Scientists have shown the possibility of using artificial intelligence to identify climate change tipping points in advance thereby paving way for proactive steps that could be taken to avoid runaway climate conditions that eventually are more disastrous and costly to deal with.
According on one of the authors of the paper – Chris Bauch, a professor of applied mathematics at the University of Waterloo – they have found that their new algorithm is not only able to predict climate change tipping points, but it is also able to predict the situation post the tipping point. The new deep-learning algorithm looks at thresholds beyond which rapid or irreversible change happens in a system.
Melting Arctic permafrost, breakdown of oceanic current systems, or ice sheet disintegration, are the climate change tipping points that the algorithm could predict. The algorithm is not only able to predict about one type of tipping point, but looks at the characteristics of tipping points generally and so it is able to predict about them and the situation beyond those tipping points.
The approach gains its strength from hybridizing AI and mathematical theories of tipping points, accomplishing more than either method could 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.
According to another author of the paper, their algorithm is able to warn us about these tipping points in advance thereby enabling us to adapt and reduce possible vulnerable situations to reduce the overall impact even if there is no possibility of avoiding it.
Deep learning is making huge strides in pattern recognition and classification, with the researchers having, for the first time, converted tipping-point detection into a pattern-recognition problem. This is done to try and detect the patterns that occur before a tipping point and get a machine-learning algorithm to say whether a tipping point is coming.
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, another of the researchers on the project and director of the Guelph Institute for Environmental Research.
Now that their AI has learned how tipping points function, the team is working on the next stage, which is to give it the data for contemporary trends in climate change. But Anand issued a word of caution of what may happen with such knowledge.
The paper “Deep learning for early warning signals of tipping points,” by Bauch, Lenton, Bury, Anand and co-authors R. I. Sujith, Induja Pavithran, and Marten Scheffer, was published in the journal Proceedings of the National Academy of Sciences (PNAS).