Identification of the melting line in the two-dimensional complex plasmas using an unsupervised machine learning method

TL;DR

This paper introduces an unsupervised machine learning approach using convolutional neural networks to identify the melting line in two-dimensional complex plasmas, matching results from traditional and supervised methods.

Contribution

It demonstrates the application of unsupervised CNNs to determine phase transitions in complex plasmas without labeled training data.

Findings

Unsupervised CNN accurately identifies the melting line.

Results agree with traditional hexatic order parameter analysis.

Method reduces reliance on labeled data for phase transition detection.

Abstract

Machine learning methods have been widely used in the investigations of the complex plasmas. In this paper, we demonstrate that the unsupervised convolutional neural network can be applied to obtain the melting line in the two-dimensional complex plasmas based on the Langevin dynamics simulation results. The training samples do not need to be labeled. The resulting melting line coincides with those obtained by the analysis of hexatic order parameter and supervised machine learning method.