skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: An equation-of-state-meter of quantum chromodynamics transition from deep learning

Abstract

A primordial state of matter consisting of free quarks and gluons that existed in the early universe a few microseconds after the Big Bang is also expected to form in high-energy heavy-ion collisions. Determining the equation of state (EoS) of such a primordial matter is the ultimate goal of high-energy heavy-ion experiments. Here we use supervised learning with a deep convolutional neural network to identify the EoS employed in the relativistic hydrodynamic simulations of heavy ion collisions. High-level correlations of particle spectra in transverse momentum and azimuthal angle learned by the network act as an effective EoS-meter in deciphering the nature of the phase transition in quantum chromodynamics. Finally, such EoS-meter is model-independent and insensitive to other simulation inputs including the initial conditions for hydrodynamic simulations.

Authors:
ORCiD logo [1]; ORCiD logo [2];  [3]; ORCiD logo [4];  [4]; ORCiD logo [5]
  1. Frankfurt Inst. for Advanced Studies (FIAS), Frankfurt (Germany); Univ. of California, Berkeley, CA (United States). Dept. of Physics; Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Nuclear Science Division
  2. Frankfurt Inst. for Advanced Studies (FIAS), Frankfurt (Germany); Goethe Univ., Frankfurt (Germany). Inst. fur Theoretische Physik
  3. Frankfurt Inst. for Advanced Studies (FIAS), Frankfurt (Germany)
  4. Frankfurt Inst. for Advanced Studies (FIAS), Frankfurt (Germany); Goethe Univ., Frankfurt (Germany). Inst. fur Theoretische Physik; GSI-Helmholtzzentrum fur Schwerionenforschung, Darmstadt (Germany)
  5. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Nuclear Science Division; Central China Normal Univ., Wuhan (China). Key Lab. of Quark and Lepton Physics (MOE) and Inst. of Particle Physics
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC); National Science Foundation (NSF); National Natural Science Foundation of China (NNSFC); Helmholtz Association
OSTI Identifier:
1433129
Grant/Contract Number:  
AC02-05CH11231; ACI-1550228; 11521064; 2014DFG02050; 2015CB856902
Resource Type:
Accepted Manuscript
Journal Name:
Nature Communications
Additional Journal Information:
Journal Volume: 9; Journal Issue: 1; Journal ID: ISSN 2041-1723
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS; 71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS

Citation Formats

Pang, Long-Gang, Zhou, Kai, Su, Nan, Petersen, Hannah, Stocker, Horst, and Wang, Xin-Nian. An equation-of-state-meter of quantum chromodynamics transition from deep learning. United States: N. p., 2018. Web. doi:10.1038/s41467-017-02726-3.
Pang, Long-Gang, Zhou, Kai, Su, Nan, Petersen, Hannah, Stocker, Horst, & Wang, Xin-Nian. An equation-of-state-meter of quantum chromodynamics transition from deep learning. United States. doi:10.1038/s41467-017-02726-3.
Pang, Long-Gang, Zhou, Kai, Su, Nan, Petersen, Hannah, Stocker, Horst, and Wang, Xin-Nian. Mon . "An equation-of-state-meter of quantum chromodynamics transition from deep learning". United States. doi:10.1038/s41467-017-02726-3. https://www.osti.gov/servlets/purl/1433129.
@article{osti_1433129,
title = {An equation-of-state-meter of quantum chromodynamics transition from deep learning},
author = {Pang, Long-Gang and Zhou, Kai and Su, Nan and Petersen, Hannah and Stocker, Horst and Wang, Xin-Nian},
abstractNote = {A primordial state of matter consisting of free quarks and gluons that existed in the early universe a few microseconds after the Big Bang is also expected to form in high-energy heavy-ion collisions. Determining the equation of state (EoS) of such a primordial matter is the ultimate goal of high-energy heavy-ion experiments. Here we use supervised learning with a deep convolutional neural network to identify the EoS employed in the relativistic hydrodynamic simulations of heavy ion collisions. High-level correlations of particle spectra in transverse momentum and azimuthal angle learned by the network act as an effective EoS-meter in deciphering the nature of the phase transition in quantum chromodynamics. Finally, such EoS-meter is model-independent and insensitive to other simulation inputs including the initial conditions for hydrodynamic simulations.},
doi = {10.1038/s41467-017-02726-3},
journal = {Nature Communications},
number = 1,
volume = 9,
place = {United States},
year = {2018},
month = {1}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 7 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

First Results from Pb+Pb Collisions at the LHC
journal, November 2012


Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

QCD equation of state and hadron resonance gas
journal, June 2010


Hydrodynamical evolution of dissipative QGP fluid
journal, November 2006


Machine learning quantum phases of matter beyond the fermion sign problem
journal, August 2017


Explaining Classifications For Individual Instances
journal, May 2008

  • Robnik-Sikonja, M.; Kononenko, I.
  • IEEE Transactions on Knowledge and Data Engineering, Vol. 20, Issue 5
  • DOI: 10.1109/TKDE.2007.190734

Determination of the W W polarization fractions in p p W ± W ± j j using a deep machine learning technique
journal, May 2016


Challenges in QCD matter physics --The scientific programme of the Compressed Baryonic Matter experiment at FAIR
journal, March 2017


High energy heavy ion collisions—probing the equation of state of highly excited hardronic matter
journal, May 1986


Hydrodynamical description of 200 A GeV/ c S+Au collisions: Hadron and electromagnetic spectra
journal, January 1997

  • Sollfrank, Josef; Huovinen, Pasi; Kataja, Markku
  • Physical Review C, Vol. 55, Issue 1
  • DOI: 10.1103/PhysRevC.55.392

Enhanced Higgs Boson to τ + τ Search with Deep Learning
journal, March 2015


Nuclear charge radii: density functional theory meets Bayesian neural networks
journal, October 2016

  • Utama, R.; Chen, Wei-Chia; Piekarewicz, J.
  • Journal of Physics G: Nuclear and Particle Physics, Vol. 43, Issue 11
  • DOI: 10.1088/0954-3899/43/11/114002

Effects of initial flow velocity fluctuation in event-by-event (3+1)D hydrodynamics
journal, August 2012


On Information and Sufficiency
journal, March 1951

  • Kullback, S.; Leibler, R. A.
  • The Annals of Mathematical Statistics, Vol. 22, Issue 1
  • DOI: 10.1214/aoms/1177729694

Event-by-Event Anisotropic Flow in Heavy-ion Collisions from Combined Yang-Mills and Viscous Fluid Dynamics
journal, January 2013


Anisotropic Hydrodynamics: Three Lectures
journal, January 2014


New Developments in Relativistic Viscous Hydrodynamics
journal, January 2010


Constraining the Equation of State of Superhadronic Matter from Heavy-Ion Collisions
journal, May 2015


Learning thermodynamics with Boltzmann machines
journal, October 2016


The phase diagram of dense QCD
journal, December 2010


Applying Bayesian parameter estimation to relativistic heavy-ion collisions: Simultaneous characterization of the initial state and quark-gluon plasma medium
journal, August 2016


Conformal relativistic viscous hydrodynamics: Applications to RHIC results at s NN = 200 GeV
journal, September 2008


Searching for exotic particles in high-energy physics with deep learning
journal, July 2014

  • Baldi, P.; Sadowski, P.; Whiteson, D.
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms5308

Analytical and numerical Gubser solutions of the second-order hydrodynamics
journal, April 2015


Deep learning in neural networks: An overview
journal, January 2015


Hydrodynamic Modeling of Heavy-Ion Collisions
journal, April 2013

  • Gale, Charles; Jeon, Sangyong; Schenke, BjÖRn
  • International Journal of Modern Physics A, Vol. 28, Issue 11
  • DOI: 10.1142/S0217751X13400113

Multiphase transport model for relativistic heavy ion collisions
journal, December 2005


Solving the quantum many-body problem with artificial neural networks
journal, February 2017


Parton shower uncertainties in jet substructure analyses with deep neural networks
journal, January 2017


Machine learning phases of matter
journal, February 2017

  • Carrasquilla, Juan; Melko, Roger G.
  • Nature Physics, Vol. 13, Issue 5
  • DOI: 10.1038/nphys4035

The iEBE-VISHNU code package for relativistic heavy-ion collisions
journal, February 2016


Collective flow signals the quark–gluon plasma
journal, March 2005


New angles on energy correlation functions
journal, December 2016

  • Moult, Ian; Necib, Lina; Thaler, Jesse
  • Journal of High Energy Physics, Vol. 2016, Issue 12
  • DOI: 10.1007/JHEP12(2016)153

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
conference, December 2015

  • He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • DOI: 10.1109/ICCV.2015.123

    Works referencing / citing this record:

    High energy heavy ion collisions—probing the equation of state of highly excited hardronic matter
    journal, May 1986


    The iEBE-VISHNU code package for relativistic heavy-ion collisions
    journal, February 2016


    Deep learning in neural networks: An overview
    journal, January 2015


    Collective flow signals the quark–gluon plasma
    journal, March 2005


    QCD equation of state and hadron resonance gas
    journal, June 2010


    Deep learning
    journal, May 2015

    • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
    • Nature, Vol. 521, Issue 7553
    • DOI: 10.1038/nature14539

    Searching for exotic particles in high-energy physics with deep learning
    journal, July 2014

    • Baldi, P.; Sadowski, P.; Whiteson, D.
    • Nature Communications, Vol. 5, Issue 1
    • DOI: 10.1038/ncomms5308

    Machine learning phases of matter
    journal, February 2017

    • Carrasquilla, Juan; Melko, Roger G.
    • Nature Physics, Vol. 13, Issue 5
    • DOI: 10.1038/nphys4035

    Machine learning quantum phases of matter beyond the fermion sign problem
    journal, August 2017


    The phase diagram of dense QCD
    journal, December 2010


    Nuclear charge radii: density functional theory meets Bayesian neural networks
    journal, October 2016

    • Utama, R.; Chen, Wei-Chia; Piekarewicz, J.
    • Journal of Physics G: Nuclear and Particle Physics, Vol. 43, Issue 11
    • DOI: 10.1088/0954-3899/43/11/114002

    Hydrodynamical evolution of dissipative QGP fluid
    journal, November 2006


    Solving the quantum many-body problem with artificial neural networks
    journal, February 2017


    Challenges in QCD matter physics --The scientific programme of the Compressed Baryonic Matter experiment at FAIR
    journal, March 2017


    First Results from Pb+Pb Collisions at the LHC
    journal, November 2012


    On Information and Sufficiency
    journal, March 1951

    • Kullback, S.; Leibler, R. A.
    • The Annals of Mathematical Statistics, Vol. 22, Issue 1
    • DOI: 10.1214/aoms/1177729694

    Quark jet versus gluon jet: fully-connected neural networks with high-level features
    journal, June 2019

    • Luo, Hui; Luo, Ming-Xing; Wang, Kai
    • Science China Physics, Mechanics & Astronomy, Vol. 62, Issue 9
    • DOI: 10.1007/s11433-019-9390-8

    Quark jet versus gluon jet: fully-connected neural networks with high-level features
    journal, June 2019

    • Luo, Hui; Luo, Ming-Xing; Wang, Kai
    • Science China Physics, Mechanics & Astronomy, Vol. 62, Issue 9
    • DOI: 10.1007/s11433-019-9390-8