Machine learning prediction of critical transition and system collapse
This work provides a model-free method for predicting critical transitions and system collapse, which is significant for fields dealing with complex dynamical systems where explicit models are often unavailable.
This paper addresses the problem of predicting critical transitions and system collapse in nonlinear dynamics without relying on a specific model. The authors developed a machine learning solution using reservoir computing with a parameter input channel, demonstrating accurate prediction of transition points and the average transient time before collapse when trained in the normal functioning regime.
To predict a critical transition due to parameter drift without relying on model is an outstanding problem in nonlinear dynamics and applied fields. A closely related problem is to predict whether the system is already in or if the system will be in a transient state preceding its collapse. We develop a model free, machine learning based solution to both problems by exploiting reservoir computing to incorporate a parameter input channel. We demonstrate that, when the machine is trained in the normal functioning regime with a chaotic attractor (i.e., before the critical transition), the transition point can be predicted accurately. Remarkably, for a parameter drift through the critical point, the machine with the input parameter channel is able to predict not only that the system will be in a transient state, but also the average transient time before the final collapse.