WATERLOO – Imagine knowing when something terrible was going to happen before it happened.
One way of understanding “tipping points” that can lead to actions to deflect problems, or in cases where it is too late to reverse, is helping those most affected to prepare.
Now imagine that this is applied to some of the largest systems in the world – climate change, national and global economies or disease states of the human body.
That’s the goal of a new multidisciplinary study published in the Proceedings of the National Academy of Sciences of the United States of America, where a team or researchers from the University of Waterloo and beyond developed a system deep learning – or artificial intelligence – to provide harbingers of tipping points in real-world systems.
“Our basic idea was to realize that because all kinds of complex systems behave similarly near tipping points, regardless of the type of system, we can use this idea from mathematical theory to improve the ability AI algorithms to detect failovers. points, ”said Chris Bauch, professor of applied mathematics at the University of Waterloo and co-author of the study.
In the realm of climate change action, uncovering these tipping points could help governments and other international bodies make better decisions about mitigating crises before they happen.
To find these warning signs of climate change, the team can use specific data sets – the more data they can process in the system, the more accurate the result – on topics such as melting arctic permafrost, ocean current systems or the increase in global temperature.
The approach, which is a hybrid model that includes both AI and established mathematical theories on tipping points, goes beyond what either discipline could accomplish by it- same, said Bauch.
The idea came from Bauch and his wife, Madhur Anand, an environmentalist and director of the Guelph Institute for Environmental Research. The two made waves in the scientific community last year when they used game theory to model different ways to prioritize vaccine distribution to determine what would save the most lives.
“It definitely gives us a head start,” Anand said of tipping points. “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.
Thomas Bury, a former Waterloo student now at McGill University, was associated with the project to use his expertise in both mathematical theories on tipping points and in computer science.
The team then reached out to collaborators with specific knowledge of environmental systems from the UK, the Netherlands and India to help them explain and contextualize the datasets the algorithm would work with.
In these early stages, Bauch explained, it’s important to study situations that have already experienced tipping points so that they can test the predictions against the data to see how accurate they are.
“At the end of the day, the goal is if we can detect an approaching tipping point, then we hope we can avoid it,” he said. “And even if we can’t avoid it, then we can plan it so that the worst impacts are mitigated. “
It goes beyond action on climate change, Bury explained, and includes things like algae blooms, fishing collapse and epileptic seizures.
Its use in the medical field is particularly promising.
“The transition from health to disease can occur through a tipping point, suggesting that our approach could have therapeutic application,” he said. It has real life application for medical topics like depression, cancer, and cardiovascular events.
“The improvement of wearable devices in collecting massive amounts of physiological data makes it an attractive area to test our algorithm,” he said.