Nuclear liquid-gas phase transition with machine learning

TL;DR

This paper demonstrates the use of machine learning, specifically unsupervised and combined methods, to identify the nuclear liquid-gas phase transition and determine its limiting temperature from experimental data.

Contribution

It introduces a novel approach combining supervised and unsupervised machine learning to analyze heavy-ion collision data for phase transition detection.

Findings

Limiting temperature of 9.24±0.04 MeV for nuclear liquid-gas transition

Machine learning effectively classifies phases directly from raw experimental data

Method aligns with traditional caloric curve results

Abstract

The machine-learning techniques have shown their capability for studying phase transitions in condensed matter physics. Here, we employ the machine-learning techniques to study the nuclear liquid-gas phase transition. We adopt an unsupervised learning and classify the liquid and gas phases of nuclei directly from the final state raw experimental data of heavy-ion reactions. Based on a confusion scheme which combines the supervised and unsupervised learning, we obtain the limiting temperature of the nuclear liquid-gas phase transition. Its value $9.24\pm0.04~\rm MeV$ is consistent with that obtained by the traditional caloric curve method. Our study explores the paradigm of combining the machine-learning techniques with heavy-ion experimental data, and it is also instructive for studying the phase transition of other uncontrollable systems, like QCD matter.