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.

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.

Conspecific and heterospecific plant densities at small-scale can drive plant-pollinator interactions.

Generalist pollinators are important in many habitats, but little research has been done on small-scale spatial variation in interactions between them and the plants that they visit. Here, using a spatially explicit approach, we examined whether multiple species of flowering plants occurring within a single meadow showed spatial structure in their generalist pollinator assemblages. We report the results for eight plant species for which at least 200 individual visits were recorded. We found that for all of these species, the proportions of their general pollinator assemblages accounted for by particular functional groups showed spatial heterogeneity at the scale of tens of metres. This heterogeneity was connected either with no or only subtle changes of vegetation and flowering species composition. In five of these species, differences in conspecific plant density influenced the pollinator communities (with greater dominance of main pollinators at low-conspecific plant densities). The density of heterospecific plant individuals influenced the pollinator spectrum in one case. Our results indicate that the picture of plant-pollinator interactions provided by averaging data within large plots may be misleading and that within-site spatial heterogeneity should be accounted for in terms of sampling effort allocation and analysis. Moreover, spatially structured plant-pollinator interactions may have important ecological and evolutionary consequences, especially for plant population biology.