- Physical Review Journals
All JournalsPhysics Magazine

Physical Review C

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Deep learning approach for predicting multiple observables in Au+Au collisions at energies available at the BNL Relativistic Heavy Ion Collider

Jun-Qi Tao1,2,3,*, Xiang Fan1,†, Yang Liu1,‡, Yu Sha4,§, Kai Zhou4,5,∥, Hua Zheng6,¶, and Ben-Wei Zhang1,**

  • *Contact author: taojunqi@mails.ccnu.edu.cn
  • †Contact author: xfan@mails.ccnu.edu.cn
  • ‡Contact author: liuyang01@mails.ccnu.edu.cn
  • §Contact author: yusha@cuhk.edu.cn
  • ∥Contact author: zhoukai@cuhk.edu.cn
  • Contact author: zhengh@snnu.edu.cn
  • **Contact author: bwzhang@mail.ccnu.edu.cn
PDF

Phys. Rev. C 113, 064911 – Published 29 June, 2026

DOI: https://doi.org/10.1103/grkg-jm2z

Abstract

We present a data-driven deep learning framework for predicting multiple bulk observables in Au+Au collisions at energies available at the BNL Relativistic Heavy Ion Collider (RHIC). A single neural network is trained exclusively on experimental measurements of charged-particle pseudorapidity density distributions, transverse momentum spectra, and elliptic flow coefficients over a broad range of collision energies and centralities, without using simulation outputs as training targets. The network architecture is inspired by the stages of a heavy-ion collision, from the quark-gluon plasma to chemical and kinetic freeze-out, and employs locally connected hidden layers and a structured input design that encodes basic geometric and kinematic features of the system. We demonstrate that these physics-motivated choices significantly improve test performance compared to purely fully connected baselines. The trained model is then used to predict the above observables at energies available at the RHIC, and the results are further cross-checked against the energy dependence of the total charged-particle multiplicity per participant pair, as well as against a CLVisc hydrodynamic calculation with TRENTo initial conditions. Our findings indicate that such physics-guided neural networks can provide useful data-driven interpolation tools for RHIC observables in regions not currently covered by the available measurements and can support further phenomenological studies.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (64)

  1. X.-N. Wang and M. Gyulassy, hijing: A Monte Carlo model for multiple jet production in pp, pA, and AA collisions, Phys. Rev. D 44, 3501 (1991).
  2. T. Pierog, I. Karpenko, J. M. Katzy, E. Yatsenko, and K. Werner, EPOS LHC: Test of collective hadronization with data measured at the CERN Large Hadron Collider, Phys. Rev. C 92, 034906 (2015).
  3. Z.-W. Lin, C. M. Ko, B.-A. Li, B. Zhang, and S. Pal, Multiphase transport model for relativistic heavy ion collisions, Phys. Rev. C 72, 064901 (2005).
  4. B.-H. Sa, D.-M. Zhou, Y.-L. Yan, X.-M. Li, S.-Q. Feng, B.-G. Dong, and X. Cai, PACIAE 2.0: An updated parton and hadron cascade model (program) for the relativistic nuclear collisions, Comput. Phys. Commun. 183, 333 (2012).
  5. J. D. Bjorken, Highly relativistic nucleus-nucleus collisions: The central rapidity region, Phys. Rev. D 27, 140 (1983).
  6. P. F. Kolb, J. Sollfrank, and U. Heinz, Anisotropic transverse flow and the quark-hadron phase transition, Phys. Rev. C 62, 054909 (2000).
  7. K. Zhou, L. Wang, L.-G. Pang, and S. Shi, Exploring QCD matter in extreme conditions with machine learning, Prog. Part. Nucl. Phys. 135, 104084 (2024).
  8. W.-B. He, Y.-G. Ma, L.-G. Pang, H.-C. Song, and K. Zhou, High-energy nuclear physics meets machine learning, Nucl. Sci. Tech. 34, 88 (2023).
  9. L. de Oliveira, M. Paganini, and B. Nachman, Learning particle physics by example: Location-aware generative adversarial networks for physics synthesis, Computing Software Big Sci. 1, 4 (2017).
  10. J. Steinheimer, L.-G. Pang, K. Zhou, V. Koch, J. Randrup, and H. Stoecker, A machine learning study to identify spinodal clumping in high energy nuclear collisions, J. High Energy Phys. 12 (2019) 122.
  11. Y.-G. Huang, L.-G. Pang, X.-F. Luo, and X.-N. Wang, Probing criticality with deep learning in relativistic heavy-ion collisions, Phys. Lett. B 827, 137001 (2022).
  12. N. Mallick, S. Prasad, A. N. Mishra, R. Sahoo, and G. G. Barnaföldi, Deep learning predicted elliptic flow of identified particles in heavy-ion collisions at the RHIC and LHC energies, Phys. Rev. D 107, 094001 (2023).
  13. M. Omana Kuttan, J. Steinheimer, K. Zhou, A. Redelbach, and H. Stoecker, A fast centrality-meter for heavy-ion collisions at the CBM experiment, Phys. Lett. B 811, 135872 (2020).
  14. L.-G. Pang, K. Zhou, and X.-N. Wang, Interpretable deep learning for nuclear deformation in heavy ion collisions, arXiv:1906.06429.
  15. T. Mengel, P. Steffanic, C. Hughes, A. C. O. da Silva, and C. Nattrass, Interpretable machine learning methods applied to jet background subtraction in heavy-ion collisions, Phys. Rev. C 108, L021901 (2023).
  16. R. Guo, Y. Li, and B. Chen, Machine Learning Approach to Analyze the Heavy Quark Diffusion Coefficient in Relativistic Heavy Ion Collisions, Entropy 25, 1563 (2023).
  17. J.-A. Sun, L. Yan, C. Gale, and S. Jeon, End-to-end generative diffusion model for heavy-ion collisions, Phys. Rev. C, 112, L051903 (2025).
  18. M. Paganini, L. de Oliveira, and B. Nachman, Accelerating science with generative adversarial networks: An application to 3D particle showers in multilayer calorimeters, Phys. Rev. Lett. 120, 042003 (2018).
  19. Q.-K. Sun, Y. Zhang, Z.-R. Hao, H.-W. Wang, G.-T. Fan, H.-H. Xu, L.-X. Liu, S. Jin, Y.-X. Yang, K.-J. Chen, et al., Enhancing reliability in photonuclear cross-section fitting with Bayesian neural networks, Nucl. Sci. Tech. 36, 52 (2025).
  20. Z.-P. Gao, Y.-J. Wang, H.-L. Lü, Q.-F. Li, C.-W. Shen, and L. Liu, Machine learning the nuclear mass, Nucl. Sci. Tech. 32, 109 (2021).
  21. Y.-Y. Cao, J.-Y. Guo, and B. Zhou, Predictions of nuclear charge radii based on the convolutional neural network, Nucl. Sci. Tech. 34, 152 (2023).
  22. M. R. Mumpower, T. M. Sprouse, A. E. Lovell, and A. T. Mohan, Physically interpretable machine learning for nuclear masses, Phys. Rev. C 106, L021301 (2022).
  23. Y.-L. Du, K. Zhou, J. Steinheimer, L.-G. Pang, A. Motornenko, H.-S. Zong, X.-N. Wang, and H. Stöcker, Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning, Eur. Phys. J. C 80, 516 (2020).
  24. M. O. Kuttan, K. Zhou, J. Steinheimer, A. Redelbach, and H. Stocker, An equation-of-state-meter for CBM using PointNet, J. High Energy Phys. 10 (2021) 184.
  25. Y.-S. Zhao, L. Wang, K. Zhou, and X.-G. Huang, Detecting the chiral magnetic effect via deep learning, Phys. Rev. C 106, L051901 (2022).
  26. M. Omana Kuttan, J. Steinheimer, K. Zhou, and H. Stoecker, QCD equation of state of dense nuclear matter from a Bayesian analysis of heavy-ion collision data, Phys. Rev. Lett. 131, 202303 (2023).
  27. B. B. Back et al. (PHOBOS Collaboration), Significance of the fragmentation region in ultrarelativistic heavy-ion collisions, Phys. Rev. Lett. 91, 052303 (2003).
  28. B. B. Back et al. (PHOBOS Collaboration), Charged-particle pseudorapidity distributions in Au + Au collisions at sNN=62.4GeV, Phys. Rev. C 74, 021901 (2006).
  29. B. Alver et al. (PHOBOS Collaboration), Charged-particle multiplicity and pseudorapidity distributions measured with the PHOBOS detector in Au+Au, Cu+Cu, d+Au, and p+p collisions at ultrarelativistic energies, Phys. Rev. C 83, 024913 (2011).
  30. L. Adamczyk et al. (STAR Collaboration), Inclusive charged hadron elliptic flow in Au + Au collisions at sNN=7.7−39GeV, Phys. Rev. C 86, 054908 (2012).
  31. C. Adler et al. (STAR Collaboration), Elliptic flow from two- and four-particle correlations in Au + Au collisions at sNN=130GeV, Phys. Rev. C 66, 034904 (2002).
  32. A. Adare et al. (PHENIX Collaboration), Elliptic and hexadecapole flow of charged hadrons in Au+Au collisions at sNN=200GeV, Phys. Rev. Lett. 105, 062301 (2010).
  33. B. I. Abelev et al. (STAR Collaboration), Identified particle production, azimuthal anisotropy, and interferometry measurements in Au+Au collisions at sNN=9.2GeV, Phys. Rev. C 81, 024911 (2010).
  34. J. Adam et al. (STAR Collaboration), Bulk properties of the system formed in Au+Au collisions at sNN=14.5 GeV at the BNL STAR detector, Phys. Rev. C 101, 024905 (2020).
  35. B. I. Abelev et al. (STAR Collaboration), Mass, quark-number, and sNN dependence of the second and fourth flow harmonics in ultrarelativistic nucleus-nucleus collisions, Phys. Rev. C 75, 054906 (2007).
  36. L. Adamczyk et al. (STAR Collaboration), Beam energy dependence of jet-quenching effects in Au+Au collisions at sNN=7.7, 11.5, 14.5, 19.6, 27, 39, and 62.4 GeV, Phys. Rev. Lett. 121, 032301 (2018).
  37. J. Adams et al. (STAR Collaboration), Transverse-momentum and collision-energy dependence of high-pT hadron suppression in Au+Au collisions at ultrarelativistic energies, Phys. Rev. Lett. 91, 172302 (2003).
  38. C. Adler et al. (STAR Collaboration), Centrality dependence of high-pT hadron suppression in Au+Au collisions at sNN=130GeV, Phys. Rev. Lett. 89, 202301 (2002).
  39. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, et al., PyTorch: An imperative style, high-performance deep learning library, arXiv:1912.01703.
  40. A. L. Maas, A. Y. Hannun, and A. Y. Ng, in Proceedings of the International Conference on Machine Learning (Atlanta, GA, 2013), Vol. 30, p. 3–8.
  41. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  42. J. L. Klay et al. (E895 Collaboration), Charged pion production in 2A to 8AGeV central Au+Au collisions, Phys. Rev. C 68, 054905 (2003).
  43. L. Ahle et al. (E-802 Collaboration), Particle production at high baryon density in central Au + Au reactions at 11.6A GeV/c, Phys. Rev. C 57, R466 (1998).
  44. S. V. Afanasiev et al. (NA49 Collaboration), Energy dependence of pion and kaon production in central Pb + Pb collisions, Phys. Rev. C 66, 054902 (2002).
  45. M. Abreu et al. (NA50 Collaboration), Scaling of charged particle multiplicity in Pb–Pb collisions at SPS energies, Phys. Lett. B 530, 43 (2002).
  46. E. Abbas et al. (ALICE Collaboration), Centrality dependence of the pseudorapidity density distribution for charged particles in Pb–Pb collisions at sNN=2.76TeV, Phys. Lett. B 726, 610 (2013).
  47. J. Adam et al. (ALICE Collaboration), Centrality dependence of the pseudorapidity density distribution for charged particles in Pb–Pb collisions at sNN=5.02TeV, Phys. Lett. B 772, 567 (2017).
  48. S. Acharya et al. (ALICE Collaboration), Centrality and pseudorapidity dependence of the charged-particle multiplicity density in Xe–Xe collisions at sNN=5.44TeV, Phys. Lett. B 790, 35 (2019).
  49. Y. Gao, H. Zheng, L. L. Zhu, and A. Bonasera, Description of charged particle pseudorapidity distributions in Pb + Pb collisions with Tsallis thermodynamics, Eur. Phys. J. A 53, 197 (2017).
  50. J. Q. Tao, M. Wang, H. Zheng, W. C. Zhang, L. L. Zhu, and A. Bonasera, Pseudorapidity distributions of charged particles in pp(p¯), p(d)A and AA collisions using Tsallis thermodynamics, J. Phys. G: Nucl. Part. Phys. 48, 105102 (2021).
  51. J.-Q. Tao, H.-B. He, H. Zheng, W.-C. Zhang, X.-Q. Liu, L.-L. Zhu, and A. Bonasera, Pseudo-rapidity distributions of charged particles in asymmetric collisions using Tsallis thermodynamics, Nucl. Sci. Tech. 34, 172 (2023).
  52. M. Wang, J.-Q. Tao, H. Zheng, W.-C. Zhang, L.-L. Zhu, and A. Bonasera, Number-of-constituent-quark scaling of elliptic flow: A quantitative study, Nucl. Sci. Tech. 33, 37 (2022).
  53. L.-G. Pang, H. Petersen, and X.-N. Wang, Pseudorapidity distribution and decorrelation of anisotropic flow within the open-computing-language implementation CLVisc hydrodynamics, Phys. Rev. C 97, 064918 (2018).
  54. X.-Y. Wu, G.-Y. Qin, L.-G. Pang, and X.-N. Wang, (3+1)-D viscous hydrodynamics at finite net baryon density: Identified particle spectra, anisotropic flows, and flow fluctuations across energies relevant to the beam-energy scan at RHIC, Phys. Rev. C 105, 034909 (2022).
  55. J. S. Moreland, J. E. Bernhard, and S. A. Bass, Alternative ansatz to wounded nucleon and binary collision scaling in high-energy nuclear collisions, Phys. Rev. C 92, 011901 (2015).
  56. Z.-F. Jiang, X.-Y. Wu, S. Cao, and B.-W. Zhang, Hyperon polarization and its relation with directed flow in high-energy nuclear collisions, Phys. Rev. C 108, 064904 (2023).
  57. Z.-F. Jiang, X.-Y. Wu, S. Cao, and B.-W. Zhang, Directed flow and global polarization in Au+Au collisions across energies covered by the beam energy scan at RHIC, Phys. Rev. C 107, 034904 (2023).
  58. A. Donnachie and P. Landshoff, Total cross sections, Phys. Lett. B 296, 227 (1992).
  59. A. Adare et al. (PHENIX Collaboration), Transverse energy production and charged-particle multiplicity at midrapidity in various systems from SNN=7.7 to 200 GeV, Phys. Rev. C 93, 024901 (2016).
  60. G. Aad et al. (ATLAS Collaboration), Measurement of the centrality dependence of the charged particle pseudorapidity distribution in lead–lead collisions at sNN=2.76TeV with the ATLAS detector, Phys. Lett. B 710, 363 (2012).
  61. B. Abelev et al. (ALICE Collaboration), Pseudorapidity density of charged particles in p+Pb collisions at SNN=5.02TeV, Phys. Rev. Lett. 110, 032301 (2013).
  62. B. Abelev et al. (ALICE Collaboration), Measurement of inelastic, single- and double-diffraction cross sections in proton–proton collisions at the LHC with ALICE, Eur. Phys. J. C 73, 2456 (2013).
  63. J. Zhu, X.-Y. Wu, and G.-Y. Qin, Anisotropic flow, flow fluctuation, and flow decorrelation in relativistic heavy-ion collisions: The roles of sub-nucleon structure and shear viscosity, Chin. Phys. C 49, 044103 (2025).
  64. A. Bazavov et al. (HotQCD Collaboration), Equation of state in (2+1)-flavor QCD, Phys. Rev. D 90, 094503 (2014).

Outline

Information

Phys. Rev. C 113, 064911– Published 29 June, 2026
  • Received 6 January 2026
  • Revised 18 March 2026
  • Accepted 9 June 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation