Chris Bauch, an applied mathematics professor and University Research Chair, recently published a paper in the Proceedings of the National Academy of Sciences (PNAS) on new research related to a deep learning algorithm capable of detecting and predicting tipping points.
Bauch was part of a team of researchers working on the project, which has far-reaching implications for assessing the risks associated with climate change tipping points.
The method used to train the AI, however, involved tipping points generally, and not only those associated with climate change. This approach takes into account tipping points that exist in human and non-human systems including the stock markets, algae blooms and even epileptic seizures. A tipping point, in this sense, refers to thresholds beyond which rapid or irreversible change happens in any system.
“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,” Bauch said.
Read more about the new research in the recent news article at this link.