Summary We present a new approach to developing predictive models of heat stress risk for grazing dairy herds. This proof-of-concept study demonstrates the potential of using a machine learning algorithm to predict heat stress events defined using rumen temperature. The approach has been enabled by animal sensors collecting large amounts of data on individual cows. The success of this approach is encouraging, as the scale and variable nature of farming outdoors in temperate climates has, to date, limited the development of our understanding and management of thermal stress among dairy cattle in these systems. To develop this approach further will require testing with independent datasets from a wider range of environments alongside model tuning.
Regular estimation of pasture availability is a time-consuming on-farm task, but one that is vital for good grazing management. The ability to automate this task is, therefore, highly valuable. Combining satellite sensing of pasture mass with global positioning for herd location provides raw data that can potentially be used to automatically estimate pasture mass, pasture growth and pasture grazing events across a farm. The feasibility of automatically obtaining and processing this information was demonstrated on a Waikato dairy farm from 22 October 2018 to 21 February 2019 (123 days), with 13 global positioning collars recording the location of grazing mobs 16 times per hour on average, in a dairy herd of initially 380 animals. Satellite sensing of pasture cover over the same period was only possible on 16 days during this period, with November being particularly cloudy, resulting in fewer pasture cover estimates. A non-linear regression model was constructed with parameters representing initial pasture cover, average pasture growth rate through time, pasture growth differences between paddocks, pasture disappearance rate relative to the density of cow GPS samples, and an ungrazeable residual. A Bayesian approach was used to infer the model parameters from the satellite-measured pasture cover data. This allowed interpolation of pasture mass through the whole period with an RMSE of 225 kgDM/ha, as well as identifying growth rate differences between paddocks, which may provide a useful basis for improved pasture management. Rough estimates of cow average daily pasture disappearance were also made, which peaked at 20 kgDM/d in November, falling to 5 kgDM/d by February. This pilot study demonstrated the feasibility of combining satellite pasture cover data with herd location data from a small number of GPS collars to infer pasture growth rates in individual paddocks through time.
Context: For dairy cows housed indoors, ambient temperature and relative humidity are key drivers of heat stress, whereas for cows kept outdoors, solar radiation and wind speed are also important. Solar radiation directly increases the heat load on cows, whereas wind speed affects their ability to dissipate heat through convection and evaporation. Aim: We aimed to determine whether climate-driven changes in these variables affect heat stress risk where cows are outdoors during summer and shoulder seasons, particularly in pasture-based farming systems such as in New Zealand. Understanding outdoor-specific factors is crucial for accurately assessing and mitigating heat stress in grazing dairy cattle, because their management needs differ substantially from those in housed systems. Methods: Using daily climate projection data from 2006 to 2098, peak daily values of the temperature–humidity index (THI) of Thom and the grazing heat-load index (GHLI) of Bryant were calculated and used to map predicted changes in both the annual (June–May) number of days with heat stress risk and also the annual accumulated heat stress exposure (the sum of effective degrees Celsius above the threshold) for dairy production regions of New Zealand. Key results: The results illustrated the limitations of using THI in the context of outdoor use, where solar radiation and wind speed are shown to be more important than relative humidity. The GHLI predicted that the risk of heat stress is already high in the Waikato (69 days), Bay of Plenty (69 days) and Canterbury (80 days) regions in the 2020s. Canterbury was also notable for having high heat stress exposure within day compared with other regions (i.e. heat stress days were particularly intense), attributable to the combined effect of high air temperatures, high solar radiation and low wind speeds. Conclusions: According to climate projections, regions already experiencing high numbers of heat stress risk days and heat stress exposure in the 2020s will experience the greatest increases in heat stress risk to the 2050s. However, dramatic increases in the number of heat stress days are not anticipated. Implications: This allows research and development to focus on mitigation practices in these regions where dairy farming systems must adapt to a changing climate. Mitigation strategies may include provision of shade, access to sprinklers, genetic selection for heat stress resilience, modifying feeding regimes to reduce heat load, or development of new solutions and technologies.
1 October 2020 in Stochastic Environmental Research and Risk Assessment