Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning

TL;DR

This paper demonstrates that machine learning can significantly improve the extraction of physical observables from single-shot images of ultracold atoms, reducing data requirements and enabling cross-measurement in different experimental configurations.

Contribution

The authors introduce a neural network approach that enhances the accuracy and efficiency of observable extraction from ultracold atom images, surpassing standard averaging methods.

Findings

Machine learning achieves accurate one- and two-particle densities from fewer images.

Quantum fluctuations and correlations are directly utilized for precise measurements.

Momentum-space observables can be extracted from real-space images, reducing experimental reconfiguration.

Abstract

Single-shot images are the standard readout of experiments with ultracold atoms -- the tarnished looking glass into their many-body physics. The efficient extraction of observables from single-shot images is thus crucial. Here, we demonstrate how artificial neural networks can optimize this extraction. In contrast to standard averaging approaches, machine learning allows both one- and two-particle densities to be accurately obtained from a drastically reduced number of single-shot images. Quantum fluctuations and correlations are directly harnessed to obtain physical observables for bosons in a tilted double-well potential at an unprecedented accuracy. Strikingly, machine learning also enables a reliable extraction of momentum-space observables from real-space single-shot images and vice versa. This obviates the need for a reconfiguration of the experimental setup between in-situ and time-of-flight imaging, thus potentially granting an outstanding reduction in resources.