Scientists have launched an AI app that identifies dinosaurs from fossilised footprints with about 90% accuracy.
Researchers developed DinoTracker using unlabelled footprint silhouettes instead of expert-assigned classifications.
The system compares footprint shapes using eight key features, including toe spread and heel position.
Steve Brusatte from University of Edinburgh co-authored the study.
The research appeared in Proceedings of the National Academy of Sciences.
Gregor Hartmann said mislabelled footprints can mislead AI systems.
The app lets users upload footprints and explore similar tracks interactively.
The AI supports earlier findings of birdlike dinosaur tracks predating known bird fossils.
Brusatte said the tracks likely came from birdlike meat-eating dinosaurs, not true birds.
Andrew Rogers
Andrew Rogers is a freelance journalist based in the USA, with over 10 years of experience covering Politics, World Affairs, Business, Health, Technology, Finance, Lifestyle, and Culture. He earned his degree in Journalism from the University of Florida. Throughout his career, he has contributed to outlets such as The New York Times, CNN, and Reuters. Known for his clear reporting and in-depth analysis, Andrew delivers accurate and timely news that keeps readers informed on both national and international developments.
Keep Reading
Add A Comment
