By Blake Jackson
Amelia Nelson, a PhD student in Cornell University's College of Veterinary Medicine, is developing a predictive model to help dairy farmers identify mastitis in cows earlier.
Working in Professor Renata Ivanek's lab and collaborating with the Cornell Agricultural Systems Testbed and Demonstration Site (CAST), Nelson aims to create a flexible technology that improves dairy herd health and farm productivity.
Mastitis, an inflammation of the cow's udder, is a widespread challenge in the dairy industry. It can result from infections caused by pathogens or physical injuries.
The condition affects animal welfare, reduces milk production, and creates significant financial costs for farmers.
According to Nelson, existing prediction methods often depend on herd-level statistics and milk electrical conductivity measurements.
However, maintaining reliable conductivity readings can be difficult. Somatic cell count testing, another method for detecting subclinical mastitis, can also be expensive.
To address these limitations, Nelson's model combines several sources of farm data. These include milk production and flow measurements, weather conditions, previous mastitis infections, diagnostic records, and geospatial information showing individual cows' locations inside the barn.
The research uses data collected at Cornell's Dairy Research and Education Center (CDREC) through CAST. Sources include Dairy Comp herd management software, the Cornell Animal Health Diagnostic Center, Delpro milking management systems, and electronic ear tags that track cow locations.
By analyzing these datasets, the model aims to identify patterns and risk factors associated with mastitis. For example, it could detect problems with milking equipment, such as liner slips, that may increase infection risks. It could also identify areas of a barn where water accumulation, poor bedding conditions, or harmful pathogens contribute to higher risks.
Nelson hopes to develop a customizable system that works with the data available on individual farms. The goal is to provide farmers with practical recommendations for improving equipment performance, managing barn conditions, and making targeted treatment decisions.
These improvements could help dairy producers increase milk production, reduce costs, improve profitability, and protect animal welfare.
Looking ahead, Nelson and her research team are preparing two scientific papers. One will examine mastitis prediction using milk parlor, weather, herd health, and diagnostic data, while the other will focus on predictions based on geospatial information.
Photo Credit: gettyimages-vwalakte
Categories: New York, Education, Livestock, Dairy Cattle