393 The role of on-animal sensors in understanding feed intake, behavior, and performance of grazing livestock

Abstract Intake by grazing animals is difficult to reliably measure in the field, particularly in more diverse grazing systems where pastures vary greatly across time and space in resource availability, which in turn leads to greater variation in animal time budgets and intake patterns. Advances in remote livestock monitoring (e.g., on-animal sensors, walk -over-weighing), and advanced analytics such as machine learning algorithms can contribute to the development of robust, adaptable tools for better understanding of animal performance and behavior in grazing systems. Many existing tools for predicting livestock production require estimates of feed intake, and while estimates based on forage sward characteristics have been developed and used for temperate, relatively homogenous pastures, they are less well defined for more diverse rangelands. These diverse pastures are more difficult to characterize due to their greater variation in quantity and quality; consequently, animal selectivity is greater in more variable pastures. However, such feedback loops between pasture diversity and animal behavior may not yet be adequately represented in biophysical models. On-animal sensors such as accelerometers and GPS devices can be used to develop new ways of assessing relative intake by providing accurate estimates of animal location and behavior profiles, such as the use of machine learning algorithms to detect how much time is spent grazing, walking, ruminating, or resting. Measurements of animal behavior could then be combined with other animal-based methods such as walk-over-weighing and fecal NIR to improve estimates of intake and production for a wide range of extensive grazing environments. Sensor-derived measurements of animal movement could also be used to improve estimates of the energetic costs of grazing, thereby improving estimates of energy available for growth. As an example, data on recent activity and paddock use from on-animal sensors could be entered into a model to estimate current feeding requirements, then combined with weather and pasture quality forecasts. The ensuing baseline could then be used to explore the potential variability of these projections and generate a range for possible expected performance over the next month or season. This approach could be repeated over time, and animal performance and behavior measures used to update model estimates and improve forward projections. These methods could also be used in conjunction with estimates of animal energy requirements to provide real-time prediction of relative feed intake, which would provide a step-change in modelling livestock production in extensive grazing systems. For these approaches to be successful, additional calibration data are needed across a wide variety of environments and species, and the tools must be cost-effective to implement. In summary, on-animal measurements provide an adaptable, data-driven approach that could be integrated with existing tools to improve our understanding of feed intake, behavior, and performance of grazing animals.