Predicting methane emission in Canadian Holstein dairy cattle using milk mid-infrared reflectance spectroscopy and other commonly available predictors via artificial neural networks

Abstract

Interest in reducing eructed CH 4 is growing, but measuring CH 4 emissions is expensive and difficult in large populations. In this study, we investigated the effectiveness of milk mid-infrared spectroscopy (MIRS) data to predict CH 4 emission in lactating Canadian Holstein cows. A total of 181 weekly average CH 4 records from 158 Canadian cows and 217 records from 44 Danish cows were used. For each milk spectra record, the corresponding weekly average CH 4 emission (g/d), test-day milk yield (MY, kg/d), fat yield (FY, g/d), and protein yield (PY, g/d) were available. The weekly average CH 4 emission was predicted using various artificial neural networks (ANN), partial least squares regression, and different sets of predictors. The ANN architectures consisted of 3 training algorithms, 1 to 10 neurons with hyperbolic tangent activation function in the hidden layer, and 1 neuron with linear (purine) activation function in the hidden layer. Random cross-validation was used to compared the predictor sets: MY (set 1); FY (set 2); PY (set 3); MY and FY (set 4); MY and PY (set 5); MY, FY, and PY (set 6); MIRS (set 7); and MY, FY, PY, and MIRS (set 8). All predictor sets also included age at calving and days in milk, in addition to country, season of calving, and lactation number as categorical effects. Using only MY (set 1), the predictive accuracy (r) ranged from 0.245 to 0.457 and the root mean square error (RMSE) ranged from 87.28 to 99.39 across all prediction models and validation sets. Replacing MY with FY (set 2; r = 0.288-0.491; RMSE = 85.94-98.04) improved the predictive accuracy, but using PY (set 3; r = 0.260-0.468; RMSE = 86.95-98.47) did not. Adding FY to MY (set 4; r = 0.272-0.469; applying the calibrated models for large-scale prediction of CH 4 emissions.

The effects of breeding and selection on lactation in dairy cattle

“…The use of these tools in breeding programs will allow breeders to produce more milk and solids with a more desirable distribution of specific characteristics over time. Furthermore, it will allow production of milk that has more desirable properties for both manufacturers and consumers, making selection for peripherally associated traits like reduced methane emissions possible (e.g., Shadpour et al, 2022 ).…”

Possible Alternatives: Identifying and Quantifying Adulteration in Buffalo, Goat, and Camel Milk Using Mid-Infrared Spectroscopy Combined with Modern Statistical Machine Learning Methods

“…Partial least squares (PLS) is the preferred and most traditional way to correlate MIRS data with milk and animal traits because of its ability to consider covariate and high-dimensional datasets. However, for complex relationships between variables (e.g., nonlinearities and interactions), PLS may not be an ideal treatment [22]. Some MIRS studies on milk have demonstrated that other machine learning algorithms such as random forests (RF), decision trees, and neural networks (NN) are also able to effectively handle milk MIRS data [23].…”