Vortex detection in atomic Bose-Einstein condensates using neural networks trained on synthetic images
arXiv:2308.08405 · doi:10.1088/2632-2153/ad03ad
Abstract
Quantum vortices in atomic Bose-Einstein condensates (BECs) are topological defects characterized by quantized circulation of particles around them. In experimental studies, vortices are commonly detected by time-of-flight imaging, where their density-depleted cores are enlarged. In this work, we describe a machine learning-based method for detecting vortices in experimental BEC images, particularly focusing on turbulent condensates containing irregularly distributed vortices. Our approach employs a convolutional neural network (CNN) trained solely on synthetic simulated images, eliminating the need for manual labeling of the vortex positions as ground truth. We find that the CNN achieves accurate vortex detection in real experimental images, thereby facilitating analysis of large experimental datasets without being constrained by specific experimental conditions. This novel approach represents a significant advancement in studying quantum vortex dynamics and streamlines the analysis process in the investigation of turbulent BECs.
arXiv comment10 pages, 6 figures
References in corpus (49)
- Vortex formation in a stirred Bose-Einstein condensate
- Vortices in a Bose-Einstein Condensate
- Berezinskii-Kosterlitz-Thouless Crossover in a Trapped Atomic Gas
- Spontaneous vortices in the formation of Bose-Einstein condensates
- Fortran programs for the time-dependent Gross-Pitaevskii equation in a fully anisotropic trap
- Observation of vortex dipoles in an oblate Bose-Einstein condensate
- Emergence of turbulence in an oscillating Bose-Einstein condensate
- Observation of vortex phase singularities in Bose-Einstein condensates
- Vortex nucleation in Bose-Einstein condensates in an oblate, purely magnetic potential
- Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
- Giant Vortex Clusters in a Two-Dimensional Quantum Fluid
- Observations of density fluctuations in an elongated Bose gas: ideal gas and quasi-condensate regimes
- Fast machine-learning online optimization of ultra-cold-atom experiments
- C programs for solving the time-dependent Gross-Pitaevskii equation in a fully anisotropic trap
- Order from chaos: Observation of large-scale flow from turbulence in a two-dimensional superfluid
- Characteristics of Two-Dimensional Quantum Turbulence in a Compressible Superfluid
- Nonequilibrium effects of anisotropic compression applied to vortex lattices in Bose-Einstein condensates
- Relaxation of superfluid turbulence in highly oblate Bose-Einstein condensates
- Quantum turbulence in trapped atomic Bose-Einstein condensates
- Vortex proliferation in the Berezinskii-Kosterlitz-Thouless regime on a two-dimensional lattice of Bose-Einstein condensates
- Observation of von Kármán Vortex Street in an Atomic Superfluid Gas
- Classifying Snapshots of the Doped Hubbard Model with Machine Learning
- Suppression of Density Fluctuations in a Quantum Degenerate Fermi Gas
- Machine Learning for Synthetic Data Generation: A Review
- Kibble-Zurek universality in a strongly interacting Fermi superfluid
- Unsupervised machine learning of topological phase transitions from experimental data
- Critical Velocity for Vortex Shedding in a Bose-Einstein Condensate
- Observation of vortex-antivortex pairing in decaying 2D turbulence of a superfluid gas
- Vortices in Bose-Einstein-Condensed Atomic Clouds
- Full Counting Statistics of Topological Defects After Crossing a Phase Transition
- Free expansion of Bose-Einstein condensates with quantized vortices
- Machine Learning for Achieving Bose-Einstein Condensation of Thulium Atoms
- Observation of Thermally Activated Vortex Pairs in a Quasi-2D Bose Gas
- Defect Saturation in a Rapidly Quenched Bose Gas
- Applying machine learning optimization methods to the production of a quantum gas
- Machine-learning enhanced dark soliton detection in Bose-Einstein condensates
- Single-exposure absorption imaging of ultracold atoms using deep learning
- Vortex shedding frequency of a moving obstacle in a Bose-Einstein condensate
- Locality of Spontaneous Symmetry Breaking and Universal Spacing Distribution of Topological Defects Formed Across a Phase Transition
- Universal Early Coarsening of Quenched Bose Gases
- Measuring the disorder of vortex lattices in a Bose-Einstein condensate
- Deep learning based quantum vortex detection in atomic Bose-Einstein condensates
- Variations of the Kibble-Zurek scaling exponents of trapped Bose gases
- Suppression of Spontaneous Defect Formation in Inhomogeneous Bose Gases
- Large-area Rb Bose-Einstein condensate in a clipped-Gaussian optical dipole trap
- Free expansion of quasi-2D Bose-Einstein condensates with quantized vortices
- Atom Cloud Detection Using a Deep Neural Network
- Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons
- Machine learning classification of two-dimensional vortex configurations
Cited by in corpus (6)
- Perspective on new implementations of atomtronic circuits
- Universal Vortex Statistics and Stochastic Geometry of Bose-Einstein Condensation
- Electrodynamics of Vortices in Quasi-2D Scalar Bose-Einstein Condensates
- CNN-Based Vortex Detection in Atomic 2D Bose Gases in the Presence of a Phononic Background
- Probing early phase coarsening in a rapidly quenched Bose gas using off-resonant matter-wave interferometry
- Vortices in the Many-Body Excited States of Interacting Bosons in Two Dimension