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

Table 4 Performance metrics of the best prediction models in within-herd validation for each trait¹

Trait	Algorithm	Model	MIR	R²	SpearR
NUE	PLS	5	MSC	0.62(0.01)	0.80(0.01)
	RR	2	MSC	0.62(0.01)	0.80(0.03)
	SVM	5	SNV	0.66(0.01)	0.82(0.03)
NL	PLS	1	SNV	0.56(0.04)	0.79(0.01)
	RR	3	MSC	0.58(0.02)	0.79(0.05)
	SVM	2	MSC	0.53(0.004)	0.74(0.04)
DMI_a	PLS	3	MSC	0.63(0.02)	0.82(0.01)
	RR	2	MSC	0.63(0.02)	0.80(0.03)
	SVM	4	MSC	0.60(0.03)	0.78(0.04)

¹NUE nitrogen use efficiency, NL nitrogen loss, DMI_a 3-d moving average of dry matter intake, PLS partial least squares, RR ridge regression, SVM support vector machine, MIR mid-infrared, MSC multiplicative scatter correction, SNV standard normal variate, R² = coefficient of determination, SpearR Spearman correlation coefficient. Values between brackets indicate the standard deviation

ISSN: 2049-1891