Machine learning classification of two-dimensional vortex configurations

TL;DR

This paper demonstrates that unsupervised machine learning can effectively classify vortex configurations in superfluid Bose-Einstein condensates, aiding the analysis of quantum turbulence data.

Contribution

It introduces a novel application of unsupervised machine learning for classifying vortex phases in 2D quantum turbulence.

Findings

Successful classification of vortex configurations

Identification of prominent vortex phases

Potential for automatic analysis of experimental data

Abstract

We consider computer generated configurations of quantised vortices in planar superfluid Bose-Einstein condensates. We show that unsupervised machine learning technology can successfully be used for classifying such vortex configurations to identify prominent vortex phases of matter. The machine learning approach could thus be applied for automatically classifying large data sets of vortex configurations obtainable by experiments on two-dimensional quantum turbulence.