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

Abstract

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 ( R 2 _RM) to capture the repeated nature of daily intakes compared with standard R 2 , RMSE and mean absolute error ( MAE ). REG, RF and SVR models predicted FWI with R 2 _RM = 0.1–0.36, RMSE = 1.51–2.96 kg and MAE = 1.19–2.49 kg, and DMI with R 2 _RM = 0.13–0.19, RMSE = 1.15–1.61 kg and MAE = 0.9–1.28 kg. The GRP models predicted FWI with R 2 _RM = 0.42–0.49, RMSE = 2.76–3.88 kg and MAE = 2.46–3.47 kg, and DMI with R 2 _RM = 0.32–0.44, RMSE = 0.32–0.44 kg, MAE = 1.55–2.22 kg. Whilst more simplistic GRP models showed higher R 2 _RM than regression and machine learning techniques, these models had larger errors, likely due to individual feeding patterns not b...

Feed Conversion Ratio (FCR) and Performance Group Estimation Based on Predicted Feed Intake for the Optimisation of Beef Production

“…Feed intake predictions in this paper are based on prior work [ 17 ]. Four models were generated on each of the MIXED and CONC diets to predict feed intake using feeding behaviours and animal metadata as input.…”

“…Individual daily fresh weight intakes (FWIs, kg/day) were calculated from the sum of individual visits to the trough and subsequently Dry Matter Intake (DMI) was calculated using the ratio measured from the most recent weekly diet sample. The Dry Matter Intake was used as the target of feed intake prediction models for each diet as previously detailed [ 17 ]. This provided three separate algorithm variants–proportion of feeding time relative to the group (GRP), Random Forest (RF) and Support Vector Regressor (SVR)—with each algorithm trained on the two diets.…”

“…As the performances of both SVR and RF models were broadly equivalent, the analysis undertaken here focuses only on the SVR model for simplicity. Details of the model implementation are reported in prior work [ 17 ]. Daily intake prediction errors in the case of the MIXED feed ration are shown below in Figure 2 .…”

“…The challenge however is that feed intake is highly specific to an individual animal. Davison et al [ 17 ] have shown that Machine Learning approaches, such as the use of Support Vector Regressors or Random Forest methods, can be highly effective at using feed time measures to estimate feed intake. The present paper reports on an extension to this analysis, to determine the validity of harnessing these measures to derive an estimate of the feed intake at an individual animal level.…”

“…The study detailed here builds on the previously reported research [ 8 , 17 ], which assessed the validity of using measurements of the time spent eating, in isolation and in tandem with other measurement data available in a production setting, to determine the precision of estimating feed intake. It aims to assess whether estimates of feed intake are sufficiently precise to be of value, in effect to ascertain if they can be used as a basis with which to generate an FCR [ 21 ] value with a level of inaccuracy required to segment the herd into tiers of growth performance.…”