Over the last 20 yr, global positioning system (GPS) collars have greatly enhanced livestock grazing behavior research. Practices designed to improve livestock grazing distribution can now be accurately and cost effectively monitored with GPS tracking. For example, cattle use of feed supplement placed in areas far from water and on steep slopes can be measured with GPS tracking and corresponding impacts on distribution patterns estimated. Ongoing research has identified genetic markers that are associated with cattle spatial movement patterns. If the results can be validated, genetic selection for grazing distribution may become feasible. Tracking collars have become easier to develop and construct, making them significantly less expensive, which will likely increase their use in livestock grazing management research. Some research questions can be designed so that dependent variables are measured by spatial movements of livestock, and in such cases, GPS tracking is a practical tool for conducting studies on extensive and rugged rangeland pastures. Similarly, accelerometers are changing our ability to monitor livestock behavior. Today, accelerometers are sensitive and can record movements at fine temporal scales for periods of weeks to months. The combination of GPS tracking and accelerometers appears to be useful tools for identifying changes in livestock behavior that are associated with livestock diseases and other welfare concerns. Recent technological advancements may make real-time or near real-time tracking on rangelands feasible and cost-effective. This would allow development of applications that could remotely monitor livestock well-being on extensive rangeland and notify ranchers when animals require treatment or other management.

Four trials were conducted to explore possible advantages of weaning beef calves in two stages compared with the traditional method of weaning by abrupt separation. In the two-stage treatment, calves were prevented from nursing their dam for a period (Stage 1) before their separation (Stage 2). Control calves nursed from their dams until they were separated. Calf weights and behavior were recorded before and after the separation of cows and calves. Following separation, calves weaned in two stages vocalized 96.6% less (P = 0.001) and spent 78.9% less time walking (P = 0.001), 23.0% more time eating (P = 0.001), and 24.1% more time resting (P = 0.001) than control calves. Compared with controls, two-stage calves had lower (P < 0.001) ADG when nursing was deprived (Stage 1), but greater (P < 0.001) ADG during the 7 d following separation. In Trial 3, calves weaned by the two-stage method had greater (P = 0.05) growth rates than control calves for 7 wk after separation, but no treatment effects on ADG were detected (P > 0.38) in Trials 1 and 2. Over the entire study period (before and after separation), ADG did not differ (P > 0.10) for both treatments. In Trial 4, calves weaned in two stages walked 1.3 km/d more (P < 0.05) during the 4-d period when nursing was prevented (Stage 1) and 5.8 km/d less (P < 0.05) during the 4-d period after separation than controls. Differences between treatments were the greatest in the 2 d after separation. On the first day after separation, two-stage calves walked 5.2 ± 0.5 km/ d, whereas control calves walked 16.7 ± 3.1 km/d. Calves weaned in two stages were less distressed than calves weaned by the traditional method of abrupt separation based on behavioral data, but overall calf ADG did not differ for either method in this study. Nutritional management of two-stage weaned calves during the nursing-deprived period should be evaluated in future research because poor pasture conditions may have decreased gains by calves weaned by the two-stage method in this study.

Precision livestock management has become a new field of study as the result of recent advancements in real-time global positioning system (GPS) tracking, accelerometer and other sensor technologies. Real-time tracking and accelerometer monitoring has the potential to remotely detect livestock disease, animal well-being and grazing distribution issues and notify ranchers and graziers so that they can respond as soon as possible. On-going research has shown that accelerometers can remotely monitor livestock behavior and detect activity changes that are associated with disease and parturition. GPS tracking can also detect parturition by monitoring the distance between a ewe and the remainder of the flock. Tracking also has the potential to detect water system failures. Combinations of GPS tracking and accelerometer monitoring may be more accurate than either device used by itself. Real-time GPS tracking can identify when livestock congregate in environmental sensitive areas which may allow managers the chance to respond before resource degradation occurs. Identification of genetic markers associated with terrain use, decreased cost of GPS tracking and novel tracking data processing should facilitate development of tools needed for genetic selection for cattle grazing distribution. Precision livestock management has potential to improve welfare of livestock grazing rangelands and forested lands, reduce labor costs and improve ranch profitability and improve the condition and sustainability of riparian areas and other environmental sensitive areas on grazing lands around the world.

In the current study, a simulated online parturition detection model is developed and reported. Using a machine learning (ML)-based approach, the model incorporates data from Global Navigation Satellite System (GNSS) tracking collars, accelerometer ear tags and local weather data, with the aim of detecting parturition events in pasture-based sheep. The specific objectives were two-fold: (i) determine which sensor systems and features provide the most useful information for lambing detection; (ii) evaluate how these data might be integrated using ML classification to alert to a parturition event as it occurs. Two independent field trials were conducted during the 2017 and 2018 lambing seasons in New Zealand, with the data from each used for ML training and independent validation, respectively. Based on objective (i), four features were identified as exerting the greatest importance for lambing detection: mean distance to peers (MDP), MDP compared to the flock mean (MDP.Mean), closest peer (CP) and posture change (PC). Using these four features, the final ML was able to detect 27% and 55% of lambing events within ±3 h of birth with no prior false positives. If the model sensitivity was manipulated such that earlier false positives were permissible, this detection increased to 91% and 82% depending on the requirement for a single alert, or two consecutive alerts occurring. To identify the potential causes of model failure, the data of three animals were investigated further. Lambing detection appeared to rely on increased social isolation behaviour in addition to increased PC behaviour. The results of the study support the use of integrated sensor data for ML-based detection of parturition events in grazing sheep. This is the first known application of ML classification for the detection of lambing in pasture-based sheep. Application of this knowledge could have significant impacts on the ability to remotely monitor animals in commercial situations, with a logical extension of the information for remote monitoring of animal welfare.

Feeding site selection is a critical part of livestock foraging that can constrain and/or increase the choices available during diet selection. When livestock choose new feeding sites, vegetation and nutrient profiles can differ from other areas, especially in heterogeneous environments with rugged terrain. Correspondingly, livestock should remain longer in feeding sites in rugged heterogeneous pastures than in homogeneous pastures where animals may alternate among feeding sites to facilitate diet mixing and to prevent satiation. The objective of this study was evaluate how terrain and corresponding heterogeneity may affect the sequence and pattern of feeding site selection of free-roaming livestock. Grazing patterns of mature cows were evaluated on six ranches located in Arizona, Montana and New Mexico. In total, 11–19 cows were tracked for 1–3-month periods at each ranch by using global positioning system (GPS) collars. Positions were recorded at 10- or 15-min intervals and used to identify where cows grazed during the early morning (0500 hours to 1000 hours). Pastures (336–9740 ha) at each ranch were divided into seven to nine sections (48–1082 ha) as an indicator of feeding sites. Classification was based on cattle density and topographical and vegetation types. Sequences of daily section selection were evaluated using transition matrixes. For all ranches, the sequence of section selection differed from what would be expected by chance, indicating that the section selected on the following day depended on the section selected on the previous day. For ranches with relatively gentle terrain, cattle selected different feeding sites ~70% of the tracking period. In contrast, cows at the ranch with the largest pasture and enclosing both mountainous and gentle terrain stayed in the same feeding site for over 10 successive days for 42% of the tracking period. Smaller pastures with only mountainous terrain were intermediate. Cows grazing gentle topography and relatively homogeneous vegetation alternated among feeding sites (sections in the present study) more frequently than cows grazing pastures with more rugged topography and more heterogeneous vegetation. This pattern could help livestock mix forages and select a more diverse diet.