There have been a total of five extinction events in Earth’s history. The first, the Ordovician-Silurian extinction, took place 440 million years ago and wiped out small marine organisms. One second, the Devonian extinction, occurred 365 million years ago, wiping out a variety of tropical marine species. After that, 250 million years ago, it was the Permian-Triassic extinction, followed by the Triassic-Jurassic extinction 210 million years ago, and the Cretaceous-Tertiary extinction 65 million years ago. Things have gone almost well in the years since then, even if 2020 has done its best to make us feel otherwise.
Scientists have long hypothesized that mass extinctions lead to productive periods of evolution, a process sometimes referred to as creative destruction or “radiation.” The idea is that these periods in which large numbers of species disappear are correlated with the arrival of new species.
To explore how well the data supports these theories, an international group of researchers applied machine learning technology to the immense fossil record of the history of life, visualizing its structure with an algorithm that incorporated 171,231 species within a multidimensional virtual space. The results helped the researchers determine whether certain species coexisted over time or never coexisted.
The machine learning algorithm was created by Nicholas Guttenberg of GoodAI and Cross Labs / Cross Compass in collaboration with the Tokyo Institute of Technology.
“Five exceptionally severe extinctions were known to have occurred during the last eon of life’s history, and it has been hypothesized that we might be entering another,” Jennifer Hoyal Cuthill, evolutionary biologist at the Institute for Data Science and Analytics and Faculty of Life Sciences at the University of Essex in the UK, which is affiliated with the Institute of Earth and Life Sciences (ELSI) at the Tokyo Institute of Technology, he told Digital Trends. “Our machine learning method… captures these ‘big five’ mass extinction events and allows us to visualize their significant impacts. But our study also places the five great mass extinctions in the context of all detectable disturbances in the fossil record. This shows the variety of evolutionary events that have impacted the history of life. “
Hoyal Cuthill said the work has opened up some interesting areas for possible research. In particular, it has helped counter some of the popular wisdom about mass extinctions and mass radiation, showing that the creation of large numbers of species and the extinction of others often occur at different times.
“Our new methods have potential applications in a wide range of data and we have more projects planned,” he said. “In general, there are so many areas of human knowledge where machine learning has yet to be applied, and therefore potentially there are a lot of great ideas waiting to be realized right now. I think this is a very exciting time. “
An article describing the work was published recently in the journal Nature.