PSXIV-16 Evaluation of Water Intake Equations with an Emphasis on Physiological Status and Evaluation of Current Relevance Behind Environmental Parameters

Abstract

Abstract Water requirements for beef cattle are often computed according to body weight (BW) and environmental variables. Inherent variation in environmental conditions within geographical locations, in addition to a cascade of physiological changes triggered as consequence of such variability are somewhat fomented by multicollinearity amongst these variables. This conundrum generates instability of current predictive models in reaching optimization equilibrium inflating its overall predictability and robustness. The goals herein involved the identification of physiologically relevant parameters and the generation of robust, data-driven, individualistic models through high frequency data loggers. Further, we evaluate re-parametrized and current proposed equations (e.g.: Hicks et al., 1988 and Arias and Mader, 2011) for the prediction of water intake for beef cattle at different life stages and physiological conditions. The dataset utilized consisted of more than 30,000 observations, including longitudinal data on lactating animals (n = 23), grass finished steers (n = 12), grain finished steers (n = 21), and grain finished implanted steers (n = 9), steers backgrounded on a low (n = 20) or moderate (n = 20) plane of nutrition bulls under negative (n = 13), maintenance (n = 13) and positive energy balance (n = 13). Individual monitoring systems allowed for the daily collection of BW, water and feed intake, and ingestive behavior. Additionally, an on-site data-logging weather station (1-min intervals) collected relative humidity, temperature, wind speed, wind direction, solar radiation, and precipitation. All reported statistics were generated on out-of-bag randomly split portions of the dataset. For identification of relevant predictive parameters of water intake, several feature selection and penalization techniques were examined. When comparing our equations to current, the errors generated for water intake predictions using physiological classification and on-site environmental variables, explained 50% more of the variation in predicting water intake (r2 = 0.38 vs r2 = 0.22-0.27). When evaluating the errors of prediction (root mean squared error, RMSE and mean absolute error, MAE), significant decreases of up to three-fold were observed on the equations generated herein (RMSE = 9.05 vs 28.8 to 35.31, MAE = 7.04 vs 26.9 to 33.9). Accurate monitoring of individual parameters such as feed intake were better predictors of water intake than environmental parameters when evaluating re-parametrization of models. Further, inclusion of a physiological stage (categorical variable) was more significant than any of the other environmental predictors. Overall, the results discussed highlight the importance of appropriately accounting for the water requirements of beef cattle and how far-off current assumptions are. Further, it raises concern on current equations that use environmental monitoring equations and techniques that attempt to describe nutrient requirements of the animals, and potentially brings the approach to requirements rather than environment.