Optimizing optical potentials with physics-inspired learning algorithms

TL;DR

This paper introduces a physics-inspired machine learning framework that significantly accelerates the optimization of 1D optical dipole potentials, enhancing speed and accuracy for ultracold gas manipulation.

Contribution

The work combines a broadband superluminescent diode with machine learning and iterative control to improve optical potential optimization speed and accuracy over traditional methods.

Findings

Optimization speed improved by an order of magnitude.

Physics-inspired models effectively predict system behavior.

Iterative learning control enhances experimental efficiency.

Abstract

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). To characterize the setup and potential speckle patterns arising from coherence, we compare the superluminescent diode to a single-mode laser by investigating interference properties. 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 iterative 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.