Project title: Employing AI to identify the complex interactions of environmental stressors on pollinator health
PI: Geraldine Wright
There is a critical need to investigate how environmental change affects pollinator behaviour so that steps can be taken to mitigate economic and ecological risk. Sound is a typically overlooked component of behaviour despite most animals producing sounds, including insects during flight. The sound of mosquito flight has been shown to be an excellent marker for species identification, as demonstrated by the Oxford-led project, HumBug. However, this technology has not yet been implemented for the identification of other flying insects, including bees and honeybees, and it is not known whether sound alone can be used to classify behaviours. My project will result in a powerful tool for integrating computer vision and sound to automatically track the behaviour of insects. The technology will be innovative in the realm of insect behaviour, with application in the risk assessment of environmental stressors, including pesticides and the high temperatures associated with climate change. The resulting models will have impact for machine learning, as multimodal models combining imaging and non-imaging data are state-of-the-art. The models I develop may also serve in the field to record pollinators while foraging and serve as a basis for an insect identification tool, with far-reaching impact in ecology and agriculture.
