Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
DY: Fachverband Dynamik und Statistische Physik
DY 6: Machine Learning in Dynamics and Statistical Physics I
DY 6.8: Vortrag
Montag, 9. März 2026, 11:30–11:45, HÜL/S186
Controlling dynamical systems into unseen target states using machine learning — Daniel Köglmayr1,2, Alexander Haluszczynski3, and •Christoph Räth1,2 — 1Deutsches Zentrum für Luft- und Raumfahrt (DLR) — 2Ludwig-Maximilians-Universität (LMU) — 3Allianz Global Investors (AGI)
Controlling nonlinear dynamical systems is a central task in many different areas of science and engineering. Combining previous work on controlling chaotic systems to arbitrary states [1] and extrapolating the system behavior into unseen parameter regions [2] using machine learning, we present here a novel, model-free, and data-driven methodology for controlling complex dynamical systems into previously unseen target states, including those with significantly different and complex dynamics. Leveraging a parameter-aware realization of next-generation reservoir computing (NGRC), our approach accurately predicts system behavior in unobserved parameter regimes, enabling control over transitions to arbitrary target states utilizing a new prediction evaluation and selection scheme [3]. By extending the applicability of machine learning-based control mechanisms to previously inaccessible target dynamics, this methodology opens the door to transformative new applications while maintaining exceptional efficiency. Our results highlight reservoir computing as a powerful alternative to traditional methods for dynamic system control.
[1] A. Haluszczynski & C. Räth, Sci Rep 11, 12991 (2021), [2] D. Köglmayr & C. Räth, Sci Rep 14, 507 (2024), [3] D. Köglmayr, A. Haluszczynski & C. Räth, submitted (https://arxiv.org/abs/2412.10251)
Keywords: Complex systems; Controlling; Machine Learning; Reservoir Computing