Scientists Asked A.I. To Analyze The Fossil Record
There have been a total of five extinction events in the earth’s history. The first, the Ordovician Silurian Extinction, occurred 440 million years ago and wiped out small marine organisms. A second, the Devonian Extinction, occurred 365 million years ago and killed a number of tropical marine species. Then, 250 million years ago, was the Permian Triassic extinction, followed by the Triassic Jurassic extinction 210 million years ago, and the Cretaceous and Tertiary extinctions 65 million years ago. In the years since then everything has been fine – even if 2020 did its best to make us feel different.
Scientists have long believed that mass extinction leads to productive evolutionary periods, a process sometimes referred to as creative destruction or “radiation”. The idea is that these periods of large numbers of species disappearing are correlated with the arrival of new species.
To find out how well the data supported these theories, an international group of researchers applied machine learning technology to the immense fossil record of life’s history and visualized their structure using an algorithm that embed 171,231 species in a multidimensional virtual space. The results helped the researchers to find out whether certain species coexisted or never coexisted.
The machine learning algorithm was developed by Nicholas Guttenberg of GoodAI and Cross Labs / Cross Compass in collaboration with the Tokyo Institute of Technology.
“Five exceptionally dire extinctions were known to have occurred in the last eon of life and we are believed to have entered another,” said Jennifer Hoyal Cuthill, evolutionary biologist at the Institute of Analytics and Data Science and the School of Life Sciences in The University of Essex in the UK, which is affiliated with the Earth-Life Science Institute (ELSI) of the Tokyo Institute of Technology, told Digital Trends. “Our machine learning method … picks up on these ‘big five’ mass extinctions and enables us to visualize their significant effects. Our study also puts the five major mass extinctions in the context of all detectable disturbances in the fossil record. This shows the range of evolutionary events that have influenced life history. “
Hoyal Cuthill said the work has opened up some exciting areas of potential research. In particular, it has helped counter some of the popular wisdoms about mass extinction and mass radiation, showing that the emergence of large numbers of species and the extinction of other species often occur at different times.
“Our new methods have potential applications for a wide variety of data, and we have more projects planned,” she said. “Overall, there are so many areas of human knowledge that machine learning has not yet been applied to and so there may be a lot of great insights waiting to be discovered now. I think this is a very exciting time. “
An article describing the work was recently published in the journal Nature.