Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake

• Published in: Animals (Basel) Vol. 11; no. 5; p. 1316
• Main Authors: Tedde, Anthony, Grelet, Clément, Ho, Phuong, Pryce, Jennie, Hailemariam, Dagnachew, Wang, Zhiquan, Plastow, Graham, Gengler, Nicolas, Froidmont, Eric, Dehareng, Frédéric, Bertozzi, Carlo, Crowe, Mark, Soyeurt, Hélène
• Format: Journal Article Web Resource
• Language: English
• Published: Basel MDPI AG 04.05.2021; MDPI
• Subjects: Accuracy; Agriculture & agronomie; Agriculture & agronomy; Animal lactation; Animal Science and Zoology; artificial neural network; Australia; body weight; Canada; Councils; Dairy cattle; dairy cows; data collection; Datasets; Denmark; Diet; Dimensionality reduc-tion; dimensionality reduction; dry matter intake; equations; Farms; Fatty acids; feed efficiency; feed intake; Feeds; General Veterinary; Ireland; lactation; lactose; Life sciences; machine learning; mid infrared spectra; Milk; milk yield; neural networks; partial least square; prediction; Sciences du vivant; Variables; Veterinary (all); Ireland; Denmark; Canada; Australia
• ISSN: 2076-2615; 2076-2615
• DOI: 10.3390/ani11051316

We predicted dry matter intake of dairy cows using parity, week of lactation, milk yield, milk mid-infrared (MIR) spectrum, and MIR-based predictions of bodyweight, fat, protein, lactose, and fatty acids content in milk. The dataset comprised 10,711 samples of 534 dairy cows with a geographical diversity (Australia, Canada, Denmark, and Ireland). We set up partial least square (PLS) regressions with different constructs and a one-hidden-layer artificial neural network (ANN) using the highest contribution variables. In the ANN, we replaced the spectra with their projections to the 25 first PLS factors explaining 99% of the spectral variability to reduce the model complexity. Cow-independent 10 × 10-fold cross-validation (CV) achieved the best performance with root mean square errors (RMSECV) of 3.27 ± 0.08 kg for the PLS regression and 3.25 ± 0.13 kg for ANN. Although the available data were significantly different, we also performed a country-independent validation (CIV) to measure the models’ performance fairly. We found RMSECIV varying from 3.73 to 6.03 kg for PLS and 3.69 to 5.08 kg for ANN. Ultimately, based on the country-independent validation, we discussed the developed models’ performance with those achieved by the National Research Council’s equation.