Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Physica Scripta

Deep-learning-enhanced imaging processing in a spinor Bose-Einstein condensate

Jun Jian, Xin Wang, Yong Kun Qin, Wenliang Liu, Jizhou Wu, Yuqing Li, Peng Li, Yongming Fu, Qunchao Fan, Jie Ma, Liantuan Xiao, Suotang Jia

Published Jun 27, 2025• 0 citations
Publisher

Abstract

Abstract Accurate and swift identification of atomic cloud regions in absorption images is crucial for extracting physical information in ultracold atomic experiments, where absorption imaging plays a critical detection role. This study has devised a novel deep learning-based approach for the identification and extraction of atomic clouds in absorption images of ultracold atoms. The methodology consists of two main components. Initially, a YOLOv5 model is developed to identify atomic cloud regions. This process involves creating a training dataset by extensively collecting data from the sodium Bose-Einstein condensate (BEC) platform and annotating atomic cloud regions in the images. These annotated images are then utilized to train a neural network, resulting in a proficient YOLOv5 model for the initial selection of atomic cloud regions. The second part involves the secondary positioning of the initially identified atomic cloud regions. This step includes conducting a grid search in proximity to the initially identified regions, using goodness-of-fit as a criterion to pinpoint the most suitable atomic cloud regions. The method showcases remarkable efficiency and accuracy in calibrating atomic cloud regions through impressive automated processing, robustness, and generalization capabilities. Its successful application in processing Rabi oscillation images further verifies its reliability based on physical laws.

DOI
10.1088/1402-4896/ade943

Related papers

Deep Learning for Absorption-Image Analysis

Jacob Morrey, I. Peterson, Robert H. Leonard +4 more

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.

arXiv:2506.04517•Jun 4, 2025•0 citations

Atom cloud detection and segmentation using a deep neural network

Lucas R. Hofer, Milan Krstajić, Péter Juhász +2 more

Abstract We use a deep neural network (NN) to detect and place region-of-interest (ROI) boxes around ultracold atom clouds in absorption and fluorescence images—with the ability to identify and bound multiple clouds within a single image. The NN also outputs segmentation masks that identify the size, shape and orientation of each cloud from which we extract the clouds’ Gaussian parameters. This allows 2D Gaussian fits to be reliably seeded thereby enabling fully automatic image processing. The method developed performs significantly better than a more conventional method based on a standardized image analysis library (Scikit-image) both for identifying ROI and extracting Gaussian parameters.

arXiv:2011.10536•Machine Learning Science and Technology•Apr 8, 2021•6 citations

Single-Exposure Absorption Imaging of Ultracold Atoms Using Deep Learning

Gal Ness, Anastasiya Vainbaum, Constantine Shkedrov +2 more

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 image-completion autoencoder neural network. The network is trained on images without an 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 (absDL.github.io).

arXiv:2003.01643•Physical Review Applied•Jul 6, 2020•29 citations

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

Shangjie Guo, A. R. Fritsch, Craig Greenberg +2 more

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:2101.05404•Machine Learning Science and Technology•Mar 9, 2021•32 citations

U-net based vortex detection in Bose–Einstein condensates with automatic correction for manually mislabeled data

Jing Ye, Yue Huang, Keyan Liu

Quantum vortices in Bose-Einstein condensates (BECs) are essential phenomena in condensed matter physics, and precisely locating their positions, especially the vortex core, is a precondition for studying their properties. With the rise of machine learning, there is a possibility to expedite the localization process and provide accurate predictions. However, traditional machine learning requires particular considerable amount of manual data annotation, leading to uncontrollable accuracy. In this paper, we utilize the U-Net method to detect vortex positions accurately at the pixel level and propose an Automatic Correction Labeling (ACL) approach to optimize the acquisition of data sets for vortex localization in BECs. This approach addresses inaccuracies in the labeled vortex positions and improves the accuracy of vortex localization, especially the vortex core positions, while enhancing the tolerance for human mislabeling. The main process involves Rough Labeling [Formula: see text] Machine Learning [Formula: see text] Probability Region Search [Formula: see text] Data Relabeling [Formula: see text] Machine Learning again. The objective of ACL is to secure more accurate labeled data for model retraining. Through vortex localization experiments conducted in a two-dimensional Bose-Einstein condensate, our results establish the following: 1. Even under conditions of biased and missing manual annotations, U-Net can still accurately locate vortex positions; 2. Vortices exhibit certain regularities, and training U-Net with a small number of samples yields excellent predictive consequences; 3. The machine learning vortex locator based on the ACL method effectively corrects errors in manually annotated data, significantly improving the model's performance metrics, thus enhancing the precision and metrics of vortex localization. This substantial advancement in the application of machine learning in vortex localization provides an effective way for vortex dynamics localization. Furthermore, this method of obtaining more accurate positions of approximate human labels through machine learning offers new insights for machine learning in other types of image recognition problems.

Scientific Reports•Dec 2, 2023•1 citation

Vortex detection in atomic Bose–Einstein condensates using neural networks trained on synthetic images

Myeonghyeon Kim, Junhwan Kwon, Tenzin Rabga +1 more

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:2308.08405•Machine Learning Science and Technology•Oct 16, 2023•8 citations
Abstract Accurate and swift identification of atomic cloud regions in absorption images is crucial for extracting physical information in ultracold atomic experiments, where absorption imaging plays a critical detection role. This study has devised a novel deep learning-based approach for the identification and extraction of atomic clouds in absorption images of ultracold atoms. The methodology consists of two main components. Initially, a YOLOv5 model is developed to identify atomic cloud regions. This process involves creating a training dataset by extensively collecting data from the sodium Bose-Einstein condensate (BEC) platform and annotating atomic cloud regions in the images. These annotated images are then utilized to train a neural network, resulting in a proficient YOLOv5 model for the initial selection of atomic cloud regions. The second part involves the secondary positioning of the initially identified atomic cloud regions. This step includes conducting a grid search in proximity to the initially identified regions, using goodness-of-fit as a criterion to pinpoint the most suitable atomic cloud regions. The method showcases remarkable efficiency and accuracy in calibrating atomic cloud regions through impressive automated processing, robustness, and generalization capabilities. Its successful application in processing Rabi oscillation images further verifies its reliability based on physical laws.
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.
Abstract We use a deep neural network (NN) to detect and place region-of-interest (ROI) boxes around ultracold atom clouds in absorption and fluorescence images—with the ability to identify and bound multiple clouds within a single image. The NN also outputs segmentation masks that identify the size, shape and orientation of each cloud from which we extract the clouds’ Gaussian parameters. This allows 2D Gaussian fits to be reliably seeded thereby enabling fully automatic image processing. The method developed performs significantly better than a more conventional method based on a standardized image analysis library (Scikit-image) both for identifying ROI and extracting Gaussian parameters.
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 image-completion autoencoder neural network. The network is trained on images without an 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 (absDL.github.io).
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.
Quantum vortices in Bose-Einstein condensates (BECs) are essential phenomena in condensed matter physics, and precisely locating their positions, especially the vortex core, is a precondition for studying their properties. With the rise of machine learning, there is a possibility to expedite the localization process and provide accurate predictions. However, traditional machine learning requires particular considerable amount of manual data annotation, leading to uncontrollable accuracy. In this paper, we utilize the U-Net method to detect vortex positions accurately at the pixel level and propose an Automatic Correction Labeling (ACL) approach to optimize the acquisition of data sets for vortex localization in BECs. This approach addresses inaccuracies in the labeled vortex positions and improves the accuracy of vortex localization, especially the vortex core positions, while enhancing the tolerance for human mislabeling. The main process involves Rough Labeling [Formula: see text] Machine Learning [Formula: see text] Probability Region Search [Formula: see text] Data Relabeling [Formula: see text] Machine Learning again. The objective of ACL is to secure more accurate labeled data for model retraining. Through vortex localization experiments conducted in a two-dimensional Bose-Einstein condensate, our results establish the following: 1. Even under conditions of biased and missing manual annotations, U-Net can still accurately locate vortex positions; 2. Vortices exhibit certain regularities, and training U-Net with a small number of samples yields excellent predictive consequences; 3. The machine learning vortex locator based on the ACL method effectively corrects errors in manually annotated data, significantly improving the model's performance metrics, thus enhancing the precision and metrics of vortex localization. This substantial advancement in the application of machine learning in vortex localization provides an effective way for vortex dynamics localization. Furthermore, this method of obtaining more accurate positions of approximate human labels through machine learning offers new insights for machine learning in other types of image recognition problems.
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.