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

TL;DR

This paper introduces a large, labeled dataset of Bose-Einstein condensate images with solitonic excitations, enabling machine learning applications in many-body physics research.

Contribution

It provides a comprehensive dataset with manual and ML-based labels, along with a physics-informed analysis framework for studying nonlinear many-body phenomena.

Findings

Over 16,000 experimental images included

Approximately 33% of images are manually labeled

Remaining images are automatically labeled using SolDet

Abstract

We establish a dataset of over $1.6\times10^4$ 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 OD 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.