Scientists Are Using AI to Help Identify Dinosaur Footprints

An international team of researchers has designed a futuristic tool to examine the footprints left by dinosaurs in our ancient past. The AI-powered app, Dinotracker, can identify dinosaur footprints in moments.

The research comes from a joint project of the Helmholtz-Zentrum research center in Berlin and the University of Edinburgh in Scotland. The Proceedings of the National Academy of Sciences published the paper Monday.

Don’t miss any of our unbiased technical content and lab reviews. Add CNET as your preferred Google source.

Identifying a dinosaur species from a footprint is not always easy. The footprint is hundreds of millions of years old, often preserved in layers of rock that have changed over the eons since the track was laid.

Plus, we still have a lot to learn about dinosaurs, and it’s not always clear which species left a footprint. Subjectivity or bias may come into play when identifying them, and scientists do not always agree with the results.

Gregor Hartmann of the Helmholtz-Zentrum, who led the project, told CNET that the research team sought to remove this propensity from the identification process by developing an algorithm that could be neutral.

“We bring a mathematical, unbiased point of view to help human experts interpret the data,” Hartmann said.

The researchers trained the algorithm on thousands of real fossil footprints, as well as millions of simulated versions that could recreate “natural distortions such as compression and edge displacement.”

How AI is used on dinosaur tracks

The system was trained to focus on eight major characteristics of dinosaur footprints, including toe width, heel position, area of ​​the foot in contact with the ground, and weight distribution on the foot.

The AI ​​tool uses these features to compare the new footprints to existing fossils, then determines which dinosaur is most likely responsible for the footprint.

The team tested it against human expert classifications and found that the AI ​​agreed with these classifications 90% of the time.

Hartmann made it clear that the AI ​​system is “unsupervised.”

“We don’t use any labels (like bird, theropod, ornithopod) during training. The network has no idea,” Hartmann said. “Only after training, we compare how the network encodes the silhouettes and compare that with human labels.”

Hartmann said the hope is that Dinotracker will be used by paleontologists and that the AI ​​tool’s data pool will grow as it is used by more experts.

Bird versus dinosaur

Thanks to Dinotracker, researchers have already discovered intriguing possibilities about bird evolution. By analyzing footprints more than 200 million years old, the AI ​​discovered strong similarities with the leg structures of extinct and modern birds.

The team believes that one possibility is that birds appeared tens of millions of years earlier than previously thought. But it’s also possible that dinosaurs’ first feet looked remarkably like those of birds.

This evidence, Hartmann notes, is not enough to rethink bird evolution, since a skeleton is the “real proof” of birds’ prior existence.

“It’s essential to keep in mind that over these millions of years, many different things can happen to these traces, from the moisture level of the mud where they were created, to the substrate on which they were created, to subsequent erosion,” he said. “All of this can significantly change the shape of the fossilized trace we find, and ultimately makes it too difficult to interpret the prints, which is what motivated our study.”

Dinotracker is available for free on GitHub. It’s not available in a download-and-use format, so you’ll need to know a little about software to make it work.