Automatic Recognition of BumblebEE species and Behaviour from their buzzes

Funded by Eva Crane Trust.

While the role of pollinators in the maintenance of wild, ornamental and crop plant communities is widely acknowledged, there is clear evidence of a global pollinator decline (Potts et al. 2010). However, the extent of the decline remains to assessed for many species. Traditional methods for monitoring bumblebees (e.g. visual counting, sweep netting) and associated ecosystem services such as pollination are laborious, thus hampering their monitoring in time and space. Thanks to recent technological and methodological advancements, the use of acoustic sensors offers good promise for bumblebee monitoring (van Klink et al. 2022). Indeed, the characteristics of buzzing sounds are very likely to be both species- and behaviour-specific (e.g. flying vs. pollinating) (Ribeiro et al. 2021). Nevertheless, buzzing sounds are highly complex and currently it is not possible to use existing acoustic classifiers for this purpose. Recent developments in artificial intelligence (e.g. supervised/unsupervised deep learning) hold significant promise for classifying bumblebee species and behaviour but have not been fully explored yet. Here, we propose a methodological project that could lead to great potential for new large-scale, cost-effective, and non-invasive bumblebee monitoring and associated ecosystem services assessment.

Total award value £22,751.75

People (1)


Dr Jeremy Froidevaux
Dr Jeremy Froidevaux

Post Doctoral Research Fellow, BES