Journal of High Energy Physics

, 2017:110 | Cite as

Deep learning in color: towards automated quark/gluon jet discrimination

  • Patrick T. Komiske
  • Eric M. MetodievEmail author
  • Matthew D. Schwartz
Open Access
Regular Article - Theoretical Physics


Artificial intelligence offers the potential to automate challenging data-processing tasks in collider physics. To establish its prospects, we explore to what extent deep learning with convolutional neural networks can discriminate quark and gluon jets better than observables designed by physicists. Our approach builds upon the paradigm that a jet can be treated as an image, with intensity given by the local calorimeter deposits. We supplement this construction by adding color to the images, with red, green and blue intensities given by the transverse momentum in charged particles, transverse momentum in neutral particles, and pixel-level charged particle counts. Overall, the deep networks match or outperform traditional jet variables. We also find that, while various simulations produce different quark and gluon jets, the neural networks are surprisingly insensitive to these differences, similar to traditional observables. This suggests that the networks can extract robust physical information from imperfect simulations.




Open Access

This article is distributed under the terms of the Creative Commons Attribution License (CC-BY 4.0), which permits any use, distribution and reproduction in any medium, provided the original author(s) and source are credited.


  1. [1]
    ATLAS collaboration, A neural network clustering algorithm for the ATLAS silicon pixel detector, 2014 JINST 9 P09009 [arXiv:1406.7690] [INSPIRE].
  2. [2]
    ATLAS collaboration, Performance of b-jet identification in the ATLAS experiment, 2016 JINST 11 P04008 [arXiv:1512.01094] [INSPIRE].
  3. [3]
    M. Tosi, Performance of tracking, b-tagging and jet/MET reconstruction at the CMS high level trigger, J. Phys. Conf. Ser. 664 (2015) 082055.CrossRefGoogle Scholar
  4. [4]
    CMS collaboration, Performance of tau-lepton reconstruction and identification in CMS, 2012 JINST 7 P01001 [arXiv:1109.6034] [INSPIRE].
  5. [5]
    NNPDF collaboration, R.D. Ball et al., Parton distributions for the LHC Run II, JHEP 04 (2015) 040 [arXiv:1410.8849] [INSPIRE].
  6. [6]
    J. Gallicchio, J. Huth, M. Kagan, M.D. Schwartz, K. Black and B. Tweedie, Multivariate discrimination and the Higgs + W/Z search, JHEP 04 (2011) 069 [arXiv:1010.3698] [INSPIRE].ADSCrossRefGoogle Scholar
  7. [7]
    T. Maggipinto et al., Role of neural networks in the search of the Higgs boson at LHC, Phys. Lett. B 409 (1997) 517 [hep-ex/9705020] [INSPIRE].
  8. [8]
    CMS collaboration, Search for supersymmetry in events with opposite-sign dileptons and missing transverse energy using an artificial neural network, Phys. Rev. D 87 (2013) 072001 [arXiv:1301.0916] [INSPIRE].
  9. [9]
    P. Baldi, P. Sadowski and D. Whiteson, Enhanced Higgs boson to τ + τ search with deep learning, Phys. Rev. Lett. 114 (2015) 111801 [arXiv:1410.3469] [INSPIRE].ADSCrossRefGoogle Scholar
  10. [10]
    J. Cogan, M. Kagan, E. Strauss and A. Schwarztman, Jet-images: computer vision inspired techniques for jet tagging, JHEP 02 (2015) 118 [arXiv:1407.5675] [INSPIRE].ADSCrossRefGoogle Scholar
  11. [11]
    L.G. Almeida, M. Backović, M. Cliche, S.J. Lee and M. Perelstein, Playing tag with ANN: boosted top identification with pattern recognition, JHEP 07 (2015) 086 [arXiv:1501.05968] [INSPIRE].ADSCrossRefGoogle Scholar
  12. [12]
    L. de Oliveira, M. Kagan, L. Mackey, B. Nachman and A. Schwartzman, Jet-images — Deep learning edition, JHEP 07 (2016) 069 [arXiv:1511.05190] [INSPIRE].CrossRefGoogle Scholar
  13. [13]
    P. Baldi, K. Bauer, C. Eng, P. Sadowski and D. Whiteson, Jet substructure classification in high-energy physics with deep neural networks, Phys. Rev. D 93 (2016) 094034 [arXiv:1603.09349] [INSPIRE].ADSGoogle Scholar
  14. [14]
    D. Guest, J. Collado, P. Baldi, S.-C. Hsu, G. Urban and D. Whiteson, Jet flavor classification in high-energy physics with deep neural networks, Phys. Rev. D 94 (2016) 112002 [arXiv:1607.08633] [INSPIRE].ADSGoogle Scholar
  15. [15]
    J. Barnard, E.N. Dawe, M.J. Dolan and N. Rajcic, Parton shower uncertainties in jet substructure analyses with deep neural networks, arXiv:1609.00607 [INSPIRE].
  16. [16]
    A. Krizhevsky, I. Sutskever and G.E. Hinton, Imagenet classification with deep convolutional neural networks, in the proceedings of Neural Information Processing Systems (NIPS 2012), December 3-8, Lake Tahoe, U.S.A. (2012).Google Scholar
  17. [17]
    J. Pumplin, How to tell quark jets from gluon jets, Phys. Rev. D 44 (1991) 2025 [INSPIRE].ADSGoogle Scholar
  18. [18]
    L. Lönnblad, C. Peterson and T. Rögnvaldsson, Finding gluon jets with a neural trigger, Phys. Rev. Lett. 65 (1990) 1321.ADSCrossRefGoogle Scholar
  19. [19]
    OPAL collaboration, A Study of differences between quark and gluon jets using vertex tagging of quark jets, Z. Phys. C 58 (1993) 387.Google Scholar
  20. [20]
    OPAL collaboration, A direct observation of quark-gluon jet differences at LEP, Phys. Lett. B 265 (1991) 462.Google Scholar
  21. [21]
    D. Ferreira de Lima, P. Petrov, D. Soper and M. Spannowsky, Quark-gluon tagging with shower deconstruction: unearthing dark matter and Higgs couplings, arXiv:1607.06031 [INSPIRE].
  22. [22]
    A.J. Larkoski, J. Thaler and W.J. Waalewijn, Gaining (mutual) information about quark/gluon discrimination, JHEP 11 (2014) 129 [arXiv:1408.3122] [INSPIRE].ADSCrossRefGoogle Scholar
  23. [23]
    B. Bhattacherjee, S. Mukhopadhyay, M.M. Nojiri, Y. Sakaki and B.R. Webber, Associated jet and subjet rates in light-quark and gluon jet discrimination, JHEP 04 (2015) 131 [arXiv:1501.04794] [INSPIRE].ADSCrossRefGoogle Scholar
  24. [24]
    J. Gallicchio and M.D. Schwartz, Quark and gluon jet substructure, JHEP 04 (2013) 090 [arXiv:1211.7038] [INSPIRE].ADSCrossRefGoogle Scholar
  25. [25]
    J. Gallicchio and M.D. Schwartz, Quark and gluon tagging at the LHC, Phys. Rev. Lett. 107 (2011) 172001 [arXiv:1106.3076] [INSPIRE].ADSCrossRefGoogle Scholar
  26. [26]
    J.R. Andersen et al., Les Houches 2015: physics at TeV colliders standard model working group report, arXiv:1605.04692 [INSPIRE].
  27. [27]
    ATLAS collaboration, Light-quark and gluon jet discrimination in pp collisions at \( \sqrt{s}=7 \) TeV with the ATLAS detector, Eur. Phys. J. C 74 (2014) 3023 [arXiv:1405.6583] [INSPIRE].
  28. [28]
    C. Frye, A.J. Larkoski, M.D. Schwartz and K. Yan, Factorization for groomed jet substructure beyond the next-to-leading logarithm, JHEP 07 (2016) 064 [arXiv:1603.09338] [INSPIRE].ADSCrossRefGoogle Scholar
  29. [29]
    R. Collobert and J. Weston, A unified architecture for natural language processing: deep neural networks with multitask learning, in the proceedings of the 25th International Conference on Machine Learning, July 5-9, Helsinki, Finland (2008).Google Scholar
  30. [30]
    P. Baldi, P. Sadowski and D. Whiteson, Searching for exotic particles in high-energy physics with deep learning, Nature Commun. 5 (2014) 4308 [arXiv:1402.4735] [INSPIRE].ADSCrossRefGoogle Scholar
  31. [31]
    S. Dieleman, K.W. Willet and J. Dambre, Rotation-invariant convolutional neural networks for galaxy morphology prediction, Mon. Roy. Astron. Soc. 450 (2015) 1441 [arXiv:1503.07077].ADSCrossRefGoogle Scholar
  32. [32]
    M.A. Nielsen, Neural networks and deep learning, Determination Press, U.S.A. (2015).Google Scholar
  33. [33]
    I. Goodfellow, Y. Bengio and A. Courville, Deep learning, MIT Press, U.S.A. (2016).Google Scholar
  34. [34]
    X. Glorot, A. Bordes and Y. Bengio, Deep sparse rectifier neural networks, in the proceedings of the 14th International Conference on Artificial Intelligence and Statistics, April 11-13, Ft. Lauderdale, U.S.A. (2011).Google Scholar
  35. [35]
    K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, Neural Netw. 2 (1989) 359.CrossRefGoogle Scholar
  36. [36]
    J. Schmidhuber, Deep learning in neural networks: an overview, Neural Netw. 61 (2015) 85 [arXiv:1404.7828].CrossRefGoogle Scholar
  37. [37]
    C. Szegedy et al., Going deeper with convolutions, in the proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 7-12, Boston U.S.A. (2015), arXiv:1409.4842.
  38. [38]
    N. Srivastava et al., Dropout: a simple way to prevent neural networks from overfitting, JMLR 15 (2014) 1929.MathSciNetzbMATHGoogle Scholar
  39. [39]
    T. Sjöstrand, et al., An Introduction to PYTHIA 8.2, Comput. Phys. Commun. 191 (2015) 159 [arXiv:1410.3012] [INSPIRE].
  40. [40]
    M. Bahr et al., HERWIG++ physics and manual, Eur. Phys. J. C 58 (2008) 639 [arXiv:0803.0883] [INSPIRE].ADSCrossRefGoogle Scholar
  41. [41]
    J. Bellm et al., HERWIG 7.0/HERWIG++ 3.0 release note, Eur. Phys. J. C 76 (2016) 196 [arXiv:1512.01178] [INSPIRE].
  42. [42]
    M. Cacciari, G.P. Salam and G. Soyez, FastJet user manual, Eur. Phys. J. C 72 (2012) 1896 [arXiv:1111.6097] [INSPIRE].ADSCrossRefGoogle Scholar
  43. [43]
    M. Cacciari, G.P. Salam and G. Soyez, The anti-k t jet clustering algorithm, JHEP 04 (2008) 063 [arXiv:0802.1189] [INSPIRE].ADSCrossRefGoogle Scholar
  44. [44]
    D.E. Kaplan, K. Rehermann, M.D. Schwartz and B. Tweedie, Top tagging: a method for identifying boosted hadronically decaying top quarks, Phys. Rev. Lett. 101 (2008) 142001 [arXiv:0806.0848] [INSPIRE].ADSCrossRefGoogle Scholar
  45. [45]
    NNPDF collaboration, R.D. Ball et al., A determination of parton distributions with faithful uncertainty estimation, Nucl. Phys. B 809 (2009) 1 [Erratum ibid. B 816 (2009) 293] [arXiv:0808.1231] [INSPIRE].
  46. [46]
    P.Y. Simard, D. Steinkraus and J.C. Platt, Best practices for convolutional neural networks applied to visual document analysis, ICDAR 3 (2003).Google Scholar
  47. [47]
    F. Chollet, Keras, available at GitHub (2015).
  48. [48]
    J. Bergstra et al., Theano: a CPU and GPU math compiler in Python, in the proceedings of the 9th Python in science conference, June 28-July 3, Austin, U.S.A. (2010).Google Scholar
  49. [49]
    K. He, X. Zhang, S. Ren and J. Sun, Delving deep into rectifiers: surpassing human-level performance on imagenet classification, in the proceedings of the IEEE International Conference on Computer Vision, December 11-18, Santiago, Chile (2015).Google Scholar
  50. [50]
    D. Kingma and J. Ba, Adam: a method for stochastic optimization, arXiv:1412.6980.
  51. [51]
    J. Snoek, H. Larochelle and R.P. Adams, Practical bayesian optimization of machine learning algorithms, in the proceedings of Neural Information Processing Systems (NIPS 2012), December 3-8, Lake Tahoe, U.S.A. (2012), arXiv:1206.2944.
  52. [52]
    CMS Collaboration, Particle-flow event reconstruction in CMS and Performance for Jets, Taus and MET, CMS-PAS-PFT-09-001 (2009).
  53. [53]
    F. Pedregosa et al., Scikit-learn: machine learning in Python, JMLR 12 (2012) 2825.MathSciNetzbMATHGoogle Scholar
  54. [54]
    A.J. Larkoski, G.P. Salam and J. Thaler, Energy correlation functions for jet substructure, JHEP 06 (2013) 108 [arXiv:1305.0007] [INSPIRE].ADSMathSciNetCrossRefzbMATHGoogle Scholar
  55. [55]
    H. Küçük, Measurement of the inclusive-jet cross-section in proton-proton collisions and study of quark-gluon jet discrimination with the ATLAS experiment at the LHC, Dissertation, University College London, London. U.K. (2016).Google Scholar

Copyright information

© The Author(s) 2017

Authors and Affiliations

  • Patrick T. Komiske
    • 1
  • Eric M. Metodiev
    • 1
    Email author
  • Matthew D. Schwartz
    • 2
  1. 1.Center for Theoretical PhysicsMassachusetts Institute of TechnologyCambridgeU.S.A.
  2. 2.Department of PhysicsHarvard UniversityCambridgeU.S.A.

Personalised recommendations