Researchers at the University of Waterloo are developing new artificial intelligence (AI) that could serve as an early warning system against climate change tipping points. New research focuses on the thresholds beyond which rapid or irreversible change occurs in a system.
Chris Bauch is Professor of Applied Mathematics at the University of Waterloo and co-author of the research paper.
“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 avoid them if we can. “
Climate change tipping points
These various climate change tipping points may include melting arctic permafrost, which could release massive amounts of methane that would cause even faster warming. It also includes the breakdown of ocean current systems, which can lead to immediate changes in weather conditions. Another possibility is the disintegration of the ice sheet, which could cause a rapid change in sea level.
According to the researchers, this new approach is innovative given that it was programmed to experience more than one type of tipping point. Instead, he learns the characteristics of tipping points in general.
The new algorithm is based on the hybridization of AI and mathematical tipping point theories, which gives better results than a single method on its own. AI is trained on a “universe of possible tipping points”, which includes approximately 500,000 models. It is then tested at specific real-world tipping points in various systems, such as historical climate core samples.
Timothy Lenton is director of the Global Systems Institute at the University of Exeter and one of the study’s other co-authors.
“Our improved method could set off red flags when we are near a dangerous tipping point,” Lenton said. “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 algorithm
Researchers have relied on deep learning, which is increasingly having a positive impact on pattern recognition and classification. Researchers first converted tipping point detection to a pattern recognition problem, which can detect patterns that are present before a tipping point. This in turn helps a machine learning algorithm to tell if a tipping point is coming.
Thomas Bury is a postdoctoral researcher at McGill University and one of the co-authors of the article.
“People know the tipping points in climate systems, but there are tipping points in ecology and epidemiology and even in the stock markets,” Bury said. “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.”
Madhur Anand is another researcher and director of the Guelph Institute for Environmental Research.
According to Anand, the newly developed deep learning algorithm is a “game changer for the ability to anticipate big changes, including those associated with climate change”.
The team will now work to give AI the data on contemporary trends in climate change. However, Anand cautions that the result is based on how those results are used.
“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.