Acoustic sensor determination of repeatable cow urinations traits in winter and spring

• Published in: Computers and electronics in agriculture 2022-05, Vol.196, p.106846, Article 106846
• Main Authors: Shorten, P.R., Welten, B.G.
• Format: Article
• Language: English
• Subjects: Acoustic; Acoustics; Albumins; Blood; Calibration; Cattle; Classifiers; Coefficient of variation; Cow; Datasets; Flow velocity; Grazing; Metabolites; Nitrogen; Repeatable; Reproducibility; Urination; Urology
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2022.106846

•Acoustic sensors were attached to 140 cows to detect urination in winter and spring.•The acoustic urination classifier had an F1 statistic of 0.89–0.96 between trials.•The acoustic duration of urination model had good performance with an R2 = 0.90.•There was between-cow variation in the urination traits of 10–15%.•Blood potassium and beta-hydroxybutyrate had the largest influence on urine N load. Urinary nitrogen (N) excreted by grazing ruminants is the predominant source of N loss from pasture-grazed agricultural systems. The aim of this study was to use cow-attached acoustic sensors to measure the between-cow repeatability in the frequency, flow rate, duration, volume and N load of urination events from 140 grazing cattle in winter and spring. The urination event classifier had an F1 statistic of 0.946 based on 6122 urination events from 215 cows in the calibration dataset. The performance statistics for the validation of the urination event classifier were F1 = 0.91 (range 0.89–0.96 between trials), precision = 0.98 (range 0.93–0.99 between trials) and sensitivity = 0.85 (range 0.81–0.92 between trials). Urination event duration had a model validation R2 = 0.90 and RMSE of 2.0 s (with a range 1.8–2.2 s between trials), which compares with 1.70 s for the calibration dataset. Acoustic sensor determination of urination flow rate had an estimated error of 0.028 L s−1, and the average cow urination flow rate was 0.26 L s−1. The between-cow variation in urination traits had a coefficient of variation of 10–15% and the urination traits were repeatable between winter and spring trials. We also found that potassium and beta-hydroxybutyrate were the blood metabolites with the largest influence on N load per event and that total protein and albumin were the two blood metabolites that were the best predictors of total daily nitrogen (TDN) output. This study demonstrates the performance of a novel acoustic technology that has been tested on 355 cows and has the potential to inform strategies to reduce environmental N losses from grazed pastoral systems.