Swansea University study used AI to uncover the effect of prehistoric asteroid on sharks and rays

Could AI be used for further research about humans?


A new Swansea University study has used advanced artificial intelligence to discover the asteroid strike that wiped out the dinosaurs 66 million years ago has had a minimal decline in species of sharks and rays.

The research, carried out by Swansea University, traced the diversity of shark and ray species over 145 million years, creating the most detailed long-term picture of their evolutionary history to date.

Lead author, Dr Catalina Pimiento, said: “Today’s sharks and rays are the survivors of a long history of change, including extinction events that have only become visible in the fossil record.

The study revealed that “for the past 40 to 50 million years, their diversity has been trending downwards.”

Dr Pimiento, of Swansea University’s Department of Biosciences and the University of Zurich’s Department of Palaeontology, explained that the long-term decline of sharks and rays matters today as it suggests that they are starting from a reduced baseline.

“They’re not just facing human pressures such as overfishing and climate change as a healthy, thriving group – they have already lost a lot of evolutionary potential over tens and millions of years”, he said.

Via Unsplash

Key findings of the research:

  •  The number of species of shark and ray’s that are comparable to modern levels was reached over 100 million years ago during the Cretaceous period.
  • There was only a 10 per cent decline in shark and ray species from the asteroid impact, which is a staggering contrast when compared to the mass extinction of non-avian dinosaurs and marine predators.
  • Since their peak, 50 million years ago in the mid-Eocene period, sharks and rays have lost over 40 per cent of their species.

These findings and patterns were only clearly discovered with the use of advanced AI methods, and was able to explicitly account for spatial and temporal biases found in the fossil record.

“We built a new, carefully curated dataset of fossil shark and ray occurrences”, Dr Catalina Pimiento said.

Catalina explained that their research “involved reviewing hundreds of studies, extracting data, checking it and resolving inconsistencies, resulting in a global synthesis of fossil occurrences spanning the past 145 million years.”

Dr Daniele Silvestro, study co-led author of ETH Zurich, said: “We then applied a new AI method that is far better at recognising and correcting the uneven and incomplete nature of the fossil record.

“Previous approaches could account for general differences in sampling, but not for the fact that fossils are unevenly collected across geographic regions or species.

“Our model can learn these patterns – for example, recognising when fewer fossils in a particular region can reflect limited sampling rather than real biological decline”

So, are we witnessing the positive progression of AI in research? And what could this mean for the future of research in academic contexts?

The full study can be found here.

For more of the latest news, guides, gossip and memes, follow The Cardiff Tab on InstagramTikTok, and Facebook

Featured image Swansea University via YouTube and Unsplash.