01635nas a2200181 4500008004100000245010500041210006900146260001500215300001200230490000600242520106000248100001801308700002001326700002501346700002101371700002401392856003701416 2022 eng d00aCombining machine learning with physics: A framework for tracking and sorting multiple dark solitons0 aCombining machine learning with physics A framework for tracking c06/01/2022 a023163 0 v43 a
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.
1 aGuo, Shangjie1 aKoh, Sophia, M.1 aFritsch, Amilson, R.1 aSpielman, I., B.1 aZwolak, Justyna, P. uhttps://arxiv.org/abs/2111.0488101358nas a2200157 4500008004100000245008900041210006900130260001500199520084100214100002501055700001801080700002001098700002101118700002401139856003701163 2022 eng d00aDark Solitons in Bose-Einstein Condensates: A Dataset for Many-body Physics Research0 aDark Solitons in BoseEinstein Condensates A Dataset for Manybody c05/17/20223 aWe establish a dataset of over 1.6×104 experimental images of Bose-Einstein condensates containing solitonic excitations to enable machine learning (ML) for many-body physics research. About 33 % of this dataset has manually assigned and carefully curated labels. The remainder is automatically labeled using SolDet -- an implementation of a physics-informed ML data analysis framework -- consisting of a convolutional-neural-network-based classifier and object detector as well as a statistically motivated physics-informed classifier and a quality metric. This technical note constitutes the definitive reference of the dataset, providing an opportunity for the data science community to develop more sophisticated analysis tools, to further understand nonlinear many-body physics, and even advance cold atom experiments.
1 aFritsch, Amilson, R.1 aGuo, Shangjie1 aKoh, Sophia, M.1 aSpielman, I., B.1 aZwolak, Justyna, P. uhttps://arxiv.org/abs/2205.0911401499nas a2200181 4500008004100000245008200041210006900123260001400192300001100206490000600217520094800223100001801171700002501189700002101214700002101235700002401256856003701280 2021 eng d00aMachine-learning enhanced dark soliton detection in Bose-Einstein condensates0 aMachinelearning enhanced dark soliton detection in BoseEinstein c6/17/2021 a0350200 v23 aMost 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 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 Bose-Einstein condensates (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.
1 aGuo, Shangjie1 aFritsch, Amilson, R.1 aGreenberg, Craig1 aSpielman, I., B.1 aZwolak, Justyna, P. uhttps://arxiv.org/abs/2101.05404