Controlling nonlinear dynamical systems into arbitrary states using machine learning
This provides a flexible control scheme for nonlinear systems with potential applications in engineering and medicine, though it appears incremental as it builds on existing ML-based prediction capabilities.
The authors tackled the problem of controlling nonlinear dynamical systems into arbitrary target states using a fully data-driven machine learning approach, demonstrating that systems like Lorenz and Rössler can be accurately forced into periodic, intermittent, and chaotic behaviors from any initial state with high flexibility and minimal data requirements.
We propose a novel and fully data driven control scheme which relies on machine learning (ML). Exploiting recently developed ML-based prediction capabilities of complex systems, we demonstrate that nonlinear systems can be forced to stay in arbitrary dynamical target states coming from any initial state. We outline our approach using the examples of the Lorenz and the Rössler system and show how these systems can very accurately be brought not only to periodic but also to e.g. intermittent and different chaotic behavior. Having this highly flexible control scheme with little demands on the amount of required data on hand, we briefly discuss possible applications that range from engineering to medicine.