Dark solitons in Bose–Einstein condensates: a dataset for many-body physics research

Published

December 21, 2022

Author(s)

Amilson R. Fritsch, Shangjie Guo, Sophia Koh, Ian Spielman, Justyna Zwolak

Abstract

We establish a dataset of over 1.6 x 10^4 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.

Citation

Machine Learning: Science and Technology

Volume

3

Issue

4

Pub Type

Journals

Download Paper

https://doi.org/10.1088/2632-2153/ac9454

Local Download

Keywords

dataset, dark solitons, machine learning, supervised learning

Citation

Fritsch, A. , Guo, S. , Koh, S. , Spielman, I. and Zwolak, J. (2022), Dark solitons in Bose–Einstein condensates: a dataset for many-body physics research, Machine Learning: Science and Technology, [online], https://doi.org/10.1088/2632-2153/ac9454, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=934213 (Accessed October 10, 2025)