20 New Insights on Data Integration and Artificial Intelligence to Predict Primiparous Lactation Curves Capturing Genotype-by-Environment Interactions. (21st September 2022)

• Record Type: Journal Article
• Authors: Zhang, Fan; Weigel, Kent; Cabrera, Victor E
• Is Part Of: Journal of animal science. Volume 100(2022)Supplement 3
• Page Start: 12
• Page End: 12
• Publication Date: 2022-09-21
• Subjects: machine learning -- prediction models -- lactation curves; Livestock -- Periodicals; Livestock; Electronic journals; Periodicals; 636.005
• DOI: 10.1093/jas/skac247.021
• Languages: English
• ISSNs: 0021-8812

Abstract

Abstract: We are developing a Dairy Brain by applying precision dairy farming, big data analytics, artificial intelligence, and the internet of things with the aim to accomplish a near real-time, data-integrated, data-driven, continuous decision-making engine through which management decisions can be better informed by integrated data streams to improve the economics of the farm and to positively benefit the individual animal and the overall farm through descriptive, predictive, and prescriptive analytics. Within this general concept, we have developed a machine learning hybrid K-medoids, random forest and support vector regression (K-R-S) approach for predicting the lactation curves of individual primiparous cows within a targeted environment using monthly milk production data from their dams and paternal siblings for 6, 400 calves born in Wisconsin farms in year 2016. Our K-R-S hybrid approach outperformed the mean of paternal siblings in predicting first lactation test-day milk yield of primiparous cows 74.2% of the predictions. The algorithm has the ability to predict all data points required to construct primiparous cows' full lactation curves even before they have started their productive life. Our approach allows the genotype-by-environment interactions to be portrayed in the prediction algorithm. Our current model uses only test-day (monthly) production data, but the artificial intelligence architecture is prepared to accommodate more frequent farm records (e.g., daily milk records from milking parlor) or other phenotype measures such as reproductive or health parameters for better characterization of the animals and their production environment towards improved prediction accuracy. We envision the prediction architecture will serve as an engine of farm-specific continuous prediction relaying on a constant flux of integrated data from different farm data sources following the Dairy Brain notion of data integration, analytics, and decision making.