Single-exposure absorption imaging of ultracold atoms using deep learning

Abstract

Absorption imaging is the most common probing technique in experiments with ultracold atoms. The standard procedure involves the division of two frames acquired at successive exposures, one with the atomic absorption signal and one without. A well-known problem is the presence of residual structured noise in the final image, due to small differences between the imaging light in the two exposures. Here we solve this problem by performing absorption imaging with only a single exposure, where instead of a second exposure the reference frame is generated by an unsupervised image-completion autoencoder neural network. The network is trained on images without absorption signal such that it can infer the noise overlaying the atomic signal based only on the information in the region encircling the signal. We demonstrate our approach on data captured with a quantum degenerate Fermi gas. The average residual noise in the resulting images is below that of the standard double-shot technique. Our method simplifies the experimental sequence, reduces the hardware requirements, and can improve the accuracy of extracted physical observables. The trained network and its generating scripts are available as an open-source repository (http://absDL.github.io/).

7 pages, 6 figures

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Quantum Machine Learning
• Machine learning and the physical sciences
• A high-bias, low-variance introduction to Machine Learning for physicists
• Fast machine-learning online optimization of ultra-cold-atom experiments
• Multiparameter optimisation of a magneto-optical trap using deep learning
• A Survey of Deep Learning for Scientific Discovery
• Applying machine learning optimization methods to the production of a quantum gas
• Realistic Shortcuts to Adiabaticity in Optical Transfer
• High Sensitivity RF Spectroscopy of a Strongly-Interacting Fermi Gas
• Supervised machine learning of ultracold atoms with speckle disorder
• Fast and High-Fidelity Readout of Single Trapped-Ion Qubit via Machine Learning Methods
• Optimized fringe removal algorithm for absorption images
• Deep Learning-Assisted Classification of Site-Resolved Quantum Gas Microscope Images

Cited by in corpus (18)

• Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
• Machine-learning-accelerated Bose-Einstein condensation
• Machine-learning enhanced dark soliton detection in Bose-Einstein condensates
• Absence of heating in a uniform Fermi gas created by periodic driving
• Perspective on new implementations of atomtronic circuits
• Deep learning based quantum vortex detection in atomic Bose-Einstein condensates
• Continuous field tracking with machine learning and steady state spin squeezing
• Optical lattice experiments at unobserved conditions and scales through generative adversarial deep learning
• Thermometry of one-dimensional Bose gases with neural networks
• Vortex detection in atomic Bose-Einstein condensates using neural networks trained on synthetic images
• Spatial calibration of high-density absorption imaging
• Atom Cloud Detection Using a Deep Neural Network
• Atom Number Fluctuations in Bose Gases -- Statistical analysis of parameter estimation
• On the fluctuations of the number of atoms in the condensate
• Dark solitons in Bose-Einstein condensates: a dataset for many-body physics research
• Adaptive, symmetry-informed Bayesian metrology for precise quantum technology measurements
• Utilizing machine learning to improve the precision of fluorescence imaging of cavity-generated spin squeezed states
• Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning