Table 9 Predictive performance of the ANN models for prediction of manure N output using the whole dataset.

From: Can machine learning algorithms perform better than multiple linear regression in predicting nitrogen excretion from lactating dairy cows

Primary predictors

Features1

R2

RMSE2

RRMSE3

CCC4

NI

NI + LW + MY

 + FP + DNC + DMEC

0.83

32.1 ± 1.68

10.9 ± 0.44

0.76 ± 0.025

LW and MY

LW + MY + DNC + CDMI + DMEC

0.79

35.2 ± 1.08

12.1 ± 0.47

0.70 ± 0.021

  1. 1NI N intake; DNC diet N concentration; MY milk yield; FP forage proportion; LW live weight; DMEC diet metabolizable energy concentration; CDMI concentrate dry matter intake.
  2. 2RMSE root mean square error (obtained by tenfold cross validation), mean ± standard deviation.
  3. 3RRMSE relative root mean square error (obtained by tenfold cross validation), mean ± standard deviation.
  4. 4CCC concordance correlation coefficients (obtained by tenfold cross validation), mean ± standard deviation.
Back to article page