Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms

• Published in: Animals (Basel) 2021-04, Vol.11 (5), p.1288
• Main Authors: Tedde, Anthony, Grelet, Clément, Ho, Phuong N, Pryce, Jennie E, Hailemariam, Dagnachew, Wang, Zhiquan, Plastow, Graham, Gengler, Nicolas, Brostaux, Yves, Froidmont, Eric, Dehareng, Frédéric, Bertozzi, Carlo, Crowe, Mark A, Dufrasne, Isabelle, Soyeurt, Hélène, GplusE Consortium Group
• Format: Article
• Language: English
• Subjects: Agricultural economics; Agriculture & agronomie; Agriculture & agronomy; Algorithms; Animal diseases; Animal husbandry; Animal Science and Zoology; Animal welfare; Automation; Body weight; dairy cow bodyweight; dairy cows; Dairy farming; Dairy farms; dairy herds; data collection; Datasets; dimensionality reduction; Disease detection; Feasibility; feature selection; General Veterinary; herd improvement; Holstein; Infrared spectra; Life sciences; machine learning; mid infrared spectra; Milk; milk yield; Model accuracy; Morphology; Organizations; Parity; partial least square; prediction; Prediction models; Reproduction; risk; Root-mean-square errors; Sciences du vivant; Variables; Veterinary (all)
• ISSN: 2076-2615; 2076-2615
• DOI: 10.3390/ani11051288

Knowing the body weight (BW) of a cow at a specific moment or measuring its changes through time is of interest for management purposes. The current work aimed to validate the feasibility of predicting BW using the day in milk, parity, milk yield, and milk mid-infrared (MIR) spectrum from a multiple-country dataset and reduce the number of predictors to limit the risk of over-fitting and potentially improve its accuracy. The BW modeling procedure involved feature selections and herd-independent validation in identifying the most interesting subsets of predictors and then external validation of the models. From 1849 records collected in 9 herds from 360 Holstein cows, the best performing models achieved a root mean square error (RMSE) for the herd-independent validation between 52 ± 2.34 kg to 56 ± 3.16 kg, including from 5 to 62 predictors. Among these models, three performed remarkably well in external validation using an independent dataset (N = 4067), resulting in RMSE ranging from 52 to 56 kg. The results suggest that multiple optimal BW predictive models coexist due to the high correlations between adjacent spectral points.