Machine-learning prediction of tipping with applications to the Atlantic Meridional Overturning Circulation
This addresses the challenge of anticipating critical transitions like tipping points, which is relevant across diverse fields including climate science, but the method is incremental as it builds on existing machine-learning frameworks.
The researchers tackled the problem of predicting tipping points in nonautonomous dynamical systems, such as the collapse of the Atlantic Meridional Overturning Circulation (AMOC), by developing a general data-driven machine-learning approach that exploits noise, and they predicted a potential collapse window from 2040 to 2065 based on synthetic and empirical data.
Anticipating a tipping point, a transition from one stable steady state to another, is a problem of broad relevance due to the ubiquity of the phenomenon in diverse fields. The steady-state nature of the dynamics about a tipping point makes its prediction significantly more challenging than predicting other types of critical transitions from oscillatory or chaotic dynamics. Exploiting the benefits of noise, we develop a general data-driven and machine-learning approach to predicting potential future tipping in nonautonomous dynamical systems and validate the framework using examples from different fields. As an application, we address the problem of predicting the potential collapse of the Atlantic Meridional Overturning Circulation (AMOC), possibly driven by climate-induced changes in the freshwater input to the North Atlantic. Our predictions based on synthetic and currently available empirical data place a potential collapse window spanning from 2040 to 2065, in consistency with the results in the current literature.