Machine-learning enhanced dark soliton detection in Bose-Einstein condensates

Abstract

Most data in cold-atom experiments comes from images, the analysis of which is limited by our preconceptions of the patterns that could be present in the data. We focus on the well-defined case of detecting dark solitons -- appearing as local density depletions in a Bose-Einstein condensate (BEC) -- using a methodology that is extensible to the general task of pattern recognition in images of cold atoms. Studying soliton dynamics over a wide range of parameters requires the analysis of large datasets, making the existing human-inspection-based methodology a significant bottleneck. Here we describe an automated classification and positioning system for identifying localized excitations in atomic BECs utilizing deep convolutional neural networks to eliminate the need for human image examination. Furthermore, we openly publish our labeled dataset of dark solitons, the first of its kind, for further machine learning research.

arXiv comment17 pages, 5 figures

References in corpus (21)

• Dark Solitons in Bose-Einstein Condensates
• Dark solitons in atomic Bose-Einstein condensates: from theory to experiments
• Experimental observation of oscillating and interacting matter wave dark solitons
• Dynamics of dark solitons in elongated Bose-Einstein condensates
• A Convolutional Neural Network Neutrino Event Classifier
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Rapid production of ${}^{87}$Rb BECs in a combined magnetic and optical potential
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Machine Learning techniques for state recognition and auto-tuning in quantum dots
• Auto-tuning of double dot devices in situ with machine learning
• Brownian motion of solitons in a Bose-Einstein Condensate
• Computer-automated tuning procedures for semiconductor quantum dot arrays
• Creating solitons with controllable and near zero velocity in Bose-Einstein condensates
• Convolutional Neural Networks for Direct Detection of Dark Matter
• Single-exposure absorption imaging of ultracold atoms using deep learning
• Stability and dispersion relations of three-dimensional solitary waves in trapped Bose-Einstein condensates
• Atomic-level Characterisation of Quantum Computer Arrays by Machine Learning
• Supervised machine learning of ultracold atoms with speckle disorder
• Deep learning based quantum vortex detection in atomic Bose-Einstein condensates
• Deep learning for Directional Dark Matter search

Cited by in corpus (11)

• Topological data analysis and machine learning
• Machine-learning-accelerated Bose-Einstein condensation
• Efficient sorting of orbital-angular-momentum states with large topological charges and their unknown superpositions via machine learning
• Machine-learning assisted quantum control in random environment
• Vortex detection in atomic Bose-Einstein condensates using neural networks trained on synthetic images
• Dark soliton detection using persistent homology
• Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons
• Measuring the rogue wave pattern triggered from Gaussian perturbations by deep learning
• Dark solitons in Bose-Einstein condensates: a dataset for many-body physics research
• Characterizing far from equilibrium states of the one-dimensional nonlinear Schr{ö}dinger equation
• Observing phase jumps of solitons in Bose-Einstein condensates