A first approach to predict nitrogen efficiency of dairy cows through milk FT-MIR spectra


  • Grelet, C. , Froidmont, E. , Hostens, M. , Vanlierde, A. , Foldager, L. , Salavati, M. , Ingvartsen, K. , Sorensen, M. . , Crowe, M. , Ferris, C. , Marchitelli, C. , Becker, F. , Gpluse Consortium, & Dehareng, F. (2018). A first approach to predict nitrogen efficiency of dairy cows through milk FT-MIR spectra. Proceedings in: 69th Annual Meeting of the European Federation of Animal Science, Dubrovnik, Croatia, 26-31 August 2018,
Type Conference Proceedings
Year of conference 2018
Title A first approach to predict nitrogen efficiency of dairy cows through milk FT-MIR spectra
Conference name 69th Annual Meeting of the European Federation of Animal Science
Conference location Dubrovnik, Croatia
Volume Book of abstract
conference Date 26-31 August 2018
Abstract Protein efficiency has become a key factor in dairy production for both environmental and economic reasons. Cost effective and large-scale phenotyping methods are required to improve this trait through genetic selection or feeding and management of cows. The aim of this study is to evaluate the possibility of using MIR spectra of milk to predict protein efficiency of dairy cows. Data were collected from 133 cows, from calving until 50 days in milk, in 3 research herds distributed in Denmark, Ireland and UK. For two herds, diets were designed to challenge cows and induce production diseases. Amounts of protein ingested (kg/day) and fat and protein corrected milk (FPCM, in kg/day) were measured daily. Protein efficiency to produce milk was ’quantified’ by using the ratio “FPCM/protein ingested”. MIR milk spectra were recorded twice weekly and were standardized into a common format to avoid bias between apparatus or periods. Regression models between protein efficiency and MIR milk spectra have been developed on 1145 observations using PLS or SVM methods and a cross-validation was realized using 10 subsets. The model was better in terms of R² of cross-validation and error when using SVM method compared to PLS method. Inclusion of milk yield and lactation number as predictors, in combination with the spectra, also improved the calibration. The best model was obtained by using spectra, milk yield and lactation number as predictors, and SVM modeling with R²cv of 0.75. These preliminary results show that there is a possibility to have information on protein efficiency to produce milk through milk MIR spectra. This could allow large-scale predictions for both genetic studies and farm management.
Author address c.grelet@cra.wallonie.be
Fichier
Authors Grelet, C., Froidmont, E., Hostens, M., Vanlierde, A., Foldager, L., Salavati, M., Ingvartsen, K., Sorensen, M. ., Crowe, M., Ferris, C., Marchitelli, C., Becker, F., Gpluse Consortium, , Dehareng, F.