Use of sensor-determined behaviours to develop algorithms for pasture intake by individual grazing cattle

Abstract

Practical and reliable measurement of pasture intake by individual animals will enable improved precision in livestock and pasture management, provide input data for prediction and simulation models, and allow animals to be ranked on grazing efficiency for genetic improvement. In this study, we assessed whether pasture intake of individual grazing cattle could be estimated from time spent exhibiting behaviours as determined from data generated by on-animal sensor devices. Variation in pasture intake was created by providing Angus steers (n = 10, mean ± s.d. liveweight 650 ± 77 kg) with differing amounts of concentrate supplementation during grazing within individual ryegrass plots (≤0.22 ha). Pasture dry matter intake (DMI) for the steers was estimated from the slope (kg DM day–1) of the regression of total pasture DM per plot on intake over an 11-day period. Pasture DM in each plot, commencing with ≤2 t DM ha–1, was determined by using repeatedly calibrated pasture height and electronic rising plate meters. The amounts of time spent grazing, ruminating, walking and resting were determined for the 10 steers by using data from collar-mounted, inertial measurement units and a previously developed, highly accurate, behaviour classification model. An initial pasture intake algorithm was established for time spent grazing: pasture DMI (kg day–1) = –4.13 + 2.325 × hours spent grazing (P = 0.010, r2 = 0.53, RSD = 1.65 kg DM day–1). Intake algorithms require further development, validation and refinement under varying pasture conditions by using sensor devices to determine specific pasture intake behaviours coupled with established methods for measuring pasture characteristics and grazing intake and selectivity.

Classification of ingestive-related cow behaviours using RumiWatch halter and neck-mounted accelerometers

“…The proposed algorithms did not consider ruminating behaviour and they also required a high sampling rate (50 Hz). Other studies (Greenwood et al, 2017;Kasfi et al, 2016;Martiskainen et al, 2009b;Smith et al, 2016) used algorithms with high computational load (e.g., multi-class binary classification, random forest, SVM, and neural networks), which could not be implemented on the on-cow nodes.…”

Challenges of feeding dairy cows in Australia and New Zealand

“…Real-time estimation of pasture intake by individual cows in a herd is also now possible with sensor and wireless-sensor networks that relate specific behaviour to intake of pasture. For example, Greenwood et al (2017) developed reliable algorithms that predict intake of pasture when forage is not limiting, but concluded that further refinement of the algorithms is needed to account for variation within and among pastures and use of different sensor types that enable more specific classification of ingestive behaviours such as bite size, eating time, number of chews and eating rate. With real-time information on nutrient intake, mechanistic nutrition models may provide a supplementary-feed solution allowing optimal milk production that has a reduced impact on the environment.…”

Internet of Things for evaluating foraging and feeding behavior of cattle on grassland-based farming systems: concepts and review of sensor technologies

“…Other authors have assessed rumination and activity patterns by using accelerometers. For example, rumination, feeding, activity, and animal temperature [54], feeding, ruminating, active, and resting [55], rumination time, chewing cycles, and rumination bouts [53], lying time, neck activity, reticulorumen temperature, and rumination time [58], grazing, searching, ruminating, resting, and scratching [56], level of activity and rumination [60], grazing, ruminating, walking, resting behaviors to develop algorithms for pasture intake by individual grazing cattle [61], rumination and its relationship to feeding and lying behavior in Holstein dairy cows] [62]. In [63], GPS locations were recorded to calculate mean slope, elevation, distance from water, distance traveled per day, and elevation for each cow.…”