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

arXiv: https://arxiv.org/abs/2101.05404 · HTML: https://mlsanity.com/paper/2101.05404/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 50 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 7 of 7)

- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Orbital Graph Convolutional Neural Network for Material Property Prediction](https://mlsanity.com/paper/2008.06415/) (2020)
- [A Convolutional Neural Network Neutrino Event Classifier](https://mlsanity.com/paper/1604.01444/) (2016)
- [Image-Based Jet Analysis](https://mlsanity.com/paper/2012.09719/) (2020)
- [Single-exposure absorption imaging of ultracold atoms using deep learning](https://mlsanity.com/paper/2003.01643/) (2020)

## Built on by (most cited first, 5 of 5)

- [Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons](https://mlsanity.com/paper/2111.04881/) (2021)
- [Dark solitons in Bose-Einstein condensates: a dataset for many-body physics research](https://mlsanity.com/paper/2205.09114/) (2022)
- [Measuring the rogue wave pattern triggered from Gaussian perturbations by deep learning](https://mlsanity.com/paper/2109.08909/) (2021)
- [Can machine learning for quantum-gas experiments be explainable?](https://mlsanity.com/paper/2605.18689/) (2026)
- [Q-GAIN: A Python Package for Machine Learning and Physically Informed Analysis Applications](https://mlsanity.com/paper/2607.02413/) (2026)

## Abstract (arXiv)

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.