Skip to main content

Table 6 Performance metrics of the best prediction models in external validation for each trait1

From: Predicting nitrogen use efficiency, nitrogen loss and dry matter intake of individual dairy cows in late lactation by including mid-infrared spectra of milk samples

Trait

Algorithm

Model

MIR

R2

SpearR

NUE

PLS

2

Original

0.63(0.02)

0.81(0.01)

RR

4

Original

0.58(0.01)

0.73(0.04)

SVM

3

Original

0.62(0.01)

0.80(0.02)

NL

PLS

3

Original

0.19(0.03)

0.37(0.05)

RR

6

No

0.35(0.01)

0.64(0.04)

SVM

3

Original

0.09(0.02)

0.24(0.02)

DMI_a

PLS

6

No

0.22(0.07)

0.56(0.13)

RR

6

No

0.47(0.02)

0.74(0.05)

SVM

3

Original

0.10(0.02)

0.34(0.04)

  1. 1NUE nitrogen use efficiency, NL nitrogen loss, DMI_a moving average of dry matter intake, PLS partial least squares, RR ridge regression, SVM support vector machine, MIR mid-infrared, Original MIR without pre-treatment, No MIR is not included in the model, R2 = coefficient of determination, SpearR Spearman correlation coefficient