Nuclear liquid-gas phase transition with machine learning

Abstract

Machine-learning techniques have shown their capability for studying phase transitions in condensed matter physics. Here, we employ 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±0.04MeV is consistent with that obtained by the traditional caloric curve method. Our study explores the paradigm of combining machine-learning techniques with heavy-ion experimental data, and it is also instructive for studying the phase transition of other uncontrollable systems, such as QCD matter.