Dielectric relaxation parameters combing raw milk compositions to improve the prediction performance of milk somatic cell count.

Background: Milk somatic cell count (SCC) is an international standard for identifying mastitis in dairy cows and measuring raw milk quality. Milk SCC can be predicted based on dielectric relaxation parameters (DRPs). We noted a high correlation between DRPs and the milk composition content (MCC), and so we hypothesized that combining DRPs with MCC could improve the prediction accuracy of milk SCC. The present study aimed to analyze the relationship between milk SCC, DRPs and MCC, as well as to investigate the potential of combining DRPs with MCC to improve the prediction accuracy of milk SCC.

Results: The dielectric spectra (20-4500 MHz) of 276 milk samples were measured, and their DRPs (ε, ε, Δε, τ and σ) were solved by the modified Debye equation. The SCC prediction models were developed using dielectric full spectra, DRPs and DRPs combined with MCC. The results showed the correlations between DRPs (ε, ε, Δε and σ) and MCC (fat, protein, lactose and total solids) were high, and SCC exhibited a non-linear relationship with DRPs and MCC. The 5DRPs + MCC-generalized regression neural network model had the best prediction, with a standard error of prediction for prediction of 0.143 log SCC mL and residual of the prediction bias of 2.870, which was superior to the models based on full spectra, DRPs and near-infrared or visible/near-infrared.

Conclusion: The present study has improved the prediction accuracy of milk SCC based on the DRPs combing MCC and provides a new method for dairy farming and milk quality assessment. © 2024 Society of Chemical Industry.