Predicting feed intake using modelling based on feeding behaviour in finishing beef steers

• Main Authors: C. Davison, J.M. Bowen, C. Michie, J.A. Rooke, N. Jonsson, I. Andonovic, C. Tachtatzis, M. Gilroy, C-A. Duthie
• Format: Article
• Language: English
• Published: Elsevier 2021-07-01
• Series: Animal
• Subjects: Beef cattle; DM intake; Feed efficiency; Finishing steers; Machine learning
• Online Access: http://www.sciencedirect.com/science/article/pii/S1751731121000732

Current techniques for measuring feed intake in housed cattle are both expensive and time-consuming making them unsuitable for use on commercial farms. Estimates of individual animal intake are required for assessing production efficiency. The aim of this study was to predict individual animal intake using parameters that can be easily obtained on commercial farms including feeding behaviour, liveweight and age. In total, 80 steers were used, and each steer was allocated to one of two diets (40 per diet) which consisted of (g/kg; DM) forage to concentrate ratios of either 494:506 (MIXED) or 80:920 (CONC). Individual daily fresh weight intakes (FWI; kg/day) were recorded for each animal using 32 electronic feeders over a 56-day period, and individual DM intakes (DMI; kg/day) subsequently calculated. Individual feeding behaviour variables were calculated for each day of the measurement period from the electronic feeders and included: total number of visits to the feeder, total time spent at the feeder (TOTFEEDTIME), total time where feed was consumed (TIMEWITHFEED) and average length of time during each visit to the feeder. These feeding behaviour variables were chosen due to ease of obtaining from accelerometers. Four modelling techniques to predict individual animal intake were examined, based on (i) individual animal TOTFEEDTIME relative expressed as a proportion of the dietary group (GRP) and total GRP intake, (ii) multiple linear regression (REG) (iii) random forests (RF) and (iv) support vector regressor (SVR). Each model was used to predict CONC and MIXED diets separately, giving eight prediction models, (i) GRP_CONC, (ii) GRP_MIXED, (iii) REG_CONC, (iv) REG_MIXED, (v) RF_CONC, (vi) RF_MIXED, (vii) SVR_CONC and (viii) SVR_MIXED. Each model was tested on FWI and DMI. Model performance was assessed using repeated measures correlations (R2_RM) to capture the repeated nature of daily intakes compared with standard R2, RMSE and mean absolute error (MAE). REG, RF and SVR models predicted FWI with R2_RM = 0.1–0.36, RMSE = 1.51–2.96 kg and MAE = 1.19–2.49 kg, and DMI with R2_RM = 0.13–0.19, RMSE = 1.15–1.61 kg and MAE = 0.9–1.28 kg. The GRP models predicted FWI with R2_RM = 0.42–0.49, RMSE = 2.76–3.88 kg and MAE = 2.46–3.47 kg, and DMI with R2_RM = 0.32–0.44, RMSE = 0.32–0.44 kg, MAE = 1.55–2.22 kg. Whilst more simplistic GRP models showed higher R2_RM than regression and machine learning techniques, these models had larger errors, likely due to individual feeding patterns not being captured. Although regression and machine learning techniques produced lower errors associated with individual intakes, overall precision of prediction was too low for practical use.