Deep Learning for Absorption-Image Analysis

TL;DR

This paper introduces modified deep learning models for analyzing absorption images of ultracold atom clouds, achieving comparable accuracy to traditional methods with faster computation, and enabling simpler experimental setups.

Contribution

It presents a novel application of deep learning for image regression in absorption imaging, trained on simulated data, and demonstrates advantages over least-squares techniques.

Findings

Deep learning models match least-squares accuracy in parameter estimation.

Models trained on simulated images perform well on real data.

Single-image models enable simplified, single-exposure absorption imaging.

Abstract

The quantum state of ultracold atoms is often determined through measurement of the spatial distribution of the atom cloud. Absorption imaging of the cloud is regularly used to extract this spatial information. Accurate determination of the parameters which describe the spatial distribution of the cloud is crucial to the success of many ultracold atom applications. In this work, we present modified deep learning image classification models for image regression. To overcome challenges in data collection, we train the model on simulated absorption images. We compare the performance of the deep learning models to least-squares techniques and show that the deep learning models achieve accuracy similar to least-squares, while consuming significantly less computation time. We compare the performance of models which take a single atom image against models which use an atom image plus other images that contain background information, and find that both models achieved similar accuracy. The use of single image models will enable single-exposure absorption imaging, which simplifies experiment design and eases imaging hardware requirements.