Researchers to Explore Effect of Big Data on Dairy Farms

When farmers adopt new digital technologies, it affects far more than just their bottom lines: It can impact a web of relationships -- including between farmers and workers, banks, insurance companies, veterinarians, nutritionists, and cheese and yogurt companies.

All of this raises questions about who owns the data, who has access to it, and how it can be used, for good or ill.

A new project, "Big Data on the Dairy Farm: Relational Transformations Across Agricultural Occupations and Organizations With the Rise of Digital Technologies," has been awarded $1.2 million by the National Science Foundation's Human-Centered Computing program.

The three-year project is led by Diane Bailey, the Geri Gay Professor of Communication in the College of Agriculture and Life Sciences (CALS) and director of the Cornell University Institute for Digital Agriculture; Julio Giordano, associate professor of animal science (CALS); and colleagues at Stanford University and the University of California, Santa Barbara.

"Big data transformed many industries in the 1990s and 2000s to streamline internal business processes and optimize supply chains," Bailey said, "but that type of transformation is just beginning to occur in many areas of farming, prompted by the generation and collection of huge amounts of new data about crops, livestock, soil and other farm entities. We want to understand how the digital technologies that collect, share, analyze and display these data are transforming not just farmers' work and identity and knowledge, but also the entire organizational ecosystem around farming."

Digital agriculture involves the integration of physical technologies, such as robots, drones and sensors, as well as advanced modeling of biology, systems engineering and economics in agriculture. It is a growing industry, expected to be worth $12.9 billion by 2027; new research has found that 87% of agricultural executives report using artificial intelligence technologies.

These kinds of technologies in farming can bestow benefits, such as higher milk production and better crop yields, but they also have the potential to negatively impact relationships in unexpected ways, Bailey said. For example, because data systems can make a farm's data transparent to many entities, an insurance company might deny a farmer's claim if the farmer ignored what the data models recommended and instead followed their own judgment, Bailey said.

"It's like the wild west of data out there: Everyone's trying to make a name for themselves and find a spot in this burgeoning industry," Bailey said. "Suddenly we have this whole data ecosystem of farmers, cows, barns, milking parlors, third-party vendors and so on. Each wants to use this data to optimize their own operations. How do all of these technological innovations affect the relationships between these people and organizations, and ultimately, how do they impact the farmer and the cows?"

To examine how these relationships affect cows and farmers, this project will leverage Giordano's research in predictive modeling of cow health, reproduction and economics with data from digital tools. Giordano collects data from wearable and non-wearable sensors that monitor every aspect of animal behavior, physiology and performance, then creates models using that aggregated data -- as well as analytics techniques, such as machine learning -- to automate animal management tasks and decision-making.

"Technologies for monitoring and managing cows for improved health, reproduction, well-being and performance are transforming dairy production," Giordano said. "In this project, we will explore how the web of relationships that governs availability of data for modeling affects the performance of predictive models under real-world conditions."

In the first year of the study, researchers will conduct fieldwork at 10 farms in New York and California, observing how work is done and conducting interviews with farm owners and employees. The study will expand to 20 farms in the second year and will include visits and interviews with third-party vendors, data aggregators, veterinarians, nutritionists, bankers, cheese and yogurt companies and others.

In the third year, the data will be analyzed and models built and tested to explain how the use of digital technologies is transforming dairy farming and, in turn, how dairy farming practices shape data models and modeling.

"While our primary goal is to inform the dairy industry," Bailey said, "we hope that our work will contribute to understanding the larger picture of how digitization and digital transformation are impacting the changing nature of work and management more generally."