Insights into thermal stress effects on performance and behavior of grazing cattle via multimodal sensor monitoring

Cattle have been observed to change their behavior and location in response to thermal stress. This study employs a multimodal sensor-based approach to assess if the behavior of grazing cattle changed in response to thermal conditions that occurred during two trials conducted in Queensland, Australia, over late spring and early summer. Each trial involved sixty cattle (Brahman and Droughtmaster) fitted with eGrazor collars containing triaxial accelerometer and GNSS sensors. Cattle were genotyped and weighed weekly, and relevant meteorological data was collected. Accelerometer data was used to classify cattle behavior at five-second intervals into six distinct categories: grazing, walking, ruminating, resting, drinking, and other. GNSS data and satellite imagery were utilized to estimate time spent in open areas, while the Comprehensive Climate Index (CCI) was calculated from meteorological data and used to identify the two warmest and coolest weeks of both trials. Correlation analysis revealed that, during days of higher CCI, cattle increased time in the shade (correlation coefficient [Formula: see text]), reduced daytime grazing ([Formula: see text]), shifted grazing to nighttime ([Formula: see text]), and prolonged daytime resting ([Formula: see text]). Weather variations had a subtle influence on weight gain, while cattle with increased Bos indicus genetic proportion were more active during periods of higher CCI. These findings emphasize the potential of sensor-based monitoring to quantify cattle behavioral responses to variable weather conditions in relevant production environments.