Floral Vision: Monitoring plant-pollinator networks by integrating citizen science, computer vision, and museum specimens

James Boyko, Nathan Fox, Yutong Wang, Yiluan Song, Yu Zhou (random order)
Code

Highlights

  • We validate and expand plant-pollinator interaction network with citizen science data (iNaturalist images).
  • We process images with interacting plant and pollinators with text-promptable image segmentation and identify species with computer vision models like Pl@ntNet.
  • We compare pheonlogy of interacting species inferred from museum specimen and identify pairs with high risks of phenological mismatch under climate change.

iNaturalist images with plants and pollinators


MY ALT TEXT

A plant-pollinator network generated based on a set of iNaturalist images with both species labeled using graphistry.

What's the insect on?

MY ALT TEXT
MY ALT TEXT

An iNaturalist image with bee and with bee removed using LangSAM, text-promptable image segmentation.


Phenology of interacting species

Home