Anomaly detection at the apiary: predicting state and swarming preparation activity of honey bee colonies using low-cost sensor technology

Abstract

Contemporary apiary practices rely on frequent manual inspections of the beehive to be able to notice undesired states of the bee colony early enough to react with an adequate measure. However, the inspections themselves may harm the bees and their success heavily depends on the beekeepers experience.We propose an approach for an automated prediction of anomalies in honey bee colonies that focuses on swarming events as well as the colony’s health state using a low budget DIY sensor setup, and compare methods from the domain of time series clustering.Our results show that our approach enables detecting signs of a swarming event 48-24 hours before it occurs with an accuracy that is helpful for beekeeper’s daily work. This facilitates the development towards an efficient, minimally invasive precision beekeeping practice.