Animal biometric assessment using non-invasive computer vision and machine learning are good predictors of dairy cows' age and welfare: The future of automated veterinary support systems.

Fuentes, S., Gonzalez Viejo, C., Tongson, E., et al. (2022). Animal biometric assessment using non-invasive computer vision and machine learning are good predictors of dairy cows' age and welfare: The future of automated veterinary support systems. Journal of Agriculture and Food Research, 10, 100388. ISSN 2666-1543.

This study explores the use of non-invasive video-based biometric analysis to assess dairy cow welfare on a robotic dairy farm in Australia. Two machine learning models were developed: Model 1, a regression model predicting somatic cell count, weight, rumination, and feed intake, and Model 2, a classification model using facial features to predict cow age. Model 1 demonstrated high correlation (R = 0.96) and performance, while Model 2 achieved 98% accuracy with low error. These models can support automated veterinary systems, enhancing milk productivity and welfare assessment in dairy farms.