Skip to main content
Fig. 2 | Animal Microbiome

Fig. 2

From: An artificial intelligence approach of feature engineering and ensemble methods depicts the rumen microbiome contribution to feed efficiency in dairy cows

Fig. 2

Machine learning prediction using feature selection and Ridge regression with 10-fold cross-validation on the residual feed intake (RFI) of lactating dairy cows. 2.A. Model used for the prediction of dry matter intake (DMI) containing the main energy sinks in a lactating dairy cow (NESec, MBW, and BEC), the effect of parity, the effect of previous treatment plus the effect of the rumen microbiome; 2.B. Prediction of DMI using only the rumen microbiome (pMicrobiome) to explore the overall contribution of the rumen microbes to feed intake; 2.C. Prediction of the residual DMI, also known as RFI, using only the rumen microbiome composition; and 2.D. Summary of RFI prediction with the rumen microbiome, from which confusion matrix was derived from comparing extracted observed vs. predicted residuals. The loss function for the AI model was the mean squared error (MSE) and the scoring metric was R2

Back to article page

Animal Microbiome

ISSN: 2524-4671