operations. Critical Reviews in Analytical Chemistry 44, 200–219. https://doi.org/10.1080/10408347.2013.843055

Iwasaki, W., Morita, N., Nagata, M.P.B., 2019. IoT sensors for smart livestock management, in: Chemical, Gas, and Biosensors for Internet of Things and Related Applications. Elsevier, pp. 207–221.

Kaur, U., Malacco, V.M.R., Bai, H., Price, T.P., Datta, A., Xin, L., Sen, S., Nawrocki, R.A., Chiu, G., Sundaram, S., Min, B.-C., Daniels, K.M., White, R.R., Donkin, S.S., Brito, L.F., Voyles, R.M., 2023. Invited review: integration of technologies and systems for precision animal agriculture—a case study on precision dairy farming. Journal of Animal Science 101, skad206. https://doi.org/10.1093/jas/skad206

Khan, D., Zaman, H., Sultan, A., Ahmad, M.T., Bibi, R., Athar, H., Bibi, S., Ahmed, U., Yasin, U., Shahbaz, M., 2025. Exploring the Potential of Precision Livestock Farming Technologies for Enhancing Animal Welfare and Public Health. Sch J Agric Vet Sci 12, 205–212. https://doi.org/10.36347/sjavs.2025.v12i06.001

Kjønås, K., 2023. How cyber security incidents can affect Norwegian food production (Master’s Thesis). NTNU.

Kopler, I., Marchaim, U., Tikász, I.E., Opaliński, S., Kokin, E., Mallinger, K., Neubauer, T., Gunnarsson, S., Soerensen, C., Phillips, C.J.C., Banhazi, T., 2023. Farmers’ Perspectives of the Benefits and Risks in Precision Livestock Farming in the EU Pig and Poultry Sectors. Animals 13, 2868. https://doi.org/10.3390/ani13182868

Li, G., Zhao, Y., Purswell, J.L., Du, Q., Chesser, G.D., Lowe, J.W., 2020. Analysis of feeding and drinking behaviors of group-reared broilers via image processing. Computers and Electronics in Agriculture 175, 105596. https://doi.org/10.1016/j.compag.2020.105596

Li, Y., Wang, M., Chen, X., Cui, S., Hofstra, N., Kroeze, C., Ma, L., Xu, W., Zhang, Q., Zhang, F., 2022. Multi-pollutant assessment of river pollution from livestock production worldwide. Water research 209, 117906.

Ma, W., Qi, X., Sun, Y., Gao, R., Ding, L., Wang, R., Peng, C., Zhang, J., Wu, J., Xu, Z., Li, M., Zhao, H., Huang, S., Li, Q., 2024. Computer Vision-Based Measurement Techniques for Livestock Body Dimension and Weight: A Review. Agriculture 14, 306. https://doi.org/10.3390/agriculture14020306

Macon, A., Leeb, S.S.B., Markvickab, E., Rohrerc, F., Milesc, J., Brown-Brandl, T., 2021. Characterizing Lactating Sow Posture in Farrowing Crates Utilizing Automated Image Capture and Wearable Sensors. Presented at the Agricultural Engineering.

Menendez III, H.M., Brennan, J.R., Gaillard, C., Ehlert, K., Quintana, J., Neethirajan, S., Remus, A., Jacobs, M., Teixeira, I.A., Turner, B.L., 2022. ASAS–NANP Symposium: Mathematical Modeling in Animal Nutrition: Opportunities and challenges of confined and extensive precision livestock production. Journal of Animal Science 100, skac160.

Mishra, S., Sharma, S.K., 2023. Advanced contribution of IoT in agricultural production for the development of smart livestock environments. Internet of Things 22, 100724.

Mora, M., Piles, M., David, I., Rosa, G.J.M., 2024. Integrating computer vision algorithms and RFID system for identification and tracking of group-housed animals: an example with pigs. Journal of Animal Science 102, skae174. https://doi.org/10.1093/jas/skae174

Morota, G., Ventura, R.V., Silva, F.F., Koyama, M., Fernando, S.C., 2018. Big data analytics and precision animal agriculture symposium: Machine learning and data mining advance predictive big data analysis in precision animal agriculture. Journal of animal science 96, 1540–1550.

Mota-Rojas, D., Wang, D., Titto, C.G., Gómez-Prado, J., Carvajal-de La Fuente, V., Ghezzi, M., Boscato-Funes, L., Barrios-García, H., Torres-Bernal, F., Casas-Alvarado, A., Martínez-Burnes, J., 2021. Pathophysiology of Fever and Application of Infrared Thermography (IRT) in the Detection of Sick Domestic Animals: Recent Advances. Animals 11, 2316. https://doi.org/10.3390/ani11082316

Neethirajan, S., 2025. Safeguarding digital livestock farming-a comprehensive cybersecurity roadmap for dairy and poultry industries. Frontiers in Big Data 8, 1556157.

Neethirajan, S., Kemp, B., 2021. Digital Phenotyping in Livestock Farming. Animals 11, 2009. https://doi.org/10.3390/ani11072009

Ni, J.-Q., Heber, A.J., Cortus, E.L., Lim, T.-T., Bogan, B.W., Grant, R.H., Boehm, M.T., 2012. Assessment of ammonia emissions from swine facilities in the U.S.—Application of knowledge from experimental research. Environmental Science & Policy 22, 25–35. https://doi.org/10.1016/j.envsci.2012.06.001

Nienaber, J.A., Hahn, G.L., 2007. Livestock production system management responses to thermal challenges. International Journal of Biometeorology 52, 149–157.

Nikander, J., Manninen, O., Laajalahti, M., 2020. Requirements for cybersecurity in agricultural communication networks. Computers and electronics in agriculture 179, 105776.

Oczak, M., Bayer, F., Vetter, S., Maschat, K., Baumgartner, J., 2022. Comparison of the automated monitoring of the sow activity in farrowing pens using video and accelerometer data. Computers and Electronics in Agriculture 192, 106517. https://doi.org/10.1016/j.compag.2021.106517

Orman, A., Endres, M.I., 2016. Use of thermal imaging for identification of foot lesions in dairy cattle. Acta Agriculturae Scandinavica, Section A — Animal Science 66, 1–7. https://doi.org/10.1080/09064702.2016.1179785

Pacheco, V.M., Brown-Brandl, T.M., De Sousa, R.V., Rohrer, G.A., Sharma, S.R., Martello, L.S., 2024. Deep learning-based sow posture classifier using colour and depth images. Smart Agricultural Technology 9, 100563. https://doi.org/10.1016/j.atech.2024.100563

Papakonstantinou, G.I., Voulgarakis, N., Terzidou, G., Fotos, L., Giamouri, E., Papatsiros, V.G., 2024. Precision Livestock Farming Technology: Applications and Challenges of Animal Welfare and Climate Change. Agriculture 14, 620. https://doi.org/10.3390/agriculture14040620

Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (Eds.), 2021. Computational Science – ICCS 2021: 21st International Conference, Krakow, Poland, June 16–18, 2021, Proceedings, Part IV, Lecture Notes in Computer Science. Springer International Publishing, Cham. https://doi.org/10.1007/978-3-030-77970-2

Pereira, G.M., Heins, B.J., O’Brien, B., McDonagh, A., Lidauer, L., Kickinger, F., 2020. Validation of an ear tag–based accelerometer system for detecting grazing behavior of dairy cows. Journal of Dairy Science 103, 3529–3544. https://doi.org/10.3168/jds.2019-17269

Ramirez, B.C., Xin, H., Halbur, P.G., Beermann, D.H., Hansen, S.L., Linhares, D.C., Peschel, J.M., Rademacher, C.J., Reecy, J.M., Ross, J.W., 2019. At the intersection of industry, academia, and government: how do we facilitate productive precision livestock farming in practice? Animals 9, 635.

Riaboff, L., Shalloo, L., Smeaton, A.F., Couvreur, S., Madouasse, A., Keane, M.T., 2022. Predicting livestock behaviour using accelerometers: A systematic review of processing techniques for ruminant behaviour prediction from raw accelerometer data. Computers and Electronics in Agriculture 192, 106610.

Ruchay, A., Kober, V., Dorofeev, K., Kolpakov, V., Miroshnikov, S., 2020. Accurate body measurement of live cattle using three depth cameras and non-rigid 3-D shape recovery. Computers and Electronics in Agriculture 179, 105821. https://doi.org/10.1016/j.compag.2020.105821

Samer, M., Loebsin, C., Fiedler, M., Ammon, C., Berg, W., Sanftleben, P., Brunsch, R., 2011. Heat balance and tracer gas technique for airflow rates measurement and gaseous emissions quantification in naturally ventilated livestock buildings. Energy and Buildings 43, 3718–3728.

Sharma, R., 2025. Wearable biosensors: an aid for cattle well-being. Sensor Review 45, 544–562. https://doi.org/10.1108/SR-11-2024-0933

Silva, F.F., Morota, G., Rosa, G.J.D.M., 2021. Editorial: High-Throughput Phenotyping in the Genomic Improvement of Livestock. Front. Genet. 12, 707343. https://doi.org/10.3389/fgene.2021.707343

Tedeschi, L.O., 2019. ASN-ASAS SYMPOSIUM: FUTURE OF DATA ANALYTICS IN NUTRITION: Mathematical modeling in ruminant nutrition: approaches and paradigms, extant models, and thoughts for upcoming predictive analytics. Journal of animal science 97, 1921–1944.

Tedeschi, L.O., Greenwood, P.L., Halachmi, I., 2021. Advancements in sensor technology and decision support intelligent tools to assist smart livestock farming. Journal of Animal Science 99, skab038.

Torky, M., Hassanein, A.E., 2020. Integrating blockchain and the internet of things in precision agriculture: Analysis, opportunities, and challenges. Computers and electronics in agriculture 178, 105476.

Van Der Linden, D., Michalec, O.A., Zamansky, A., 2020. Cybersecurity for smart farming: socio-cultural context matters. IEEE Technology and Society Magazine 39, 28–35.

Walker, A.M., Jonsson, N.N., Waterhouse, A., McDougall, H., Kenyon, F., McLaren, A., Morgan-Davies, C., 2024. Development of a novel Bluetooth Low Energy device for proximity and location monitoring in grazing sheep. animal 18, 101276. https://doi.org/10.1016/j.animal.2024.101276

Whittaker, A.L., Muns, R., Wang, D., Martínez-Burnes, J., Hernández-Ávalos, I., Casas-Alvarado, A., Domínguez-Oliva, A., Mota-Rojas, D., 2023. Assessment of Pain and Inflammation in Domestic Animals Using Infrared Thermography: A Narrative Review. Animals 13, 2065. https://doi.org/10.3390/ani13132065

Wolfert, S., Ge, L., Verdouw, C., Bogaardt, M.-J., 2017. Big data in smart farming–a review. Agricultural systems 153, 69–80.

Yu, Z., Han, Y., Cha, L., Chen, S., Wang, Z., Zhang, Y., 2024. Design of an intelligent wearable device for real-time cattle health monitoring. Front. Robot. AI 11, 1441960. https://doi.org/10.3389/frobt.2024.1441960

Zhang, Z., Zhang, H., He, Y., Liu, T., 2022. A Review in the Automatic Detection of Pigs Behavior with Sensors. Journal of Sensors 2022, 1–17. https://doi.org/10.1155/2022/4519539

Zhao, A., Wu, H., Fan, D., Li, K., 2025. Individual Cow Recognition Based on Ultra-Wideband and Computer Vision. Animals 15, 456. https://doi.org/10.3390/ani15030456

Attachments

Land Grant Participating States/Institutions

IL, NE

Non Land Grant Participating States/Institutions