Using the power of artificial intelligence (AI), scientists have revealed new insights into the creation and destruction of mass extinctions. Unlike conventional wisdom, their study suggests mass extinctions are not always a form of “creative destruction” that allows the opportunity for new organisms to radiate and thrive. Instead, it suggests that mass extinctions are rarely connected to radiations of new species.
Paleontologists have previously pinpointed five major mass extinction events including a handful of smaller mass extinctions in the history of our planet by looking for evidence of species loss in the fossil record. Perhaps the most well-known is the Cretaceous–Paleogene extinction event, aka K-T extinction, which wiped out the dinosaurs around 65 million years ago. It’s often held that this event effectively created a wasteland and "wiped the slate clean," providing fertile ground to allow organisms like mammals to recolonize and "radiate."
But is this necessarily the case with mass extinctions? The new research, reported in the journal Nature last week, used AI to sift through an extensive log of the fossil records, including over a million entries made up of almost two hundred thousand species, and identify patterns between extinction and radiation events.
"Some of the most challenging aspects of understanding the history of life are the enormous timescales and numbers of species involved,” Dr Hoyal Cuthill, lead study author from the University of Essex in the UK and the Tokyo Institute of Technology, said in a statement.
“New applications of machine learning can help by allowing us to visualize this information in a human-readable form. This means we can, so to speak, hold half a billion years of evolution in the palms of our hands, and gain new insights from what we see."
They concluded that mass extinctions and subsequent radiations were not as linked as previously thought. Among the 5 percent most significant periods of disruption, the AI identified the ‘big five’ mass extinction events, seven other mass extinctions, two combined mass extinction–radiation events, and 15 mass radiations. Most crucially, it discovered mass radiations and extinctions rarely occurred in tandem with one another, dispelling the idea that mass extinctions necessarily lead to the radiation of species, like some kind of profound cycle of nature. It appears that mass extinctions are not necessarily the engines of evolutionary radiation.
For example, take the Cambrian explosion. This was a period some 541 million years ago when most of the major groups of animals first appeared in the fossil record, sparking the dawn of highly mobile animals that were armed with modern anatomical features. This new research suggests the Cambrian explosion, along with a handful of other significant explosions of animal diversity, generally occurred at times that were widely separated from the mass extinction events.
“The ecosystem is dynamic, you don't necessarily have to chip an existing piece off to allow something new to appear," explained Dr Nicholas Guttenberg, study co-author from the Tokyo Institute of Technology.