Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons

TL;DR

This paper presents SolDet, an open-source framework combining machine learning and physics-based analysis to identify, track, and classify multiple solitons in Bose-Einstein condensate images, improving feature detection in cold-atom experiments.

Contribution

The paper introduces a novel framework integrating ML object detection with physics-informed classification for solitons, with an open-source implementation called SolDet.

Findings

Successfully identifies and tracks multiple solitons in BEC images.

Provides a physics-informed classifier for soliton categorization.

Offers a quantitative quality metric for soliton likelihood.

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.