Nuclear liquid-gas phase transition with machine learning

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 $9.24\pm 0.04\mathrm{MeV}$ 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.

arXiv comment9 pages, 8 figures, 1 table; Physical Review Research, in press (2020)

References in corpus (32)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Learning phase transitions by confusion
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Jet-Images -- Deep Learning Edition
• Deep-learning Top Taggers or The End of QCD?
• Identifying topological order through unsupervised machine learning
• Caloric curves and critical behavior in nuclei
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Machine Learning Phases of Strongly Correlated Fermions
• The liquid to vapor phase transition in excited nuclei
• Constraining Effective Field Theories with Machine Learning
• Limiting temperatures and the Equation of State of Nuclear Matter
• Application of Information Theory in Nuclear Liquid Gas Phase Transition
• Light nuclei production as a probe of the QCD phase diagram
• Shannon Information Entropy in Heavy-ion Collisions
• Regressive and generative neural networks for scalar field theory
• Critical Behavior in Light Nuclear Systems: Experimental Aspects
• Measuring the Temperature of Hot Nuclear Fragments
• Microscopic model approaches to fragmentation of nuclei and phase transitions in nuclear matter
• Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
• Liquid-Gas phase transition in nuclei
• Universal fluctuations in heavy-ion collisions in the Fermi energy domain
• A machine learning study to identify spinodal clumping in high energy nuclear collisions
• The Quantum Nature of a Nuclear Phase Transition
• Bimodality as a signal of Liquid-Gas phase transition in nuclei?
• Multiplicity Derivative: A new signature of first order phase transition in intermediate energy heavy ion collision
• Shear viscosity of neutron-rich nucleonic matter near its liquid-gas phase transition
• Thermal and transport properties in central heavy-ion reactions around a few hundred MeV/nucleon
• Finite-size scaling phenomenon of nuclear liquid--gas phase transition probes

Cited by in corpus (26)

• Machine Learning in Nuclear Physics
• Machine learning the nuclear mass
• Novel Bayesian neural network based approach for nuclear charge radii
• The QCD phase diagram and Beam Energy Scan physics: a theory overview
• Heavy quark potential in quark-gluon Plasma: Deep neural network meets lattice quantum chromodynamics
• Phase Transition Study meets Machine Learning
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• Reconstructing the neutron star equation of state from observational data via automatic differentiation
• Machine-learning-based identification for initial clustering structure in relativistic heavy-ion collisions
• Kinetic approach of light-nuclei production in intermediate-energy heavy-ion collisions
• Reconstructing spectral functions via automatic differentiation
• An equation-of-state-meter for CBM using PointNet
• Determining impact parameters of heavy-ion collisions at low-intermediate incident energies using deep learning with convolutional neural network
• Impact of fragment formation on shear viscosity in the nuclear liquid-gas phase transition region
• Probing criticality with deep learning in relativistic heavy-ion collisions
• A learning by confusion approach to characterize phase transitions
• Modeling Heavy-Ion Fusion Cross Section Data via a Novel Artificial Intelligence Approach
• Effect of initial-state geometric configurations on the nuclear liquid-gas phase transition
• Machine learning method for ${}^{12}$C event classification and reconstruction in the active target time-projection chamber
• Determination of impact parameter in high-energy heavy-ion collisions via deep learning
• Machine learning phase transitions of the three-dimensional Ising universality class
• A simple framework for contrastive learning phases of matter
• Temperature and density effects on the two-nucleon momentum correlation function from excited single nuclei
• Bayesian inference of nuclear incompressibility from collective flow in mid-central Au+Au collisions at 400--1500 MeV/nucleon
• Phase transitions and finite-size effects in integrable virial statistical models
• Machine learning that predicts well may not learn the correct physical descriptions of glassy systems