Prehistoric predator?  Artificial intelligence says no

Prehistoric predator? Artificial intelligence says no

An artistic digital rendition of the recently identified dinosaur. Photo credit: Dr. Anthony Romilio

Artificial intelligence has shown that prehistoric footprints thought to be from a vicious dinosaur predator are actually from a shy herbivore.

In an international collaboration, paleontologist Dr. Anthony Romilio from the University of Queensland used AI pattern recognition to reanalyze the footprints of Dinosaur Stampede National Monument, southwest of Winton in central Queensland.

“Large dinosaur footprints were first discovered in the 1970s at a trail called Dinosaur Stampede National Monument, and for many years were thought to have been left by a predatory dinosaur australovatorwith legs almost six feet long,” said Dr. Romilio.

“The mysterious tracks were believed to have been left in the middle Cretaceous period, around 93 million years ago.

“But figuring out exactly which dino species made the footprints — especially tens of millions of years ago — can be quite a difficult and confusing matter.

“Especially since these large footprints are surrounded by thousands of tiny dinosaur footprints, leading many to believe this predator may have prompted an onslaught of smaller dinosaurs.”

“To crack the case, we decided to use an AI program called Deep Convolutional Neural Networks.”

It was trained using 1,500 dinosaur footprints, all of which were originally theropods or ornithopods — the groups of dinosaurs relevant to the Dinosaur Stampede National Monument footprints.

The result was clear: the tracks came from a herbivorous ornithopod dinosaur.

dr Jens Lallensack, lead author from Liverpool John Moores University in the UK, said the computer support was crucial as the team was initially stuck in an impasse.

“We were pretty stuck, so thank God for the modern technology,” said Dr. sack.

“In our three-person research team, one person was for carnivores, one person was undecided, and one person was for herbivores.

“So – to really check our science – we decided to turn to five experts for clarification and use AI.

“The AI ​​was the clear winner and, with an error rate of around 11 percent, surpassed all experts by a wide margin.

“When we used AI on the large footprints at Dinosaur Stampede National Monument, all but one of these footprints were reliably classified as being left by an ornithopod dinosaur – our prehistoric ‘predator’.”

The team hopes to continue to add to the database of fossil dinosaur tracks and conduct further AI investigations.

The research is published in the Journal of The Royal Society Interface and includes collaborations between Australian, German and British researchers.

A replica of the dinosaur track is on display at the Queensland Museum in Brisbane and the track can be viewed near south-west of Winton, Queensland.

More information:
Jens N. Lallensack et al, A Machine Learning Approach to Distinguishing Theropod and Ornithischian Dinosaur Tracks, Journal of The Royal Society Interface (2022). DOI: 10.1098/rsif.2022.0588

Provided by the University of Queensland

Quote: Prehistoric Predator? Artificial Intelligence Says No (2022, November 15), retrieved November 15, 2022 from https://phys.org/news/2022-11-prehistoric-predator-artificial-intelligence.html

This document is protected by copyright. Except for fair trade for the purpose of private study or research, no part may be reproduced without written permission. The content is for informational purposes only.


#Prehistoric #predator #Artificial #intelligence

Leave a Comment

Your email address will not be published. Required fields are marked *