Artificial Intelligence

AI App Identifies Dinosaurs From Footprint Photos

Does AI footprint analysis revolutionize dinosaur evolution or simply validate existing expert classifications?

Published JAN 28

AI App Identifies Dinosaurs From Footprint Photos

Story

Image credit: Unsplash

The Facts

Researchers from the Helmholtz-Zentrum research center in Berlin have launched a new artificial intelligence app called DinoTracker that allows users to upload photos of dinosaur footprints from mobile devices and receive instant analysis identifying which type of dinosaur may have left the track.
CNET
SciTech Daily
The Telegraph
The AI system was trained using nearly 2,000 real fossil footprints along with millions of simulated variations to recreate natural distortions such as compression and edge displacement. The algorithm achieved around 90% agreement with human expert classifications, even for contentious species.
Discover Magazine
PHYS
The neural network identified eight key features of footprint variation, including the spread of the toes, the position of the heel, the size of the contact area the foot made while striking the ground and the amount of weight placed on different parts of the foot.
PNAS
The University of Edinburgh
Eurasia Review
The AI detected strong similarities between some dinosaur tracks, dating back more than 200 million years, and the foot structures of both extinct and modern birds. This suggests that birds could have originated tens of millions of years earlier than previously believed.
Daily Mail
SciTech Daily
The system indicated that mysterious footprints from the Isle of Skye in Scotland, impressed on the muddy shore of a lagoon around 170 million years ago, might have been made by some of the oldest relatives of duck-billed dinosaurs known from anywhere in the world.
Discover Magazine
PHYS
The Telegraph
Traditional methods required researchers to manually compile computer datasets in which specific tracks were assigned to specific dinosaurs, potentially introducing bias. The new unsupervised approach provides an unbiased way to recognize variation in footprints and test hypotheses about their makers.
EurekAlert!
The University of Edinburgh

Sources Split

LEFT

CENTER

RIGHT

ESTAB
CRIT

CENTER

PRO
ESTAB

The Spin

Narrative A

The new AI footprint system reveals serious flaws in existing dinosaur classifications, with many expert labels likely wrong since no one ever finds the actual dinosaur next to its tracks. The technology supports revolutionary findings about birdlike tracks dating back 60 million years before the earliest known bird fossils, potentially rewriting evolutionary timelines.

guardian

Narrative B

AI footprint analysis matches human expert classifications 80-93% of the time, validating decades of paleontological work rather than overturning it. The technology serves as a useful research tool and educational resource, making expert knowledge accessible to curious explorers rather than replacing scientific judgment on complex evolutionary questions.

Spiros Margaris on X

The Conversation

Narrative C

Although touted as groundbreaking, the DinoTracker AI has limitations: it focuses on footprint shape rather than actual foot anatomy, meaning its classifications — and suggestions about bird origins — may be misleading without expert verification. The app's output could reinforce misinterpretations and overstate evolutionary conclusions, underscoring the continued need for cautious scientific analysis.