- 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 image reconstruction for background subtraction in heavy-ion collisions

Umar Sohail Qureshi1,2,3,* and Raghav Kunnawalkam Elayavalli3

  • *Contact author: uqureshi@cern.ch
PDF

Phys. Rev. C 112, 064906 – Published 9 December, 2025

DOI: https://doi.org/10.1103/dqnx-1fqk

Abstract

Jet reconstruction in an ultrarelativistic heavy-ion collision suffers from a notoriously large, fluctuating thermal background. Traditional background‐subtraction methods struggle to remove this soft background while preserving the jet's hard substructure. In this Letter, we present DeepSub, a machine-learning-based approach for full-event background‐subtraction. DeepSub utilizes a model based on Swin Transformer layers to denoise jet images and disentangle hard jets from the heavy-ion background. DeepSub significantly outperforms existing subtraction techniques by reproducing key jet observables such as jet pT and mass, and substructure observables such as girth and the energy correlation function, at the subpercent to percent level. As such, DeepSub paves the way for precision heavy-ion measurements in hitherto inaccessible kinematic regimes.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (78)

  1. Y. Mehtar-Tani, J. G. Milhano, and K. Tywoniuk, Jet physics in heavy-ion collisions, Int. J. Mod. Phys. A 28, 1340013 (2013).
  2. J. D. Bjorken, Energy Loss of Energetic Partons in Quark-Gluon Plasma: Possible Extinction of High pT Jets in Hadron-Hadron Collisions, Technical Report (FERMILAB, Batavia, 1982).
  3. D. d'Enterria, Jet quenching, Landolt-Bornstein 23, 471 (2010).
  4. A. Majumder and M. Van Leeuwen, The theory and phenomenology of perturbative QCD based jet quenching, Prog. Part. Nucl. Phys. 66, 41 (2011).
  5. G.-Y. Qin and X.-N. Wang, Jet quenching in high-energy heavy-ion collisions, Int. J. Mod. Phys. E 24, 1530014 (2015).
  6. K. Adcox et al. (PHENIX Collaboration), Suppression of hadrons with large transverse momentum in central Au + Au collisions at sNN = 130-GeV, Phys. Rev. Lett. 88, 022301 (2001).
  7. C. Adler et al. (STAR Collaboration), Centrality dependence of high pT hadron suppression in Au + Au collisions at sNN = 130-GeV, Phys. Rev. Lett. 89, 202301 (2002).
  8. K. Aamodt et al. (ALICE Collaboration), Suppression of charged particle production at large transverse momentum in central Pb-Pb collisions at sNN= 2.76 TeV, Phys. Lett. B 696, 30 (2011).
  9. S. S. Adler et al. (PHENIX Collaboration), Suppressed π0 production at large transverse momentum in central Au + Au collisions at SNN = 200 GeV, Phys. Rev. Lett. 91, 072301 (2003).
  10. 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).
  11. C. Adler et al. (STAR Collaboration), Disappearance of back-to-back high pT hadron correlations in central Au + Au collisions at sNN = 200-GeV, Phys. Rev. Lett. 90, 082302 (2003).
  12. K. Aamodt et al. (ALICE Collaboration), Particle-yield modification in jet-like azimuthal di-hadron correlations in Pb-Pb collisions at sNN=2.76 TeV, Phys. Rev. Lett. 108, 092301 (2012).
  13. S. Chatrchyan et al. (CMS Collaboration), Study of high-pT charged particle suppression in PbPb compared to pp collisions at sNN=2.76 TeV, Eur. Phys. J. C 72, 1945 (2012).
  14. G. Aad et al. (ATLAS Collaboration), Measurement of charged-particle spectra in Pb + Pb collisions at sNN=2.76 TeV with the ATLAS detector at the LHC, J. High Energy Phys. 09 (2015) 050.
  15. V. Khachatryan et al. (CMS Collaboration), Charged-particle nuclear modification factors in PbPb and pPb collisions at sNN=5.02 TeV, J. High Energy Phys. 04 (2017) 039.
  16. G. Aad et al. (ATLAS Collaboration), Observation of a centrality-dependent dijet asymmetry in lead-lead collisions at sNN=2.77 tev with the ATLAS detector at the LHC, Phys. Rev. Lett. 105, 252303 (2010).
  17. S. Chatrchyan et al. (CMS Collaboration), Observation and studies of jet quenching in PbPb collisions at nucleon-nucleon center-of-mass energy = 2.76 TeV, Phys. Rev. C 84, 024906 (2011).
  18. S. Chatrchyan et al. (CMS Collaboration), Jet momentum dependence of jet quenching in PbPb collisions at sNN=2.76 TeV, Phys. Lett. B 712, 176 (2012).
  19. V. Khachatryan et al. (CMS Collaboration), Measurement of transverse momentum relative to dijet systems in PbPb and pp collisions at sNN=2.76 TeV, J. High Energy Phys. 01 (2016) 006.
  20. A. M. Sirunyan et al. (CMS Collaboration), Measurement of the splitting function in pp and Pb-Pb collisions at sNN= 5.02 TeV, Phys. Rev. Lett. 120, 142302 (2018).
  21. M. S. Abdallah et al. (STAR Collaboration), Differential measurements of jet substructure and partonic energy loss in Au + Au collisions at SNN =200 GeV, Phys. Rev. C 105, 044906 (2022).
  22. S. Acharya et al. (A Large Ion Collider Experiment, ALICE Collaboration), Measurement of the groomed jet radius and momentum splitting fraction in pp and Pb−Pb collisions at sNN=5.02 tev, Phys. Rev. Lett. 128, 102001 (2022).
  23. S. Chatrchyan et al. (CMS Collaboration), Modification of jet shapes in PbPb collisions at sNN=2.76 TeV, Phys. Lett. B 730, 243 (2014).
  24. S. Acharya et al. (ALICE Collaboration), Measurement of jet radial profiles in Pb−Pb collisions at sNN= 2.76 TeV, Phys. Lett. B 796, 204 (2019).
  25. G. Aad et al. (ATLAS Collaboration), Measurement of angular and momentum distributions of charged particles within and around jets in Pb + Pb and pp collisions at sNN=5.02 TeV with the ATLAS detector, Phys. Rev. C 100, 064901 (2019); 101, 059903(E) (2020).
  26. S. Chatrchyan et al., Measurement of jet fragmentation in PbPb and pp collisions at sNN=2.76 TeV, Phys. Rev. C 90, 024908 (2014).
  27. M. Aaboud et al. (ATLAS Collaboration), Measurement of jet fragmentation in Pb + Pb and pp collisions at sNN=2.76 TeV with the ATLAS detector at the LHC, Eur. Phys. J. C 77, 379 (2017).
  28. S.-Y. Chen, K.-M. Shen, X.-F. Xue, W. Dai, B.-W. Zhang, and E.-K. Wang, Study of EEC discrimination power on quark and gluon quenching effects in heavy-ion collisions at s=5.02 TeV, arXiv:2409.13996.
  29. V. Chekhovsky et al. (CMS Collaboration), Observation of nuclear modification of energy-energy correlators inside jets in heavy ion collisions, Phys. Lett. B 866, 139556 (2025).
  30. M. Cacciari, G. P. Salam, and G. Soyez, Fastjet user manual, Eur. Phys. J. C 72, 1896 (2012).
  31. B. Abelev et al. (ALICE Collaboration), Measurement of charged jet suppression in Pb-Pb collisions at sNN = 2.76 TeV, J. High Energy Phys. 03 (2014) 013.
  32. P. Berta, L. Masetti, D. Miller, and M. Spousta, Pileup and underlying event mitigation with iterative constituent subtraction, J. High Energy Phys. 08 (2019) 175.
  33. P. Berta, M. Spousta, D. W. Miller, and R. Leitner, Particle-level pileup subtraction for jets and jet shapes, J. High Energy Phys. 06 (2014) 092.
  34. Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, arXiv:2103.14030.
  35. J. Liang, J. Cao, G. Sun, K. Zhang, L. V. Gool, and R. Timofte, Swinir: Image restoration using swin transformer, arXiv:2108.10257.
  36. HEP ML Community, A living review of machine learning for particle physics.
  37. Y.-T. Chien and R. K. Elayavalli, Probing heavy ion collisions using quark and gluon jet substructure, arXiv:1803.03589.
  38. Y. Du, D. Pablos, and K. Tywoniuk, Classification of quark and gluon jets in hot QCD medium with deep learning, in Proceedings of Particles and Nuclei International Conference 2021 — PoS(PANIC2021), PANIC2021 (Sissa Medialab, Lisbon, Portugal, 2022), p. 224.
  39. L. Liu, J. Velkovska, Y. Wu, and M. Verweij, Identifying quenched jets in heavy ion collisions with machine learning, J. High Energy Phys. 04 (2023) 140.
  40. L. Apolinário, N. F. Castro, M. Crispim Romão, J. G. Milhano, R. Pedro, and F. C. R. Peres, Deep learning for the classification of quenched jets, J. High Energy Phys. 11 (2021) 219.
  41. Y. S. Lai, J. Mulligan, M. Płoskoń, and F. Ringer, The information content of jet quenching and machine learning assisted observable design, J. High Energy Phys. 10 (2022) 011.
  42. M. Crispim Romão, J. G. Milhano, and M. van Leeuwen, Jet substructure observables for jet quenching in quark gluon plasma: A machine learning driven analysis, SciPost Phys. 16, 015 (2024).
  43. Y.-L. Du, Overview: Jet quenching with machine learning, arXiv:2308.10035.
  44. U. S. Qureshi and R. Kunnawalkam Elayavalli, Model-agnostic tagging of quenched jets in heavy-ion collisions, arXiv:2411.19389.
  45. Y.-L. Du, D. Pablos, and K. Tywoniuk, Deep learning jet modifications in heavy-ion collisions, J. High Energy Phys. 03 (2021) 206.
  46. Z. Yang, Y. He, W. Chen, W.-Y. Ke, L.-G. Pang, and X.-N. Wang, Deep learning assisted jet tomography for the study of mach cones in QGP, Eur. Phys. J. C 83, (2023).
  47. R. Haake and C. Loizides, Machine-learning-based jet momentum reconstruction in heavy-ion collisions, Phys. Rev. C 99, 064904 (2019).
  48. H. Bossi, r-dependence of inclusive jet suppression and groomed jet splittings in heavy-ion collisions with ALICE, arXiv:2208.14492.
  49. T. Mengel, P. Steffanic, C. Hughes, A. C. O. Da Silva, and C. Nattrass, Multiplicity-based background subtraction for jets in heavy ion collisions, arXiv:2402.10945.
  50. R. Li, Y.-L. Du, and S. Cao, Jet momentum reconstruction in the QGP background with machine learning, arXiv:2412.06466.
  51. T. Mengel, P. Steffanic, C. Hughes, A. C. O. D. Silva, and C. Nattrass, Multiplicity-based background subtraction for jets in heavy ion collisions, arXiv:2402.10945.
  52. Y.-L. Du, Overview: Jet quenching with machine learning, arXiv:2308.10035.
  53. D. Stewart and J. Putschke, Neural network biased corrections: Cautionary study in background corrections for quenched jets, Phys. Rev. C 111, 054902 (2025).
  54. K. C. Zapp, F. Krauss, and U. A. Wiedemann, A perturbative framework for jet quenching, J. High Energy Phys. 03 (2013) 080.
  55. R. K. Elayavalli and K. C. Zapp, Simulating v+jet processes in heavy ion collisions with jewel, Eur. Phys. J. C 76, 695 (2016).
  56. R. Kunnawalkam Elayavalli and K. C. Zapp, Medium response in jewel and its impact on jet shape observables in heavy ion collisions, J. High Energy Phys. 07 (2017) 141.
  57. J. G. Milhano and K. Zapp, Improved background subtraction and a fresh look at jet sub-structure in JEWEL, Eur. Phys. J. C 82, 1010 (2022).
  58. J. Adam et al. (ALICE Collaboration), Centrality dependence of the pseudorapidity density distribution for charged particles in Pb-Pb collisions at sNN=5.02 TeV, Phys. Lett. B 772, 567 (2017).
  59. B. Abelev et al. (ALICE Collaboration), Measurement of event background fluctuations for charged particle jet reconstruction in Pb-Pb collisions at sNN=2.76 TeV, J. High Energy Phys. 03 (2012) 053.
  60. S. Acharya et al. (ALICE Collaboration), Transverse momentum spectra and nuclear modification factors of charged particles in pp, p-Pb and Pb-Pb collisions at the LHC, J. High Energy Phys. 11 (2018) 013.
  61. J. Cogan, M. Kagan, E. Strauss, and A. Schwarztman, Jet-images: Computer vision inspired techniques for jet tagging, J. High Energy Phys. 02 (2015) 118.
  62. L. de Oliveira, M. Kagan, L. Mackey, B. Nachman, and A. Schwartzman, Jet-images — deep learning edition, J. High Energy Phys. 07 (2016) 069.
  63. P. T. Komiske, E. M. Metodiev, and M. D. Schwartz, Deep learning in color: Towards automated quark/gluon jet discrimination, J. High Energy Phys. 01 (2017) 110.
  64. J. Lin, M. Freytsis, I. Moult, and B. Nachman, Boosting h→bb¯ with machine learning, J. High Energy Phys. 10 (2018) 101.
  65. S. Macaluso and D. Shih, Pulling out all the tops with computer vision and deep learning, J. High Energy Phys. 10 (2018) 121.
  66. P. T. Komiske, E. M. Metodiev, B. Nachman, and M. D. Schwartz, Pileup mitigation with machine learning (pumml), J. High Energy Phys. 12 (2017) 051.
  67. M. Kagan, Image-based jet analysis, arXiv:2012.09719.
  68. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, arXiv:1706.03762.
  69. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, An image is worth 16 × 16 words: Transformers for image recognition at scale, arXiv:2010.11929.
  70. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai et al., Pytorch: An imperative style, high-performance deep learning library, arXiv:1912.01703.
  71. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  72. M. Cacciari, G. P. Salam, and G. Soyez, The anti-kt jet clustering algorithm, J. High Energy Phys. 04 (2008) 063.
  73. M. Cacciari and G. P. Salam, Dispelling the N3 myth for the kt jet-finder, Phys. Lett. B 641, 57 (2006).
  74. A. Roy, J. Pivarski, and C. W. Freer, An array-oriented Python interface for FastJet, J. Phys.: Conf. Ser. 2438, 012011 (2023).
  75. A. J. Larkoski, G. P. Salam, and J. Thaler, Energy correlation functions for jet substructure, J. High Energy Phys. 06 (2013) 108.
  76. W. Chen, S. Cao, T. Luo, L.-G. Pang, and X.-N. Wang, Effects of jet-induced medium excitation in γ-hadron correlation in A+A collisions, Phys. Lett. B 777, 86 (2018).
  77. U. S. Qureshi and R. Kunnawalkam Elayavalli, Dataset from deepsub: Deep image reconstruction for background subtraction in heavy-ion collisions, arXiv:2507.14036.
  78. U. S. Qureshi, Deepsub: Deep image reconstruction for background subtraction in heavy-ion collisions, https://github.com/umarsqureshi/DeepSub (2025).

Outline

Information

Phys. Rev. C 112, 064906– Published 9 December, 2025
  • Received 22 July 2025
  • Accepted 14 October 2025
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. Funded by SCOAP3.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation