A-Aieee: Scottish scientists help create dinosaur footprint app

Taking a step back in time just got easier, according to the experts behind a new specialist app.

The system aims to take the pain out of paleontology, making it easier to identify footprints left behind by long-extinct species.

Fossilised prints are an important indicator of pre-historic life, but research has shown they are difficult to interpret.

Edinburgh University claims the new DinoTracker app will make the process easier for scientists and the public alike.

Its team worked with the Helmholtz-Zentrum research centre in Berlin, using advanced algorithms to enable computers to train themselves to recognise variations in the shape of dinosaur footprints.

Almost 2,000 fossil specimens and millions of additional variations mimicking “realistic” shifts in factors like compression and edge displacement were used.

Eight key features were identified, including heel position, the size of the contact area, toe spread and distribution of weight on different parts of the foot.

When matching a print to a species, the algorithm was in line with classifications by human experts around 90 per cent of the time, even for more hard-to-judge dinosaurs.

The system also indicated that prints found in Skye around 170 million years ago may have been left by some of the world’s earliest relatives of duck-billed dinos.

And it suggests that birds may have developed tens of millions of years earlier than was previously thought.

Funded by the innovations pool of the BMBF-Project: Data-X, the Helmholtz project ROCK-IT, the Helmholtz-AI project NorMImag the National Geographic Society and the Leverhulme Trust, the findings are detailed in a study published in PNAS.

Professor Steve Brusatte, of Edinburgh University’s School of GeoSciences, said: “This study is an exciting contribution for paleontology and an objective, data-driven way to classify dinosaur footprints – something that has stumped experts for over a century.

“It opens up exciting new possibilities for understanding how these incredible animals lived and moved, and when major groups like birds first evolved. This computer network might have identified the world’s oldest birds, which I think is a fantastic and fruitful use for AI.”