Artificial intelligence has revealed that prehistoric footprints thought to have been made by a vicious dinosaur predator were actually from a shy plant-eater.
In an international collaboration, University of Queensland paleontologist Dr Anthony Romelio has used AI pattern recognition to re-analyze footprints from Dinosaur Stampede National Monument, southwest of Winton in central Queensland.
Large dinosaur footprints were first discovered in the 1970s at a trail site called Dinosaur Stampede National Monument, and for many years they were believed to have been left by a predatory dinosaur, such as Australovinatorabout two meters long,” said Dr. Romelio.
The mysterious tracks were thought to have been left during the middle Cretaceous period, about 93 million years ago.
But figuring out exactly what kinds of dinosaurs made footprints — especially tens of millions of years ago — can be very difficult and confusing work.
Especially since these large tracks are surrounded by thousands of small dinosaur footprints, leading many to believe that this predatory beast may have triggered a stampede of smaller dinosaurs.
“So, to solve the issue, we decided to use an artificial intelligence program called deep convolutional neural networks.”
He was trained on 1,500 dinosaur footprints, all of which were theropod or ornithopod in origin—the dinosaur collections related to the Dinosaur National Monument prints.
The results were clear: the tracks were drawn by a herbivorous ornithopod.
Computer assistance was vital, as the team was originally at a standstill, said Dr Jens Lalinsak, lead author from Liverpool John Moores University in the UK.
“We were very stuck, so thank God for modern technology,” said Dr. Lalinsak.
“In our research team of three, there was one person who was pro-carnivore, one person who was reluctant, and one who was pro-plant.
So – to really check out our science – we decided to go to five experts to demonstrate, as well as use artificial intelligence.
“AI was the clear winner, outperforming all the experts by a wide margin, with a margin of error of about 11 percent.
“When we used AI on large tracks from Dinosaur Stampede National Monument, all but one of these tracks were confidently classified as being left by an ornithopod dinosaur — a prehistoric ‘predator’.”
The team hopes to continue adding to the database of dinosaur fossil tracks and conducting further AI investigations.
Research published in Interface Journal of the Royal Society It includes collaborations between Australian, German and UK researchers.
A replica of the dinosaur track is on display at the Queensland Museum, Brisbane, and the track site can be visited near southwest Winton, Queensland.
Jens N. Lallensack et al, A machine learning approach to distinguish the tracks of theropod and ornithischian dinosaurs, Interface Journal of the Royal Society (2022). DOI: 10.1098/rsif.2022.0588
Provided by The University of Queensland
the quote: a prehistoric predator? Artificial Intelligence Says No (2022, November 15) Retrieved November 16, 2022 from https://phys.org/news/2022-11-prehistoric-predator-artustry-intelligence.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.
#Prehistoric #predator #Artificial #intelligence