Bridging the Gap between Field Experiments and Machine Learning: The EC H2020 B-GOOD Project as a Case Study towards Automated Predictive Health Monitoring of Honey Bee Colonies
Loading...
insects-15-00076.pdf (3.15 MB)
Date
2024-01-22
Journal Title
Journal ISSN
Volume Title
Publisher
MDPI
Abstract
Honey bee colonies have great societal and economic importance. The main challenge that beekeepers face is keeping bee colonies healthy under ever-changing environmental conditions. In the past two decades, beekeepers that manage colonies of Western honey bees (Apis mellifera) have become increasingly concerned by the presence of parasites and pathogens affecting the bees, the reduction in pollen and nectar availability, and the colonies’ exposure to pesticides, among others. Hence, beekeepers need to know the health condition of their colonies and how to keep them alive and thriving, which creates a need for a new holistic data collection method to harmonize the flow of information from various sources that can be linked at the colony level for different health determinants, such as bee colony, environmental, socioeconomic, and genetic statuses. For this purpose, we have developed and implemented the B-GOOD (Giving Beekeeping Guidance by computational-assisted Decision Making) project as a case study to categorize the colony’s health condition and find a Health Status Index (HSI). Using a 3-tier setup guided by work plans and standardized protocols, we have collected data from inside the colonies (amount of brood, disease load, honey harvest, etc.) and from their environment (floral resource availability). Most of the project’s data was automatically collected by the BEEP Base Sensor System. This continuous stream of data served as the basis to determine and validate an algorithm to calculate the HSI using machine learning. In this article, we share our insights on this holistic methodology and also highlight the importance of using a standardized data language to increase the compatibility between different current and future studies. We argue that the combined management of big data will be an essential building block in the development of targeted guidance for beekeepers and for the future of sustainable beekeeping.
Description
Honey bees are very important for nature and food production. However, beekeepers’ work is continuously challenged by pests, pathogens, pesticides, and other impacts of the environment on their honey bee colonies, and, therefore, they would greatly benefit from up-to-date insights on the health condition of their bees. To disturb those bee colonies as little as possible, it is preferable that this information be collected in an automated way. In this article, we present the B-GOOD project as a case study to monitor the health of honey bee colonies in an automated, standardized way. The use of a similar approach by researchers in their future studies would allow the combination of different datasets on bee health. More data combinations would facilitate the use of machine learning to better and more accurately determine the thresholds for beekeeper interventions, the underlying mechanisms of honey bee colony health, and the prediction of health and colony losses, among other indicators.
Keywords
Citation
van Dooremalen, C.; Ulgezen, Z.N.; Dall’Olio, R.; Godeau, U.; Duan, X.; Sousa, J.P.; Schäfer, M.O.; Beaurepaire, A.; van Gennip, P.; Schoonman, M.; et al. Bridging the Gap between Field Experiments and Machine Learning: The EC H2020 B-GOOD Project as a Case Study towards Automated Predictive Health Monitoring of Honey Bee Colonies. Insects 2024, 15, 76. https://doi.org/10.3390/insects15010076