SAMOP 2023 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
Q: Fachverband Quantenoptik und Photonik
Q 13: Ultra-cold Atoms, Ions and BEC I (joint session A/Q)
Q 13.4: Vortrag
Montag, 6. März 2023, 18:00–18:15, F303
Optimizing optical potentials with physics-inspired learning algorithms — •Martino Calzavara1,4, Yevhenii Kuriatnikov2, Andreas Deutschmann-Olek3, Felix Motzoi1, Sebastian Erne2, Andreas Kugi3, Tommaso Calarco1,4, Jörg Schmiedmayer2, and Maximilian Prüfer2 — 1Forschungszentrum Jülich GmbH, Peter Grünberg Institute, Quantum Control (PGI-8), 52425 Jülich, Germany — 2Vienna Center for Quantum Science and Technology, Atominstitut, TU Wien, Stadionallee 2, 1020 Vienna, Austria — 3Automation and Control Institute, TU Wien, Gußhausstraße 27-29, 1040 Vienna, Austria — 4Institute for Theoretical Physics, Universität zu Köln, 50937 Cologne, Germany
We present our new experimental and theoretical framework which combines a broadband superluminescent diode (SLED/SLD) with fast learning algorithms to provide speed and accuracy improvements for the optimization of 1D optical dipole potentials, here generated with a Digital Micromirror Device (DMD). We employ Machine Learning (ML) tools to train a physics-inspired model acting as a digital twin of the optical system predicting the behavior of the optical apparatus including all its imperfections. Implementing an algorithm based on Iterative Learning Control (ILC), we optimize optical potentials an order of magnitude faster than heuristic optimization methods. We compare iterative model-based “offline” optimization and experimental feedback-based “online” optimization. Our methods provide a new route to fast optimization of optical potentials which is relevant for the dynamical manipulation of ultracold gases.