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

Abstract Background Nitrate leaching to groundwater and surface water and ammonia volatilization from dairy farms have negative impacts on the environment. Meanwhile, the increasing demand for dairy products will result in more pollution if N losses are not controlled. Therefore, a more efficient, and environmentally friendly production system is needed, in which nitrogen use efficiency (NUE) of dairy cows plays a key role. To genetically improve NUE, extensively recorded and cost-effective proxies are essential, which can be obtained by including mid-infrared (MIR) spectra of milk in prediction models for NUE. This study aimed to develop and validate the best prediction model of NUE, nitrogen loss (NL) and dry matter intake (DMI) for individual dairy cows in China. Results A total of 86 lactating Chinese Holstein cows were used in this study. After data editing, 704 records were obtained for calibration and validation. Six prediction models with three different machine learning algorithms and three kinds of pre-processed MIR spectra were developed for each trait. Results showed that the coefficient of determination (R2) of the best model in within-herd validation was 0.66 for NUE, 0.58 for NL and 0.63 for DMI. For external validation, reasonable prediction results were only observed for NUE, with R2 ranging from 0.58 to 0.63, while the R2 of the other two traits was below 0.50. The infrared waves from 973.54 to 988.46 cm− 1 and daily milk yield were the most important variables for prediction. Conclusion This study developed reasonable prediction models for N related traits of Chinese Holstein cows. Models with MIR spectra outperformed the other models indicating that MIR spectra have additional value for predicting these target traits. Pre-processing MIR spectra by mathematical algorithms may fail to improve prediction accuracies. The most important wave ranges of MIR (973.54 to 988.46 cm− 1) for prediction are associated with particular chemical compounds, which can be useful to unravel the biological mechanisms of nitrogen utilization in dairy cows. These models will be applied to large-scale data to further investigate the genetic architecture of nitrogen efficiency and further reduce the adverse impacts on the environment after more data is collected.