Development of a digital twin for pig growth and behaviour

Increasing productivity has been the main focus of the pig farming sector, however often at the cost of pig welfare. Recent technological developments allowed for the rise of a range of precision livestock farming (PLF) technologies that can automatically monitor the pigs and assist the farmer. By combining state-of-the-art PLF technologies, data about both production (i.e. pig growth) and welfare (i.e. various pig behaviours) will be collected into an extensive dataset. Using mechanistic modelling techniques, a reference growth curve for each individual pig will be estimated, which allows to predict the weight at time of slaughter. Additionally, databased dynamic modelling will be applied to create a time series model for the individual weight of each pig based on real-time data during the growing phase. By comparing the dynamic short-term weight prediction with the reference growth curve an early warning system for growth deviations will be developed. Based on the combined models, a monitoring and predictive digital twin (DT) of the individual pig will be created. To gain insight into the further development of a prescriptive DT for the pig sector, the application potential will be explored by consultation of pig farmers and veterinarians. Finally, a user interface is created to allow easy interaction between the pig farmer and the DT for pig growth and behaviour.