Abstract
Technology that facilitates estimation of individual animal intake rates in group-housed settings will result in improvements in animal production and management efficiency. Estimating intake in pasture settings may benefit from models that use other variables as proxies. Relationships among dry matter intake (DMI), animal performance variables, and environmental variables to model DMI were investigated. 202 animals were studied in a drylot setting (153 bulls for 85 days and 55 steers for 55 days) using VYTELLE SENSETM In-Pen-Weighing and Feed-Intake nodes. A machine learning model was calibrated using: DMI, sex, age, full body weight, ADG, water intake, water visit frequency and duration. DMI was positively related to full body weight (r = 0.39, P < 0.001), water intake (r=0.23, P < 0.001), and ADG (r=0.18, P < 0.001). In addition, DMI had significant but weak correlations with water visit frequency (r=0.031, P < 0.001). DMI exhibited weak negative relationships with maximum air temperature (r=-0.094, P < 0.001) maximum relative humidity (r=-0.056, P < 0.001), net radiation (r=-0.040, P < 0.001), and precipitation (r=-0.022, P < 0.001). Weak positive relationships were observed between DMI and maximum wind speed (r=0.031, P < 0.001) and direction (r=-0.022, P < 0.001). The model was validated with resultant average RMSE of 1.06 kg for daily predicted DMI compared to measured daily DMI. In addition, when daily predicted DMI was averaged for each animal, the accuracy of model results improved with RMSE of 0.11 kg. Study results demonstrate that inclusion of water intake and animal performance variables improves predictive accuracy of DMI. Validating and refining the model used to predict DMI in drylots will facilitate future extrapolation to larger group field settings. Vytelle and its logo are trademarks of Vytelle, LLC.