AI tool reveals climate shifts may have fueled bursts of bird evolution Sadie Harley Scientific Editor Andrew Zinin Chief Editor University of Michigan researchers have used an AI tool to demonstrate that birds in the group Passeriformes evolved in rapid evolutionary bursts and that these bursts frequently coincided with climate shifts throughout Earth's history. Evolutionary theory predicts that the evolution of organisms occurs in pulsed bursts followed by slowdowns—something researchers have seen hints of in the fossil record. Now, looking at passerines, University of Michigan researchers have identified these evolutionary bursts by examining data gleaned from skeletal measurements of contemporary bird specimens.

The researchers also observed that these bursts coincided with historical climate change. "This is really important for evolutionary theory because there's a long history, going back 100 years, that predicts the emergence of new groups, called evolutionary radiations, is often associated with an explosive burst of diversification. Evolutionary theory predicts that adaptive radiations may account for a large portion of the diversity of life on Earth," said Jake Berv, lead author of the study and postdoctoral fellow in the U-M School for Environment and Sustainability.

"This could be because of a new ecological opportunity, or it could be because a group dispersed to a new continent, resulting in dramatic accelerations in their rate of evolution. The idea is that, over time, there's less opportunity as evolution proceeds, and so it slows down, and that this occurs in pulses across time. That's what theory predicts, and that seems to be what we see in the data as well." The findings, deduced using artificial intelligence and a large-scale statistical model, are published in Nature Ecology & Evolution.

Seeing with Skelevision To trace how this group of birds evolved, the U-M scientists, including senior author Brian Weeks, examined more than 2,000 species and collected more than 170,000 individual skeletal measurements. To create such a large dataset, the team used an AI tool called Skelevision, which Weeks' lab developed with David Fouhey's lab at New York University. Skelevision uses a camera to photograph specimens—for this study, bird skeletons—against a background grid that provides a common scale.

Over a seven-year collaboration, Weeks and Fouhey developed an AI model that can precisely measure a dozen bones across the avian skeleton. The researchers used Skelevision to scan and measure more than 15,000 individual museum specimens, most of which came from the U-M Museum of Zoology collections. Scanning each specimen takes only about 45 seconds, which makes it possible to digitize entire collections.

A method to the madness Berv then developed a new statistical method called bifrost that enabled researchers to examine a species' entire skeleton at once. This allowed the researchers to estimate the evolution of body shape over the approximately 45-million-year history of Passeriformes. "The whole organism is an integrated, complex morphology, and each of the individual pieces is interrelated to every other part in the body," Berv said.