Dr. Hovey is wearing a blue jumpsuit and is holding a piglet
Dr. Russ Hovey, a professor in the Department of Animal Science, is part of a team of researchers who are working on a new grant aimed at using artificial intelligence to help piglets start their lives strong and healthy. (Kevin Ulrich/UC Davis)

Smart Start: Grant Aims to Help Piglets Have a Strong Start to Life

A strong start in life is more than just an advantage—it’s the critical foundation for a healthy, productive future. A solid beginning in life is crucial for piglets, as their early health is the foundation for both their survival and future growth. This early development not only impacts their productivity but also has long-lasting effects on the overall economic success and sustainability of the farm.

As the result of genetic improvement and management gains, some sows are able to give birth to larger litters than in years past, meaning there simply aren’t enough teats for each piglet in a litter to nurse. As a result, some are at risk of improper development or may die before weaning. 

Piglets not having enough to eat is critical to animal welfare, the emotional well-being of the caretakers, and overall farm economics. All of which is why Dr. Russ Hovey, a professor in the Department of Animal Science at UC Davis, is so eager to start work on a recent grant he and an international team of researchers have been awarded that involves the use of artificial intelligence (AI) to monitor and study the nursing ability of sows, and the early life of their piglets.

The National Institute of Food and Agriculture (NIFA) has awarded the research team a $1 million grant over four years for their proposal, IDEAS Tripartite: Automated Piglet and Sow Monitoring for Early Detection of At-Risk Piglets. This project is one of 11 selected for the Inter-Disciplinary Engagement in Animal Systems (IDEAS) program, which supports integrated research and outreach projects focused on precision animal management, the environmental impacts of animal production, and the societal aspects of animal welfare.

Dr. Hovey will work with fellow researchers from Michigan State, North Carolina State University, the University of Nebraska-Lincoln, Queen’s University Belfast in Northern Ireland, the Agri-Food and Biosciences Institute in Belfast, the Agriculture and Food Development Authority of the Republic of Ireland and the Sherbrooke Research and Development Centre of Agriculture and Agri-Food Canada to better understand some of the mysteries that remain for the early days of a piglet. 

“This is a big problem, and this is the right team to help solve it,” Dr. Hovey said.

AI insight into a piglet’s early life

One of the main goals of the study is to develop a method to automatically track piglets’ nursing patterns, teat choices, and sow behavior. To do this, the team will use artificial intelligence to develop an automated computer system to follow piglet movement and nursing activity. With cameras placed around a sow and her piglets, all movements will be viewed and evaluated in real time. 

“As it is now, it’s extremely labor-intensive and difficult to have a room full of sows with their piglets and to identify who is struggling and why,” Dr. Hovey explained.

The hope with the computer vision system is that it will detect nuances that the human eye can’t. Each camera will focus on sows and their piglets 24 hours a day, offering researchers real time data.  

A head start to success

For piglets to start life healthy, it’s essential they consume enough in the first few days. This is particularly important because during this period they consume colostrum, the first milk produced by the sow after birth. Colostrum is rich in antibodies that provide passive immunity, helping protect piglets from diseases and infections throughout their life.

“One of the objectives of the grant is to bring the expertise of videography (AI) and recognition software to the monitoring of litters and helping the farm managers to make those decisions about which piglets are struggling, and which ones need intervention,” Dr. Hovey said. “Because if they don’t thrive when they’re young, then they will underperform for the rest of their lives.”

Dr. Hovey is wearing a blue jumpsuit and is looking over a pen of swine
One of the primary objectives of this research project is to produce strong data to educate sow and piglet husbandry practices on the farm. (Kevin Ulrich/UC Davis)

Dr. Hovey went on to explain that it is extremely difficult to measure how much milk sows are producing, unlike cows that are milked regularly in a controlled setting like a milking parlor. Their milk production is usually assessed indirectly, often through observation or by measuring piglet weight gain, which is not as precise. To address this limitation, Hovey and co-workers will use a stable isotope to directly measure the amount of milk produced by each teat over time. Combining these data with real-time camera data could be crucial to understanding how much a sow is producing and how much a piglet is consuming, which in Dr. Hovey’s opinion could be, “a game changer.”

“We’re trying to get a lot of raw data on how much milk a piglet consumed, what its activity was, using the cameras of course, how did it perform, compared to the next one, and at what point can we identify which piglets didn’t get enough to drink and can we step in sooner to possibly cross foster them, or do we have a problem with the mom’s udder. Maybe she’s not making enough milk,” Dr. Hovey explained.

“The Ground truth”

This project will also provide data to support research into piglet selection and teat fidelity.

Sows and piglets display complex nursing and suckling behaviors that significantly impact piglet health. Piglets typically select one teat and remain loyal to it throughout nursing, a behavior known as teat fidelity. The team aims to develop an AI-based method to automatically track piglets' nursing patterns and teat preferences, as well as monitor sow behavior.

“The camera is going to be trained on certain piglets which will allow us to identify and assess teat fidelity,” Dr. Hovey said. “And it will show how each piglet grew during the weaning process to provide, as my colleague calls it, “the ground truth.”

Equipped for success: A toolkit for caretakers

The goal of this work is to provide a set of tools that can help train farmers, animal caretakers, and students in identifying piglets at risk of pre-weaning mortality or poor growth.

“The emotional well-being of the caretaker will be addressed in this study as well,” Dr. Hovey said.

He went on to explain that the experience of trying to track which piglets get sick and possibly even die before weaning can have a negative emotional impact on caretakers.

“There is a high turnover rate amongst these caretakers, and they can experience a high rate of burnout,” Dr. Hovey explained. “The products from this study will provide a blueprint for these folks to know when there is an issue right away, enabling them to address it.”

He went on to add, “We will have real time results, so by the end of this project we will be able to provide a training program for employees and staff,” Dr. Hovey said.

Holiday research

The grant is being led from Michigan State under the leadership of Dr. Madonna Benjamin, a swine veterinarian.

Dr. Hovey is excited to get started on the project and will be traveling to East Lansing, Michigan over the holiday break. “All our international collaborators will be on speed dial over Christmas and New Years,” Hovey said. “Everyone is equally excited about starting our first litters on this project.”

And Dr. Hovey and the team have every reason to be enthusiastic, as they hold high hopes for the potential trickle-down effects of their research, particularly in terms of overall production efficiency.

“If we can solve this problem of piglet mortality, it could translate to less feed and resources being used, which is more cost effective for producers,” Dr. Hovey said. “And in turn, that would benefit consumers.”

 

Tags

Subscribe to the CLEAR Center Newsletter

* indicates required