AI Traces How Fish Schooling Evolved Across 2,839 Species
Curaçao – Researchers used artificial intelligence to trace how fish schooling evolved across 2,839 species, and released video of a school of bigeye scad off the coast of Curaçao.
Video released with the research, credited to Ella G. Henry, shows a dense school of bigeye scad, Selar crumenophthalmus, swimming as a single unit in open water.
A Cornell University team led by Andrew Hein and Jay Love reported in the Proceedings of the National Academy of Sciences that fish have independently gained the ability to move together as a group some 60 times, and lost it some 320 times, over the last 350 million years. Using machine learning on written descriptions and citizen-science images, they quantified schooling in 2,839 species.
The study found species lower in the food chain were more likely to school, that group-hunting predators almost all eat prey that also move in groups, and that lineages in which every species schools have produced more species than those that do not. The findings were published on November 6 and released to the press in early November.
Clean HD download
Register a media account or sign in to buy & download this story
Sign in to download Apply for media access