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

Abstract

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.

Correlations of feed intake predicted with milk infrared spectra and breeding values in the Dutch Holstein population

“…This shows that indeed these predictions are possible to some extent, but also that ignoring systematic effects of, for example, MY and BW did not reduce the accuracy of the predictions of DMI. Brand et al (2021) achieved better predictions of pregnancy status from milk IR spectra with a machine learning approach than with PLS, but Tedde et al (2021) found very similar DMI prediction accuracies using either PLS regression or machine learning. This suggests that improvement of predictions using milk IR spectra using machine learning compared with PLS regression is trait dependent.…”

The Impact on Cow Performance and Feed Efficiency When Individual Cow Milk Composition and Energy Intake Are Accounted for When Allocating Concentrates

“…While individual cow 'walk-over' weighing systems already exist and are in place on some commercial farms, their adoption within the UK is very limited, and this situation looks unlikely to change for the foreseeable future. Nevertheless, research has attempted to predict individual cow BW on the basis of days-in-milk, milk yield, parity and milk mid-infrared spectrum [27]. If this approach is successful then individual cow BW values could be predicted with sufficient accuracy to improve precision within individual cow feeding systems.…”

Fourier transform mid-infrared milk screening to improve milk production and processing

“…Moreover, whereas milk is an important source of nutritive elements for humans, its fine composition—or, more specifically, composition changes—is important to know, as it mirrors the metabolic and health status of the animal. This explains why some indicators related to metabolism and animal health, such as energy balance or intake ( Ho et al, 2020 ), BW ( Tedde et al, 2021a ), DMI ( Tedde et al, 2021b ), acetonemia ( Grelet et al, 2016 ), pregnancy status ( Delhez et al, 2020 ), SARA ( Mensching et al, 2021 ), fertility ( Ho et al, 2019 ), lameness ( Bonfatti et al, 2020 ), and so on, can be derived from the milk FT-MIR spectrum. Another important topic is the environmental footprint of milk production.…”