Climate tipping points are a particular threat to life on Earth, as when they are reached, they can set off chain reactions of climate-altering processes, supercharging global heating and rapidly exacerbating the existing climate crisis.
Examples include the melting of the Arctic permafrost, which could release massive amounts of the potent greenhouse gas methane, which would generate further rapid heating; the breakdown of ocean current systems, which would cause almost immediate major changes to global weather patterns; and ice sheet disintegration, which could lead to rapid sea-level rises.
Using a “deep-learning” algorithm, the researchers examined thresholds beyond which rapid or irreversible change happens in a system.
Chris Bauch, professor of applied mathematics at the University of Waterloo in Ontario, Canada, said: “We found that the new algorithm was able to not only predict the tipping points more accurately than existing approaches but also provide information about what type of state lies beyond the tipping point.
“Many of these tipping points are undesirable, and we’d like to prevent them if we can.”
The researchers also said they took an innovative approach with the creation of the AI, programming it to learn not just about individual tipping points, but about the processes and characteristics of the Earth’s climate tipping points generally.
Through using a combination of AI and existing mathematical theories of tipping points, the team said their AI was able to accomplish more than either method could on its own.
The researchers trained the AI on what they described as a “universe of possible tipping points”, including around half a million ecosystem models, and then tested it on specific real-world tipping points in various Earth systems – this included using historical climate core samples.
“Our improved method could raise red flags when we’re close to a dangerous tipping point,” said Timothy Lenton, director of the Global Systems Institute at the University of Exeter and one of the study’s co-authors.
“Providing improved early warning of climate tipping points could help societies adapt and reduce their vulnerability to what is coming, even if they cannot avoid it.”
The researchers said deep learning is “making huge strides in pattern recognition and classification”, with the team converting tipping-point detection into a pattern-recognition problem, for the first time.
They said this was done to try and detect the patterns that occur before a tipping point, so a machine-learning algorithm is able to say whether a tipping point is coming.
“People are familiar with tipping points in climate systems, but there are tipping points in ecology and epidemiology and even in the stock markets,” said Thomas Bury, a postdoctoral researcher at McGill University in Montreal, and another of the co-authors on the paper.
“What we’ve learned is that AI is very good at detecting features of tipping points that are common to a wide variety of complex systems.”
The new deep learning algorithm is a “game-changer for the ability to anticipate big shifts, including those associated with climate change,” said Madhur Anand, one of the researchers on the project and director of the Guelph Institute for Environmental Research in Ontario.
The team said the next step is to give the AI the data for contemporary trends in climate change. But Professor Anand issued a word of caution of what may happen with such knowledge.
“It definitely gives us a leg up,” she said. “But of course, it’s up to humanity in terms of what we do with this knowledge. I just hope that these new findings will lead to equitable, positive change.”
The research is published in the journal Proceedings of the National Academy of Sciences.