“We called this project the ‘virtual dairy farm brain’ because we’re trying to mimic the thinking of a very good dairy farm manager,” team leader, Victor Cabrera, a UW-Madison dairy science professor said.
UW’s multidisciplinary team includes dairy scientists, agricultural economists, and computer scientists who have started aggregating data from 4,000 dairy cows to their campus-based server.
“Dairy farms have embraced a lot of technologies that generate vast amounts of data,” Cabrera said.
“The problem is that farmers haven’t been able to integrate this information to improve whole-farm decision-making.”
AI predicts best management options
The main challenge will be filtering out useful data collected from daily dairy operations, according to Cabrera.
The type of data collected ranges from lbs of milk produced and lbs of feed consumed by dairy cows, how many steps a cow takes, genomic testing results, as well as general farm data such as weather patterns and the price of milk.
“We are collecting a lot of data, but a lot of it is repetitious or not relevant,” Cabrera said. “We need to be able to filter out the noise and attach identifiers to each type of data. To do this in real time is not a trivial thing.”
The UW team will use artificial intelligence to better predict the outcome of various management practices. Computer scientists from the university’s Center for High Throughput Computing are developing algorithms that analyze the dairy farms’ activity, which will be used to predict best management practices.
The final step will be to apply what was learned from the relevant data to create intuitive, cloud-based decision-support tools that allow farmers to use real-time data from their farms to make “smarter” management decisions.
“We think the methodology should apply to any farm. It could be adjusted to suit whatever data are available,” Cabrera said.
“The basic approach would be very similar on a 100-cow farm or an 8,000-cow operation.”
Cabrera added once the two-year project is completed, he hopes to begin a larger study involving 100 to 200 dairy farms representing a variety of sizes and management practices.