Modelling Pig Rearing as Digital Shadow

Abstract

Pig rearing and animal welfare are increasingly in the interest of society. To enhance animal welfare using data-driven analyses, modeling the pig rearing process is essential to create corresponding data sets. Pig rearing is a complex process for increasing pigs’ weight (from approx. five to 25 kilograms) involving various actors (e. g. farmers, veterinarians) to provide goods (e.g., food, water) and services (e.g., medical care). Thereby, pigs live in pens equipped with condition-measuring sensors, like the pen's temperature or pigs' activity. Manual measurements (e.g., weights) are also conducted, resulting in various data sources. For analyzing these data, measured in different contexts, a digital shadow appears as an approach for modeling these data traces. Therefore, we report on a digital shadow for pig rearing, including the assets pen and pig, sensor sources, data traces (e.g., pens’ temperature), and the purpose of analyzing causes of necrosis (dead tissue) with association rules.