Pollination is critical to many ecosystem services, such as the maintenance of biodiversity and human nutrition. Addressing how plant-pollinator interactions change across environmental gradients requires quantifying pollinator visitation. However, we are limited by the available tools.
Ecologists typically observe pollinators in the field, record the species identity of the easily distinguished individuals, and collect with a net the remaining individuals so that they can be later identified to species in the lab. This is labor and time intensive, and thus prevents the massive data collection that is necessary to achieve a general, predictive understanding of how pollination responds to global change.
Therefore, we want to use machine learning methods and technology to automise ecological data collection on plant-pollinator interactions.
The first component of the project is about developing an automated camera system consisting of a Raspberry Pi micro-computer, tailored lenses and motion or beam sensors coupled with a deep learning approach for fast object detection like YOLO. The tool must be capable of detecting and capturing clear images or video recordings of visiting insects on flowers and uniquely trace and count each individual. The images will be validated and labeled by entomologists.
The second part of the project is about using the captured images and images from existing online databases for training state of the art Convolutional Neural Networks with the goal of insect identification down to the lowest possible taxonomic level (order > family > genus > species).
Finally, the developed AI models together with the automated camera system will be used for pollinator identification in field studies aimed at quantifying plant-pollinator networks.
How can you contribute?
If you have labeled images of pollinators and are willing to share them with us, feel free to contact Valentin Ștefan at firstname.lastname@example.org
Tiffany Knight - email@example.com
Valentin Ștefan - firstname.lastname@example.org