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.

Technology that facilitates estimations of individual animal dry matter intake rates in group-housed settings will improve production and management efficiencies. Estimating dry matter intake in pasture settings or facilities where feed intake cannot be monitored may benefit from predictive algorithms that use other variables as proxies. This study examined the relationships between dry matter intake (DMI), animal performance, and environmental variables. Here we determined whether a machine learning approach can predict DMI from measured water intake variables, age, sex, full body weight, and average daily gain (ADG). Two hundred and five animals were studied in a drylot setting (152 bulls for 88 days and 53 steers for 50 days). Collected data included daily DMI, water intake, daily predicted full body weights, and average daily gain using In-Pen-Weighing Positions and Feed Intake Nodes. After exclusion of 26 bulls of low-frequency breeds and one severe (greater than 3 standard deviations) outlier, the final number of animals used for modeling were 178 (125 bulls, 53 steers). Climate data were recorded at 30-minute intervals throughout the study period. Random Forest Regression (RFR) and Repeated Measures Random Forest (RMRF) were used as a machine learning approaches to develop a predictive algorithm. Repeated Measures ANOVA (RMANOVA)was used as the traditional approach. Using the RMRF method, an algorithm was constructed that predicts an animal’s DMI within 0.75 kg. Evaluation and refining of algorithms used to predict DMI in drylot by adding more representative data will allow for future extrapolation to controlled small plot grazing and, ultimately, more extensive group field settings.