Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons
arXiv:2111.04881 · doi:10.1103/PhysRevResearch.4.023163
Abstract
In ultracold-atom experiments, data often comes in the form of images which suffer information loss inherent in the techniques used to prepare and measure the system. This is particularly problematic when the processes of interest are complicated, such as interactions among excitations in Bose-Einstein condensates (BECs). In this paper, we describe a framework combining machine learning (ML) models with physics-based traditional analyses to identify and track multiple solitonic excitations in images of BECs. We use an ML-based object detector to locate the solitonic excitations and develop a physics-informed classifier to sort solitonic excitations into physically motivated subcategories. Lastly, we introduce a quality metric quantifying the likelihood that a specific feature is a longitudinal soliton. Our trained implementation of this framework, SolDet, is publicly available as an open-source python package. SolDet is broadly applicable to feature identification in cold-atom images when trained on a suitable user-provided dataset.
arXiv comment13 pages, 9 figures
References in corpus (43)
- Quantum phase transition from a superfluid to a Mott insulator in a gas of ultracold atoms
- Dark Solitons in Bose-Einstein Condensates
- Machine learning phases of matter
- Synthetic magnetic fields for ultracold neutral atoms
- Spontaneous symmetry breaking in a quenched ferromagnetic spinor Bose condensate
- Many-body quantum state tomography with neural networks
- Oscillations and interactions of dark and dark-bright solitons in Bose-Einstein condensates
- Rapidly Rotating Bose-Einstein Condensates in and near the Lowest Landau Level
- A template bank for gravitational waveforms from coalescing binary black holes: non-spinning binaries
- JILA SrI Optical Lattice Clock with Uncertainty of
- Quantum Loop Topography for Machine Learning
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
- Fast machine-learning online optimization of ultra-cold-atom experiments
- Efficient learning of quantum noise
- Observation of Solitonic Vortices in Bose-Einstein Condensates
- Bogoliubov-Cerenkov radiation in a Bose-Einstein condensate flowing against an obstacle
- Machine learning out-of-equilibrium phases of matter
- Stabilization of Solitons Generated by a Supersonic Flow of Bose-Einstein Condensate Past an Obstacle
- Experimental Deep Reinforcement Learning for Error-Robust Gateset Design on a Superconducting Quantum Computer
- Machine Learning techniques for state recognition and auto-tuning in quantum dots
- Making, probing and understanding Bose-Einstein condensates
- Multiparameter optimisation of a magneto-optical trap using deep learning
- Periodic spin textures in a degenerate F=1 Rb spinor Bose gas
- Auto-tuning of double dot devices in situ with machine learning
- Attention-based Quantum Tomography
- Quenched binary Bose-Einstein condensates: spin domain formation and coarsening
- Brownian motion of solitons in a Bose-Einstein Condensate
- Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
- Linear "ship waves" generated in stationary flow of a Bose-Einstein condensate past an obstacle
- Harnessing Interpretable and Unsupervised Machine Learning to Address Big Data from Modern X-ray Diffraction
- Creating solitons with controllable and near zero velocity in Bose-Einstein condensates
- Applying machine learning optimization methods to the production of a quantum gas
- Toward Robust Autotuning of Noisy Quantum Dot Devices
- Observation of topological Bloch-state defects and their merging transition
- Machine-learning enhanced dark soliton detection in Bose-Einstein condensates
- Stability and dispersion relations of three-dimensional solitary waves in trapped Bose-Einstein condensates
- Deep learning based quantum vortex detection in atomic Bose-Einstein condensates
- Stationary wave patterns generated by an impurity moving with supersonic velocity through a Bose-Einstein condensate
- Optimization of Quantum-dot Qubit Fabrication via Machine Learning
- Creation and manipulation of quantized vortices in Bose-Einstein condensates using reinforcement learning
- Dark soliton detection using persistent homology
- Experimentally Realizing Efficient Quantum Control with Reinforcement Learning