Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning

Abstract

Using deep convolutional neural network (CNN), the nature of the QCD transition can be identified from the final-state pion spectra from hybrid model simulations of heavy-ion collisions that combines a viscous hydrodynamic model with a hadronic cascade "after-burner". Two different types of equations of state (EoS) of the medium are used in the hydrodynamic evolution. The resulting spectra in transverse momentum and azimuthal angle are used as the input data to train the neural network to distinguish different EoS. Different scenarios for the input data are studied and compared in a systematic way. A clear hierarchy is observed in the prediction accuracy when using the event-by-event, cascade-coarse-grained and event-fine-averaged spectra as input for the network, which are about 80%, 90% and 99%, respectively. A comparison with the prediction performance by deep neural network (DNN) with only the normalized pion transverse momentum spectra is also made. High-level features of pion spectra captured by a carefully-trained neural network were found to be able to distinguish the nature of the QCD transition even in a simulation scenario which is close to the experiments.

arXiv comment16 pages, 21 figures. Updated version for the publication in Eur. Phys. J. C

References in corpus (66)

• Deep Learning in Neural Networks: An Overview
• Experimental and Theoretical Challenges in the Search for the Quark Gluon Plasma: The STAR Collaboration's Critical Assessment of the Evidence from RHIC Collisions
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Microscopic Models for Ultrarelativistic Heavy Ion Collisions
• The order of the quantum chromodynamics transition predicted by the standard model of particle physics
• Relativistic Hadron-Hadron Collisions in the Ultra-Relativistic Quantum Molecular Dynamics Model (UrQMD)
• A Multi-Phase Transport Model for Relativistic Heavy Ion Collisions
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Signatures of the Tricritical Point in QCD
• The QCD transition temperature: results with physical masses in the continuum limit
• Conformal Relativistic Viscous Hydrodynamics: Applications to RHIC results at sqrt(s_NN) = 200 GeV
• Elliptic and triangular flow in event-by-event (3+1)D viscous hydrodynamics
• Non-Gaussian fluctuations near the QCD critical point
• QCD Equation of State and Hadron Resonance Gas
• New Developments in Relativistic Viscous Hydrodynamics
• The Phase Structure of the Polyakov--Quark-Meson Model
• Causal viscous hydrodynamics in 2+1 dimensions for relativistic heavy-ion collisions
• Applying Bayesian parameter estimation to relativistic heavy-ion collisions: simultaneous characterization of the initial state and quark-gluon plasma medium
• Phase diagrams in the three-flavor Nambu--Jona-Lasinio model with the Polyakov loop
• First Results from Pb+Pb collisions at the LHC
• Collective Flow signals the Quark Gluon Plasma
• Challenges in QCD matter physics - The Compressed Baryonic Matter experiment at FAIR
• Learning Thermodynamics with Boltzmann Machines
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Hydrodynamics near the QCD Phase Transition: Looking for the Longest-Lived Fireball
• Color Glass Condensate at the LHC: hadron multiplicities in $pp$, $pA$ and $AA$ collisions
• Influence of the shear viscosity of the quark-gluon plasma on elliptic flow in ultrarelativistic heavy-ion collisions
• Effects of initial flow velocity fluctuation in event-by-event (3+1)D hydrodynamics
• Inhomogeneous phases in the Nambu-Jona-Lasino and quark-meson model
• Hydrodynamical Description of 200 A GeV/c S+Au Collisions: Hadron and Electromagnetic Spectra
• Phase diagram and critical endpoint for strongly-interacting quarks
• GLISSANDO: GLauber Initial-State Simulation AND mOre
• Improved version of the PHOBOS Glauber Monte Carlo
• Antiflow of Nucleons at the Softest Point of the EoS
• Constraining the Eq. of State of Super-Hadronic Matter from Heavy-Ion Collisions
• The onset of classical QCD dynamics in relativistic heavy ion collisions
• New Angles on Energy Correlation Functions
• 2+1 Flavor Polyakov--Nambu--Jona-Lasinio Model at Finite Temperature and Nonzero Chemical Potential
• The renormalization group and quark number fluctuations in the Polyakov loop extended quark-meson model at finite baryon density
• Propagators and phase structure of Nf=2 and Nf=2+1 QCD
• Anisotropic Hydrodynamics for Rapidly Expanding Systems
• Nuclear charge radii: Density functional theory meets Bayesian neural networks
• Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks
• The Phase Transition to the Quark-Gluon Plasma and Its Effect on Hydrodynamic Flow
• Spinodal amplification of density fluctuations in fluid-dynamical simulations of relativistic nuclear collisions
• Regressive and generative neural networks for scalar field theory
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Thermodynamics and critical behavior in the Nambu-Jona-Lasinio model of QCD
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• Machine Learning Spatial Geometry from Entanglement Features
• Analytical and numerical Gubser solutions of the second-order hydrodynamics
• Early collective expansion: Relativistic hydrodynamics and the transport properties of QCD matter
• Locate QCD Critical End Point in a Continuum Model Study
• Methodology study of machine learning for the neutron star equation of state
• Machine learning action parameters in lattice quantum chromodynamics
• The QCD critical end point in the PNJL model
• Influence of the hadronic phase on observables in ultrarelativistic heavy ion collisions
• Quarkonium Physics at a Fixed-Target Experiment using the LHC Beams
• Thermalization of gluons with Bose-Einstein condensation
• Application of neural network to sign problem via path optimization method
• Determination of the $WW$ polarization fractions in $pp\to W^{\pm }{W}^{\pm }jj$ using a deep machine learning technique
• Continuum study on QCD phase diagram through an OPE-modified gluon propagator
• Electromagnetic probes of a pure-glue initial state in nucleus-nucleus collisions at energies available at the CERN Large Hadron Collider
• Glueballs amass at RHIC and LHC Colliders! - The early quarkless 1st order phase transition at $T=270$ MeV - from pure Yang-Mills glue plasma to GlueBall-Hagedorn states
• Discussions on the crossover property within the Nambu--Jona-Lasinio model
• Kinetic description of Bose-Einstein condensation with test particle simulations

Cited by in corpus (40)

• Machine Learning in Nuclear Physics
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Machine learning the nuclear mass
• Exploring QCD matter in extreme conditions with Machine Learning
• Nuclear liquid-gas phase transition with machine learning
• 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
• QCD Equation of State of Dense Nuclear Matter from a Bayesian Analysis of Heavy-Ion Collision Data
• Deep learning stochastic processes with QCD phase transition
• Unsupervised Outlier Detection in Heavy-Ion Collisions
• A fast centrality-meter for heavy-ion collisions at the CBM experiment
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• Machine-learning-based identification for initial clustering structure in relativistic heavy-ion collisions
• Application of machine learning in the determination of impact parameter in the ${}^{132}$Sn+${}^{124}$Sn system
• Application of artificial intelligence in the determination of impact parameter in heavy-ion collisions at intermediate energies
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Explainable machine learning of the underlying physics of high-energy particle collisions
• An equation-of-state-meter for CBM using PointNet
• Fourier-Flow model generating Feynman paths
• Detecting Chiral Magnetic Effect via Deep Learning
• Dilepton Signature of a First-Order Phase Transition
• Directed flow of charged particles within idealized viscous hydrodynamics at energies available at the BNL Relativistic Heavy Ion Collider and at the CERN Large Hadron Collider
• Probing criticality with deep learning in relativistic heavy-ion collisions
• Enhanced yield ratio of light nuclei in heavy ion collisions with a first-order QCD phase transition
• Determination of impact parameter in high-energy heavy-ion collisions via deep learning
• Machine learning phase transitions of the three-dimensional Ising universality class
• Classification of Equation of State in Relativistic Heavy-Ion Collisions Using Deep Learning
• Distinguishing $W^{\prime }$ Signals at Hadron Colliders Using Neural Networks
• Estimation of collision centrality in terms of the number of participating nucleons in heavy-ion collisions using deep learning
• Ultra fast, event-by-event heavy-ion simulations for next generation experiments
• Neural Unfolding of the Chiral Magnetic Effect in Heavy-Ion Collisions
• Toward a foundation model for heavy-ion collision experiments based on point-cloud diffusion
• Finding signatures of the nuclear symmetry energy in heavy-ion collisions with deep learning
• Cosmology from Strong Interactions
• Jet momentum reconstruction in the QGP background with machine learning
• From Cosmic Matter to the Laboratory
• Learning Langevin dynamics with QCD phase transition
• A deep learning approach for predicting multiple observables in Au+Au collisions at RHIC
• Deep learning for jet modification in the presence of the QGP background