- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review D

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
  • Access by Xinjiang University

Optimal transport for e/π0 particle classification in LArTPC neutrino experiments

David Caratelli1,*, Nathaniel Craig1,2,†, Chuyue Fang1,‡, and Jessica N. Howard1,2,§

  • *Contact author: dcaratelli@ucsb.edu
  • †Contact author: ncraig@ucsb.edu
  • ‡Contact author: cfang@ucsb.edu
  • §Contact author: jnhoward@kitp.ucsb.edu
PDF

Phys. Rev. D 113, 072005 – Published 8 April, 2026

DOI: https://doi.org/10.1103/6zws-fnrf

Abstract

The efficient classification of electromagnetic activity from π0 and electrons remains an open problem in the reconstruction of neutrino interactions in liquid argon time projection chamber (LArTPC) detectors. We address this problem using the mathematical framework of optimal transport (OT), which has been successfully employed for event classification in other high energy physics contexts and is ideally suited to the high-resolution calorimetry of LArTPCs. Using a publicly available simulated dataset from the MicroBooNE Collaboration, we show that OT methods achieve state-of-the-art reconstruction performance in e/π0 classification. The success of this first application indicates the broader promise of OT methods for LArTPC-based neutrino experiments.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (106)

  1. P. Huber et al., Snowmass neutrino frontier report, in Snowmass 2021 (2022); arXiv:2211.08641.
  2. R. Acciarri et al. (MicroBooNE, LAr1-ND, and ICARUS-WA104 Collaborations), A proposal for a three detector short-baseline neutrino oscillation program in the Fermilab booster neutrino beam, arXiv:1503.01520.
  3. B. Abi et al. (DUNE Collaboration), Deep underground neutrino experiment (DUNE), far detector technical design report, volume I introduction to DUNE, J. Instrum. 15, T08008 (2020).
  4. B. Abi et al. (DUNE Collaboration), Long-baseline neutrino oscillation physics potential of the DUNE experiment, Eur. Phys. J. C 80, 978 (2020).
  5. A. A. Aguilar-Arevalo et al. (MiniBooNE Collaboration), The MiniBooNE detector, Nucl. Instrum. Methods Phys. Res., Sect. A 599, 28 (2009).
  6. P. Adamson et al. (NOvA Collaboration), First measurement of muon-neutrino disappearance in NOvA, Phys. Rev. D 93, 051104 (2016).
  7. D. G. Michael et al. (MINOS Collaboration), The Magnetized steel and scintillator calorimeters of the MINOS experiment, Nucl. Instrum. Methods Phys. Res., Sect. A 596, 190 (2008).
  8. F. Drielsma, K. Terao, L. Dominé, and D. H. Koh, Scalable, end-to-end, deep-learning-based data reconstruction chain for particle imaging detectors, in Proceedings of the 34th Conference on Neural Information Processing Systems (2021), arXiv:2102.01033.
  9. A. Aurisano, V. Hewes, G. Cerati, J. Kowalkowski, C. S. Lee, W. Liao, D. Grzenda, K. Gumpula, and X. Zhang, Graph neural network for neutrino physics event reconstruction, Phys. Rev. D 110, 032008 (2024).
  10. A. Abed Abud et al. (DUNE Collaboration), Separation of track- and shower-like energy deposits in ProtoDUNE-SP using a convolutional neural network, Eur. Phys. J. C 82, 903 (2022).
  11. P. Lutkus, T. Wongjirad, and S. Aeron, Towards designing and exploiting generative networks for neutrino physics experiments using liquid argon time projection chambers, in Proceedings of the 9th International Conference on Learning Representations (2022), arXiv:2204.02496.
  12. F. Drielsma, Q. Lin, P. C. de Soux, L. Dominé, R. Itay, D. H. Koh, B. J. Nelson, K. Terao, K. V. Tsang, and T. L. Usher (DeepLearnPhysics Collaboration), Clustering of electromagnetic showers and particle interactions with graph neural networks in liquid argon time projection chambers, Phys. Rev. D 104, 072004 (2021).
  13. L. Dominé, P. C. de Soux, F. Drielsma, D. H. Koh, R. Itay, Q. Lin, K. Terao, K. V. Tsang, and T. L. Usher (DeepLearnPhysics Collaboration), Point proposal network for reconstructing 3D particle endpoints with subpixel precision in liquid argon time projection chambers, Phys. Rev. D 104, 032004 (2021).
  14. HEP ML Community, A Living Review of Machine Learning for Particle Physics, arXiv:2102.02770.
  15. G. Aad et al. (ATLAS Collaboration), A continuous calibration of the ATLAS flavour-tagging classifiers via optimal transportation maps, Eur. Phys. J. C 85, 1272 (2025).
  16. M. Algren, J. A. Raine, and T. Golling, Decorrelation using optimal transport, Eur. Phys. J. C 84, 579 (2024).
  17. M. Leigh, D. Sengupta, B. Nachman, and T. Golling, Accelerating template generation in resonant anomaly detection searches with optimal transport, J. High Energy Phys. 12 (2025) 105.
  18. T. Manole, P. Bryant, J. Alison, M. Kuusela, and L. Wasserman, Background modeling for double Higgs boson production: Density ratios and optimal transport, arXiv:2208.02807.
  19. A. Davis, T. Menzo, A. Youssef, and J. Zupan, Earth mover’s distance as a measure of CP violation, J. High Energy Phys. 06 (2023) 098.
  20. T. Cheng, J.-F. Arguin, J. Leissner-Martin, J. Pilette, and T. Golling, Variational autoencoders for anomalous jet tagging, Phys. Rev. D 107, 016002 (2023).
  21. A. J. Larkoski, Factorization for collider dataspace correlators, Phys. Rev. D 112, 054012 (2025).
  22. A. J. Larkoski, Non-gaussianities in collider metric binning, arXiv:2503.03809.
  23. T. Cai, N. Craig, K. Craig, and X. Lin, Multi-scale optimal transport for complete collider events, Phys. Rev. D 112, 036021 (2025).
  24. N. Craig, J. N. Howard, and H. Li, Exploring optimal transport for event-level anomaly detection at the large hadron collider, arXiv:2401.15542.
  25. R. Gambhir, A. J. Larkoski, and J. Thaler, SPECTER: Efficient evaluation of the spectral EMD, J. High Energy Phys. 12 (2024) 219.
  26. T. Gaertner and J. Reiten, Unsupervised learning in the metric space of jets, arXiv:2312.06948.
  27. A. J. Larkoski and J. Thaler, A spectral metric for collider geometry, J. High Energy Phys. 08 (2023) 107.
  28. D. Ba, A. S. Dogra, R. Gambhir, A. Tasissa, and J. Thaler, SHAPER: Can you hear the shape of a jet?, J. High Energy Phys. 06 (2023) 195.
  29. L. Gouskos, F. Iemmi, S. Liechti, B. Maier, V. Mikuni, and H. Qu, Optimal transport for a novel event description at hadron colliders, Phys. Rev. D 108, 096003 (2023).
  30. S. E. Park, P. Harris, and B. Ostdiek, Neural embedding: Learning the embedding of the manifold of physics data, J. High Energy Phys. 07 (2023) 108.
  31. T. Cai, J. Cheng, K. Craig, and N. Craig, Which metric on the space of collider events?, Phys. Rev. D 105, 076003 (2022).
  32. S. Tsan, R. Kansal, A. Aportela, D. Diaz, J. Duarte, S. Krishna, F. Mokhtar, J.-R. Vlimant, and M. Pierini, Particle graph autoencoders and differentiable, learned energy Mover’s distance, in Proceedings of the 35th Conference on Neural Information Processing Systems (2021), arXiv:2111.12849.
  33. G. Di Guglielmo et al., A reconfigurable neural network ASIC for detector front-end data compression at the HL-LHC, IEEE Trans. Nucl. Sci. 68, 2179 (2021).
  34. J. H. Collins, An exploration of learnt representations of W jets, arXiv:2109.10919.
  35. T. Cai, J. Cheng, N. Craig, and K. Craig, Linearized optimal transport for collider events, Phys. Rev. D 102, 116019 (2020).
  36. M. Crispim Romão, N. F. Castro, J. G. Milhano, R. Pedro, and T. Vale, Use of a generalized energy Mover’s distance in the search for rare phenomena at colliders, Eur. Phys. J. C 81, 192 (2021).
  37. P. T. Komiske, E. M. Metodiev, and J. Thaler, Metric space of collider events, Phys. Rev. Lett. 123, 041801 (2019).
  38. P. T. Komiske, R. Mastandrea, E. M. Metodiev, P. Naik, and J. Thaler, Exploring the space of jets with CMS open data, Phys. Rev. D 101, 034009 (2020).
  39. K. Fraser, S. Homiller, R. K. Mishra, B. Ostdiek, and M. D. Schwartz, Challenges for unsupervised anomaly detection in particle physics, J. High Energy Phys. 03 (2022) 066.
  40. P. T. Komiske, E. M. Metodiev, and J. Thaler, The hidden geometry of particle collisions, J. High Energy Phys. 07 (2020) 006.
  41. C. Cesarotti and M. LeBlanc, A field guide to event-shape observables using optimal transport, J. High Energy Phys. 12 (2025) 014.
  42. G. Aad et al. (ATLAS Collaboration), Measurements of multijet event isotropies using optimal transport with the ATLAS detector, J. High Energy Phys. 10 (2023) 060.
  43. C. Cesarotti and J. Thaler, A robust measure of event isotropy at colliders, J. High Energy Phys. 08 (2020) 084.
  44. C. Cesarotti, M. Reece, and M. J. Strassler, The efficacy of event isotropy as an event shape observable, J. High Energy Phys. 07 (2021) 215.
  45. P. Abratenko et al. (MicroBooNE Collaboration), Search for an anomalous production of charged-current νe interactions without visible pions across multiple kinematic observables in MicroBooNE, Phys. Rev. Lett. 135, 081802 (2025).
  46. A. M. Abdullahi et al. (MicroBooNE Collaboration), First search for dark sector e+e− explanations of the MiniBooNE anomaly at MicroBooNE, arXiv:2502.10900.
  47. P. Abratenko et al. (MicroBooNE Collaboration), Inclusive search for anomalous single-photon production in MicroBooNE, arXiv:2502.06064.
  48. B. Abi et al. (DUNE Collaboration), First results on ProtoDUNE-SP liquid argon time projection chamber performance from a beam test at the CERN Neutrino Platform, J. Instrum. 15, P12004 (2020).
  49. C. Adams et al. (MicroBooNE Collaboration), Calibration of the charge and energy loss per unit length of the MicroBooNE liquid argon time projection chamber using muons and protons, J. Instrum. 15, P03022 (2020).
  50. P. Abratenko et al. (ICARUS Collaboration), ICARUS at the Fermilab short-baseline neutrino program: Initial operation, Eur. Phys. J. C 83, 467 (2023).
  51. P. Abratenko et al. (MicroBooNE Collaboration), First constraints on light sterile neutrino oscillations from combined appearance and disappearance searches with the MicroBooNE detector, Phys. Rev. Lett. 130, 011801 (2023).
  52. P. Abratenko et al. (MicroBooNE Collaboration), Search for heavy neutral leptons decaying into muon-pion pairs in the MicroBooNE detector, Phys. Rev. D 101, 052001 (2020).
  53. P. Abratenko et al. (MicroBooNE Collaboration), Search for long-lived heavy neutral leptons and Higgs portal scalars decaying in the MicroBooNE detector, Phys. Rev. D 106, 092006 (2022).
  54. P. Abratenko et al. (MicroBooNE Collaboration), First search for dark-trident processes using the MicroBooNE detector, Phys. Rev. Lett. 132, 241801 (2024).
  55. K. Abe et al. (Hyper-Kamiokande Collaboration), Hyper-Kamiokande design report, arXiv:1805.04163.
  56. A. Abdullahi et al., From oversimplified to overlooked: The case for exploring Rich Dark Sectors, Nucl. Phys. B1020, 117148 (2025).
  57. B. Batell et al., Dark sector studies with neutrino beams, in Snowmass 2021 (2022); arXiv:2207.06898.
  58. D. Rein and L. M. Sehgal, Neutrino-excitation of baryon resonances and single pion production, Ann. Phys. (N.Y.) 133, 79 (1981).
  59. T. Leitner, O. Buss, L. Alvarez-Ruso, and U. Mosel, Electron- and neutrino-nucleus scattering from the quasielastic to the resonance region, Phys. Rev. C 79, 034601 (2009).
  60. R. A. et al. (MicroBooNE Collaboration), Design and construction of the microboone detector, J. Instrum. 12, P02017 (2017).
  61. A. Abed Abud et al. (DUNE Collaboration), The DUNE far detector vertical drift technology. Technical design report, J. Instrum. 19, T08004 (2024).
  62. S. Abbaslu et al. (DUNE Collaboration), Operation of a modular 3D-pixelated liquid argon time-projection chamber in a neutrino beam, arXiv:2509.07012.
  63. A. Abed Abud et al. (DUNE Collaboration), Performance of a modular ton-scale pixel-readout liquid argon time projection chamber, Instruments 8, 41 (2024).
  64. R. Acciarri et al. (MicroBooNE Collaboration), The Pandora multi-algorithm approach to automated pattern recognition of cosmic-ray muon and neutrino events in the MicroBooNE detector, Eur. Phys. J. C 78, 82 (2018).
  65. P. Abratenko et al. (MicroBooNE Collaboration), Wire-Cell 3D pattern recognition techniques for neutrino event reconstruction in large LArTPCs: Algorithm description and quantitative evaluation with MicroBooNE simulation, J. Instrum. 17, P01037 (2022).
  66. R. Acciarri et al. (MicroBooNE Collaboration), Michel electron reconstruction using cosmic-ray data from the MicroBooNE LArTPC, J. Instrum. 12, P09014 (2017).
  67. C. Adams et al. (MicroBooNE Collaboration), Reconstruction and measurement of O(100)  MeV energy electromagnetic activity from π0→γγ decays in the MicroBooNE LArTPC, J. Instrum. 15, P02007 (2020).
  68. MicroBooNE, Microboone BNB inclusive overlay sample (no wire info), 10.5281/zenodo.8370883 (2023).
  69. MicroBooNE, Microboone BNB electron neutrino overlay sample (no wire info), 10.5281/zenodo.7261921 (2022).
  70. I. Stancu, Technical design report for the 8 GeV beam, Report No. FERMILAB-DESIGN-2001-03, 2001, 10.2172/1212167.
  71. C. Andreopoulos et al., The GENIE neutrino Monte Carlo generator, Nucl. Instrum. Methods Phys. Res., Sect. A 614, 87 (2010).
  72. P. Abratenko et al. (MicroBooNE Collaboration), New CC0π GENIE model tune for MicroBooNE, Phys. Rev. D 105, 072001 (2022).
  73. E. L. Snider and G. Petrillo, LArSoft: Toolkit for simulation, reconstruction and analysis of liquid argon TPC neutrino detectors, J. Phys. Conf. Ser. 898, 042057 (2017).
  74. C. Adams et al. (MicroBooNE Collaboration), A method to determine the electric field of liquid argon time projection chambers using a UV laser system and its application in MicroBooNE, J. Instrum. 15, P07010 (2020).
  75. R. Acciarri et al. (MicroBooNE Collaboration), Noise characterization and filtering in the MicroBooNE liquid argon TPC, J. Instrum. 12, P08003 (2017).
  76. C. Adams et al. (MicroBooNE Collaboration), Ionization electron signal processing in single phase LArTPCs. Part I. Algorithm Description and quantitative evaluation with MicroBooNE simulation, J. Instrum. 13, P07006 (2018).
  77. C. Adams et al. (MicroBooNE Collaboration), Ionization electron signal processing in single phase LArTPCs. Part II. Data/simulation comparison and performance in MicroBooNE, J. Instrum. 13, P07007 (2018).
  78. A. Abed Abud et al. (DUNE Collaboration), Reconstruction of interactions in the ProtoDUNE-SP detector with Pandora, Eur. Phys. J. C 83, 618 (2023).
  79. P. Abratenko et al. (MicroBooNE Collaboration), Neutrino event selection in the MicroBooNE liquid argon time projection chamber using Wire-Cell 3-D imaging, clustering and charge-light matching, J. Instrum. 16, P06043 (2021).
  80. R. Acciarri et al. (MicroBooNE Collaboration), Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber, J. Instrum. 12, P03011 (2017).
  81. P. Abratenko et al. (MicroBooNE Collaboration), A convolutional neural network for multiple particle identification in the MicroBooNE liquid argon time projection chamber, Phys. Rev. D 103, 092003 (2021).
  82. B. Abi et al. (DUNE Collaboration), Neutrino interaction classification with a convolutional neural network in the DUNE far detector, Phys. Rev. D 102, 092003 (2020).
  83. A. Abed Abud et al. (DUNE Collaboration), Separation of track- and shower-like energy deposits in ProtoDUNE-SP using a convolutional neural network, Eur. Phys. J. C 82, 903 (2022).
  84. C. Adams et al. (MicroBooNE Collaboration), Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber, Phys. Rev. D 99, 092001 (2019).
  85. P. Abratenko et al. (MicroBooNE Collaboration), Semantic segmentation with sparse convolutional neural network for event reconstruction in MicroBooNE, Phys. Rev. D 103, 052012 (2021).
  86. P. Abratenko et al. (MicroBooNE Collaboration), Improving neutrino energy estimation of charged-current interaction events with recurrent neural networks in MicroBooNE, Phys. Rev. D 110, 092010 (2024).
  87. R. Acciarri et al. (ArgoNeuT Collaboration), First observation of low energy electron neutrinos in a liquid argon time projection chamber, Phys. Rev. D 95, 072005 (2017).
  88. P. Abratenko et al. (MicroBooNE Collaboration), Search for an anomalous excess of charged-current νe interactions without pions in the final state with the MicroBooNE experiment, Phys. Rev. D 105, 112004 (2022).
  89. P. Abratenko et al. (MicroBooNE Collaboration), Search for an anomalous production of charged-current νe interactions without visible pions across multiple kinematic observables in MicroBooNE, Phys. Rev. Lett. 135, 081802 (2025).
  90. P. Abratenko et al. (MicroBooNE Collaboration), First search for neutral current coherent single-photon production in MicroBooNE, arXiv:2502.06091.
  91. P. Abratenko et al. (MicroBooNE Collaboration), Enhanced search for neutral current Δ radiative single-photon production in MicroBooNE, Phys. Rev. D 112, L091101 (2025).
  92. P. Abratenko et al. (MicroBooNE Collaboration), First measurement of νe and ν¯e charged-current single charged-pion production differential cross sections on argon using the MicroBooNE detector, Phys. Rev. Lett. 135, 061802 (2025).
  93. F. Mémoli, Gromov–wasserstein distances and the metric approach to object matching, Found. Comput. Math. 11, 417 (2011).
  94. B. A. et al. (DUNE Collaboration), Deep underground neutrino experiment (dune), far detector technical design report, volume ii: Dune physics, arXiv:2002.03005.
  95. L. Delchambre, Weighted principal component analysis: A weighted covariance eigendecomposition approach, Mon. Not. R. Astron. Soc. 446, 3545 (2014).
  96. R. Flamary, N. Courty, A. Gramfort, M. Z. Alaya, A. Boisbunon, S. Chambon, L. Chapel, A. Corenflos, K. Fatras, N. Fournier, L. Gautheron, N. T. Gayraud, H. Janati, A. Rakotomamonjy, I. Redko, A. Rolet, A. Schutz, V. Seguy, D. J. Sutherland, R. Tavenard, A. Tong, and T. Vayer, Pot: Python optimal transport, J. Mach. Learn. Res. 22, 1 (2021).
  97. T. Cover and P. Hart, Nearest neighbor pattern classification, IEEE Trans. Inf. Theory 13, 21 (1967).
  98. B. Schölkopf, R. C. Williamson, A. Smola, J. Shawe-Taylor, and J. Platt, Support vector method for novelty detection, in Advances in Neural Information Processing Systems, edited by S. Solla, T. Leen, and K. Müller (MIT Press, Cambridge, MA, 1999), Vol. 12, https://papers.nips.cc/paper_files/paper/1999/hash/8725fb777f25776ffa9076e44fcfd776-Abstract.html.
  99. N. Bonneel, M. van de Panne, S. Paris, and W. Heidrich, Displacement interpolation using Lagrangian mass transport, ACM Trans. Graph. 30, 1 (2011).
  100. M. Cuturi, Sinkhorn distances: Lightspeed computation of optimal transportation distances, arXiv:1306.0895.
  101. J. Altschuler, J. Weed, and P. Rigollet, Near-linear time approximation algorithms for optimal transport via sinkhorn iteration, arXiv:1705.09634.
  102. A. Genevay, L. Chizat, F. Bach, M. Cuturi, and G. Peyré, Sample complexity of sinkhorn divergences, arXiv:1810.02733.
  103. K. Nguyen and N. Ho, Energy-based sliced wasserstein distance, arXiv:2304.13586.
  104. N. Kravtsova, Note on computational complexity of the Gromov-Wasserstein distance, arXiv:2408.06525.
  105. G. Peyré, M. Cuturi, and J. M. Solomon, Gromov-wasserstein averaging of kernel and distance matrices, in International Conference on Machine Learning (2016), https://proceedings.mlr.press/v48/peyre16.html.
  106. T. Vayer, R. Flamary, R. Tavenard, L. Chapel, and N. Courty, Sliced Gromov-Wasserstein, arXiv:1905.10124.

Outline

Information

Phys. Rev. D 113, 072005– Published 8 April, 2026
  • Received 24 June 2025
  • Accepted 18 February 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. Funded by SCOAP3.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation