loading page

Using computer vision to understand the global biogeography of ant color
  • Jacob Idec,
  • Tom Bishop,
  • Brian Fisher
Jacob Idec
Hendrix College

Corresponding Author:[email protected]

Author Profile
Tom Bishop
University of Pretoria
Author Profile
Brian Fisher
California Academy of Sciences
Author Profile

Abstract

Organisms use color to serve a variety of biological functions, and these functions can be revealed by examining patterns of color variation across geographic and biological gradients. This approach, however, presents a data collection trade-off whereby researchers must either maximize intraspecific detail or taxonomic and geographic coverage. This limits our ability to fully understand color variation across entire taxonomic groups at global scales. We provide a solution by extracting color data from 47,000 individual specimens of ants, representing 10,000 species, using a computer vision algorithm. Our analyses on this dataset reveal that ants are dominated by variation in the dark-pale spectrum, that half of this variation is held within species, and that, overall, ant specimens tend to be darker in colder environments. Similar approaches may unlock a vast amount of data residing in museum and specimen databases and establish a digital platform for a data collection revolution in functional biogeography.