Artificial intelligence could reveal tipping points of climate change

Researchers are developing artificial intelligence that could assess tipping points of climate change. The deep learning algorithm could serve as an early warning system against uncontrollable climate change.

Chris Bauch, professor of applied mathematics at the University of Waterloo, is co-author of a recent research paper presenting the results of the new deep learning algorithm. Research examines the thresholds beyond which rapid or irreversible change occurs in a system, Bauch said. “We found that the new algorithm was able not only to predict tipping points more accurately than existing approaches, but also to provide information about the type of state beyond the tipping point,” said said Bauch. “A lot of these tipping points are unwanted, and we would like to prevent them if we can.”

Some tipping points that are often associated with uncontrollable climate change include melting arctic permafrost, which could release massive amounts of methane and cause even faster warming; disruption of ocean current systems, which could lead to almost immediate changes in weather patterns; or the disintegration of the ice sheet, which could lead to a rapid change in sea level.

The innovative approach to this AI, according to the researchers, is that it has been programmed to learn not only one type of tipping point, but the characteristics of tipping points in general.

The approach draws its strength from the hybridization of AI and mathematical tipping point theories, accomplishing more than either method could do on its own. After training the AI ​​on what they characterize as a “universe of possible tipping points” that included some 500,000 models, the researchers tested it on specific real-world tipping points in various systems, including historical climate core samples.

“Our improved method could set off red flags when we are near a dangerous tipping point,” said Timothy Lenton, director of the Global Systems Institute at the University of Exeter and one of the co-authors of study. “Providing better early warning of climate tipping points could help societies adapt and reduce their vulnerability to what is to come, even if they cannot avoid it.”

Deep learning is making huge strides in pattern recognition and classification, with researchers for the first time converting tipping point detection into a pattern recognition problem. This is done to try to detect patterns that occur before a tipping point and get a machine learning algorithm to tell if a tipping point is coming.

“People know the tipping points in climate systems, but there are tipping points in ecology and epidemiology and even in the stock markets,” said Thomas Bury, postdoctoral researcher at McGill University and another of the co -authors of the article. “What we have learned is that AI is very good at detecting the characteristics 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 changes, including those associated with climate change,” said Madhur Anand, another of the project researchers and director of the Guelph Institute for Environmental Research. .

Now that their AI has learned how tipping points work, the team is working on the next step, which is to provide them with the data on contemporary climate change trends. But Anand warned about what can happen with such knowledge.

“It definitely gives us a head start,” she said. “But of course it’s up to humanity to decide what we do with this knowledge. I just hope these new findings lead to fair and positive change.”

The article “Deep learning for early warning signals of tipping points”, by Bauch, Lenton, Bury, Anand and co-authors RI Sujith, Induja Pavithran and Marten Scheffer, was published in the journal Proceedings of the National Academy of Sciences (PNAS).