Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

TT: Fachverband Tiefe Temperaturen

TT 63: Quantum Dynamics and Many-body Systems – Poster (joint session DY/TT)

TT 63.14: Poster

Mittwoch, 11. März 2026, 15:00–18:00, P5

Echo state network prediction of billiard dynamics — •Anna Skopnik, Lukas Seemann, and Martina Hentschel — Institut für Physik, TU Chemnitz, Germany

Machine Learning has attracted a lot of interest recently. Here, we apply an Echo State Network (ESN) algorithm to two mesoscopic billiard systems in order to explore its usability in the prediction of the internal dynamics of ballistic cavities. First, we study the well-known Limaçon system with chaotic dynamics. Second, we study the more complex dynamics in an anisotropis system inspired by bilayer graphene (BLG) representing a mixed space dynamics with regular and chaotic trajectories. Here, we present preliminary results on the training and hyperparameter optimization for both systems, Limaçon and BLG.

Keywords: Echo State Network; Billiard Dynamics; Bilayer Graphene