Global environmental challenges require comprehensive data to monitor and manage biodiversity. We have developed a portable, modular, and low-power device with embedded vision for ecosystem monitoring. The work, led by Kevin during his postdoc in our lab is now available as a preprint at BioRxiv
In six case studies we show, for instance how bats pollinate durian tree flowers and feed on rice pests at night, how bees pollinate rapeseed crop flowers, and real-time alerts for waterbird detection. We measured classification accuracies between 55% and 96% in our field surveys and used them to standardize observations over highly-resolved time scales.
Our cameras can be used anywhere where automated vision-based monitoring is required off the grid, in natural and agricultural ecosystems, and in particular for quantifying ecosystem services based on species interactions such as pollination and biological pest control. If you are interested to use our cameras in your research, please take a look at our lab spinoff company ecoNect and feel free to get in touch
