Facilitating Learning Opportunities, Cultivating Knowledge and Welfare through Integrated Sensing and Expertise (FLOCKWISE): A novel technology for welfare-led productivity gains in laying hen farming.
Egg farmers are about to get a digital flock manager that listens to chickens and learns from their squawks. The FLOCKWISE project will retrofit FAI’s existing BirdBox system with sound-recording sensors and artificial intelligence to continuously monitor hen vocalisations, behaviour, and egg quality, then feed that data into a community learning tool that tells farmers which interventions actually improve welfare. This matters because UK egg farmers face a triple squeeze: soaring feed and electricity costs have driven many out of business, causing nationwide egg shortages; they face mounting pressure to report on environmental and animal welfare impacts; and emerging threats like avian influenza and shifting chicken breeds demand new husbandry approaches. Current management tools lack real-time, welfare-driven guidance. If successful, FLOCKWISE could transform cage-free egg production by identifying the specific management changes that reduce the most problematic welfare issues—such as feather pecking or disease outbreaks—while simultaneously cutting feed waste, lowering carbon footprints, and boosting flock productivity. The system builds on an existing collaboration between FAI, Newcastle University, and The Lakes Free Range Egg Company, with new partners from across the supply chain. The result would be a practical, data-driven tool that helps farmers keep hens healthier, farms more profitable, and shelves stocked with eggs.
View original technical description
Today's markets form a very challenging environment for egg farmers. Due to soaring costs, including feed and electricity, many have left the industry, and this has led to recent UK-wide egg shortages. Farmers are also under increasing pressure to improve and report on the environmental and ethical (including animal welfare) impact of farming. Furthermore, there are emerging and moving disease challenges, such as avian influenza (bird flu), shifts in market dynamics and changes in chicken breeds that require different welfare and husbandry requirements. This project will transform FAI's existing flock management system BirdBox to develop **Facilitating Learning Opportunities, Cultivating Knowledge and Welfare through Integrated Sensing and Expertise (FLOCKWISE)** which will use state-of-the-art sensors to continuously monitor the birds and their environment, and use artificial intelligence to learn about the best management practices to support farmers with targeted guidance to address these significant challenges. **FLOCKWISE** will incorporate novel sound recording to understand chicken vocalisations as well as egg quality data collected from the factory to detect health and welfare problems in real-time. Using these novel measures of welfare and data collected by commercial farmers, we will build a community learning tool. The tool iteratively identifies which interventions work to reduce the most problematic welfare challenges on farm, supporting farmers to achieve higher health, welfare, and productivity in their flocks, whilst improving resource use, reducing environmental impact and carbon footprint of the cage-free laying industry. This ambitious project is feasible because it builds on an existing and successful collaboration between FAI, Newcastle University, and The Lakes Free Range Egg Company and brings in new partners, CIEL and Argi-EPI, and a steering group from across the supply chain to further capacity and reach. The team provides a unique combination of practical experience of egg farming, supply chain knowledge, alongside cutting-edge research expertise in animal welfare, machine learning and social science, which has the potential to dramatically improve both hen health and welfare, egg farm profitability, and environmental impact of laying hen farming in the near future.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know