Johns Hopkins University’s Applied Physics Laboratory and Department of Earth and Planetary Sciences have collaborated to develop an artificial intelligence-based model for understanding climate change “tipping points.”
The Physics-informed AI Climate Model Agent Neuro-symbolic Simulator for Tipping Point Discovery project is working on predicting—and hopefully avoiding—climate breaking points, Johns Hopkins APL said Friday.
Using the Atlantic Meridional Overturning Circulation system of ocean currents as its specific case, the research team created an AI simulation that can demonstrate the boundaries where the tipping points have a high probability of occurrence. The model was able to recreate a 2018 experiment that invoked traditional methods and similar parameters to predict the slowdown or collapse of AMOC, which is critical in the circulation of heat and freshwater in the region.
“This emerging field will also be of interest beyond the climate community, as tipping point discovery methods also apply to social, political and economic systems,” said Jennifer Sleeman, APL computer scientist and principal investigator of PACMANS.
The study is supported by the AI-assisted Climate Tipping-point Modeling program of the Defense Advanced Research Projects Agency.
