Implementation of disease detection and nutrient partitioning models will allow dairy producers to reduce the incidence of clinical disease and loss of nutrients into the environment, improving both farm profitability and the welfare of dairy animals.
Many precision technologies are becoming available to automatically and remotely collect information on dairy cattle physiology and behavior. These technologies will be of practical use for dairy farmers if they can improve cow health and performance.
The research team is using data collected from commercial farms and the Elora Dairy Research Centre on individual cow feed intake, body weight and fatness, chewing activity, standing and lying times, respiratory gas exchange, and health and productivity to develop advanced statistical and simulation models for forecasting individual cow health and performance, and to incorporate these models into decision-support software.
Strategies for early identification of disease, determining ideal breeding times for cows, and controlling feed delivery equipment by computer-assisted analysis of data gathered from remote sensors on farms will improve the health, welfare and productivity of dairy cows.
Key message for decision makers: Implementation of disease detection and nutrient partitioning models will allow dairy producers to reduce the incidence of clinical disease and loss of nutrients into the environment, improving both farm profitability and the welfare of dairy animals.
Partners: Ontario Ministry of Agriculture, Food and Rural Affairs (OMAFRA), University of Calgary, Dairy Farmers of Canada, Canwest DHI, Valacta.
Collaborators and students: Stephen Leblanc, Todd Duffield, Eduardo Ribeiro, Flavio Schenkel, Meagan King (PDF), Marc Champigny (PDF), Carolina Reyes (PhD student), Linaya Pot (MSc student), Hinayah Oliviera (MSc student), Patty Kedzierski (MSc student).
