Eur. Phys. J. C (2020) 80: 516
https://doi.org/10.1140/epjc/s10052-020-8030-7

Regular Article - Theoretical Physics

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

¹ Frankfurt Institute for Advanced Studies, Giersch Science Center, 60438, Frankfurt am Main, Germany
² Institut für Theoretische Physik, Goethe Universität Frankfurt, 60438, Frankfurt am Main, Germany
³ Department of Physics, Nanjing University, Nanjing, 210093, China
⁴ Department of Physics and Technology, University of Bergen, 5007, Bergen, Norway
⁵ Nuclear Science Division, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA
⁶ Physics Department, University of California, Berkeley, CA, 94720, USA
⁷ Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, Wuhan, 430079, China
⁸ Nanjing Proton Source Research and Design Center, Nanjing, 210093, China
⁹ Department of physics, Anhui Normal University, Wuhu, 241000, Anhui, China
¹⁰ GSI Helmholtzzentrum für Schwerionenforschung, 64291, Darmstadt, Germany

^* e-mail: zhou@fias.uni-frankfurt.de

Received: 17 February 2020
Accepted: 8 May 2020
Published online: 10 June 2020

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.