Optimizing persistent currents in a ring-shaped Bose-Einstein condensate using machine learning

TL;DR

This paper presents a machine learning approach to optimize stirring protocols in Bose-Einstein condensates to reliably generate persistent superfluid currents, demonstrating adaptability to different objectives and constraints.

Contribution

The study introduces a Gaussian process learner to experimentally optimize stirring in BECs, a novel application of machine learning for controlling quantum fluids.

Findings

Successful optimization of stirring protocols for persistent currents

Optimal stirring profiles vary with cost functions and scenarios

Persistent currents can be reliably generated through diverse stirring methods

Abstract

We demonstrate a method for generating persistent currents in Bose-Einstein condensates by using a Gaussian process learner to experimentally control the stirring of the superfluid. The learner optimizes four different outcomes of the stirring process: (O.I) targeting and (O.II) maximization of the persistent current winding number; and (O.III) targeting and (O.IV) maximization with time constraints. The learner optimizations are determined based on the achieved winding number and the number of spurious vortices introduced by stirring. We find that the learner is successful in optimizing the stirring protocols, although the optimal stirring profiles vary significantly depending strongly on the choice of cost function and scenario. These results suggest that stirring is robust and persistent currents can be reliably generated through a variety of stirring approaches.