- Physical Review Journals
All JournalsPhysics Magazine

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
  • Letter
  • Open Access

Enhancing events in neutrino telescopes through deep-learning-driven superresolution

Felix J. Yu1,2,*, Nicholas Kamp2,†, and Carlos A. Argüelles1,2,‡

  • *Contact author: felixyu@g.harvard.edu
  • †Contact author: nkamp@g.harvard.edu
  • ‡Contact author: carguelles@g.harvard.edu
PDF

Phys. Rev. D 111, L041301 – Published 5 February, 2025

DOI: https://doi.org/10.1103/PhysRevD.111.L041301

Abstract

Recent discoveries by neutrino telescopes, such as the IceCube Neutrino Observatory, relied extensively on machine learning (ML) tools to infer physical quantities from the raw photon hits detected. Neutrino telescope reconstruction algorithms are limited by the sparse sampling of photons by the optical modules due to the relatively large spacing (10–100 m) between them. In this Letter, we propose a novel technique that learns photon transport through the detector medium through the use of deep-learning-driven superresolution of data events. These “improved” events can then be reconstructed using traditional or ML techniques, resulting in improved resolution. Our strategy arranges additional “virtual” optical modules within an existing detector geometry and trains a convolutional neural network to predict the hits on these virtual optical modules. We show that this technique improves the angular reconstruction of muons in a generic ice-based neutrino telescope. Our results readily extend to water-based neutrino telescopes and other event morphologies.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (43)

  1. C. A. Argüelles, F. Halzen, and N. Kurahashi, From the dawn of neutrino astronomy to a new view of the extreme universe, arXiv:2405.17623.
  2. M. G. Aartsen et al. (IceCube Collaboration), The IceCube neutrino observatory: Instrumentation and online systems, J. Instrum. 12, P03012 (2017); J. Instrum.19, E05001 (2024).
  3. M. G. Aartsen et al. (IceCube Collaboration), First observation of PeV-energy neutrinos with IceCube, Phys. Rev. Lett. 111, 021103 (2013).
  4. IceCube Collaboration, Evidence for high-energy extraterrestrial neutrinos at the IceCube detector, Science 342, 1242856 (2013).
  5. M. G. Aartsen et al. (IceCube Collaboration), Neutrino emission from the direction of the blazar TXS 0506+056 prior to the IceCube-170922A alert, Science 361, 147 (2018).
  6. R. Abbasi et al. (IceCube Collaboration), Evidence for neutrino emission from the nearby active galaxy NGC 1068, Science 378, 538 (2022).
  7. R. Abbasi et al. (IceCube Collaboration), Observation of high-energy neutrinos from the Galactic plane, Science 380, adc9818 (2023).
  8. R. Abbasi et al., A convolutional neural network based cascade reconstruction for the IceCube neutrino observatory, J. Instrum. 16, P07041 (2021).
  9. M. Huennefeld et al. (IceCube Collaboration), Combining maximum-likelihood with deep learning for event reconstruction in IceCube, Proc. Sci. ICRC2021 (2021) 1065 [arXiv:2107.12110].
  10. R. Abbasi et al. (IceCube Collaboration), Graph neural networks for low-energy event classification & reconstruction in IceCube, J. Instrum. 17, P11003 (2022).
  11. I. Kharuk, G. Safronov, A. Matseiko, and A. Leonov, Machine learning in Baikal-GVD experiment, Proc. Sci. ICRC2023 (2023) 1077.
  12. P. Eller (IceCube Collaboration), Public kaggle competition “IceCube—neutrinos in deep ice”, in Proceedings of the 38th International Cosmic Ray Conference (2023), arXiv:2307.15289.
  13. C. De Sio (KM3NeT Collaboration), Machine learning in KM3NeT, EPJ Web Conf. 207, 05004 (2019).
  14. C. Mo, F. Hu, L. Li, and D. Xu (TRIDENT Collaboration), Reconstruction of track-like event in TRIDENT based on a submanifold sparse convolutional network, Proc. Sci. ICRC2023 (2023) 1205.
  15. S. Reck, D. Guderian, G. Vermariën, and A. Domi (KM3NeT Collaboration), Graph neural networks for reconstruction and classification in KM3NeT, J. Instrum. 16, C10011 (2021).
  16. N. Choma, F. Monti, L. Gerhardt, T. Palczewski, Z. Ronaghi, Prabhat, W. Bhimji, M. M. Bronstein, S. R. Klein, and J. Bruna (IceCube Collaboration), Graph neural networks for IceCube signal classification, arXiv:1809.06166.
  17. F. J. Yu, N. Kamp, and C. A. Argüelles, Learning efficient representations of neutrino telescope events, arXiv:2410.13148.
  18. M. Jin, Y. Hu, and C. A. Argüelles, Two Watts is all you need: Enabling in-detector real-time machine learning for neutrino telescopes via edge computing, J. Cosmol. Astropart. Phys. 06 (2024) 026.
  19. T. Zhu, M. Jin, and C. A. Argüelles, Comparison of geometrical layouts for next-generation large-volume Cherenkov neutrino telescopes, arXiv:2407.19010.
  20. A. Radovic, M. Williams, D. Rousseau, M. Kagan, D. Bonacorsi, A. Himmel, A. Aurisano, K. Terao, and T. Wongjirad, Machine learning at the energy and intensity frontiers of particle physics, Nature (London) 560, 41 (2018).
  21. A. Li, Z. Fu, L. A. Winslow, C. Grant, H. Song, H. Ozaki, I. Shimizu, and A. Takeuchi, KamNet: An integrated spatiotemporal deep neural network for rare event searches in KamLAND-Zen, Phys. Rev. C 107, 014323 (2023).
  22. Z. Imani, T. Wongjirad, and S. Aeron, Score-based diffusion models for generating liquid argon time projection chamber images, Phys. Rev. D 109, 072011 (2024).
  23. 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).
  24. P. Abratenko et al. (MicroBooNE Collaboration), Semantic segmentation with sparse convolutional neural network for event reconstruction in MicroBooNE, Phys. Rev. D 103, 052012 (2021).
  25. A. Aurisano, A. Radovic, D. Rocco, A. Himmel, M. D. Messier, E. Niner, G. Pawloski, F. Psihas, A. Sousa, and P. Vahle, A convolutional neural network neutrino event classifier, J. Instrum. 11, P09001 (2016).
  26. L. Dominé and K. Terao (DeepLearnPhysics Collaboration), Scalable deep convolutional neural networks for sparse, locally dense liquid argon time projection chamber data, Phys. Rev. D 102, 012005 (2020).
  27. F. Drielsma, K. Terao, L. Dominé, and D. H. Koh, Scalable, end-to-end, deep-learning-based data reconstruction chain for particle imaging detectors, Proceedings of the 34th Conference on Neural Information Processing Systems (2021), arXiv:2102.01033.
  28. S. Aiello et al. (KM3NeT Collaboration), Sensitivity of the KM3NeT/ARCA neutrino telescope to point-like neutrino sources, Astropart. Phys. 111, 100 (2019).
  29. A. D. Avrorin et al. (Baikal-GVD Collaboration), Baikal-GVD: Status and prospects, EPJ Web Conf. 191, 01006 (2018).
  30. M. Agostini et al. (P-ONE Collaboration), The pacific ocean neutrino experiment, Nat. Astron. 4, 913 (2020).
  31. M. G. Aartsen et al. (IceCube-Gen2 Collaboration), IceCube-Gen2: The window to the extreme Universe, J. Phys. G 48, 060501 (2021).
  32. Z. P. Ye et al., A multi-cubic-kilometre neutrino telescope in the western Pacific Ocean, arXiv:2207.04519.
  33. T.-Q. Huang, Z. Cao, M. Chen, J. Liu, Z. Wang, X. You, and Y. Qi, Proposal for the high energy neutrino telescope, Proc. Sci. ICRC2023 (2023) 1080.
  34. Z. Wang, J. Chen, and S. C. Hoi, Deep learning for image superresolution: A survey, IEEE Trans. Pattern Anal. Mach. Intell. 43, 3365 (2020).
  35. Y. Fukuda et al. (Super-Kamiokande Collaboration), The Super-Kamiokande detector, Nucl. Instrum. Methods Phys. Res., Sect. A 501, 418 (2003).
  36. K. Abe et al. (Hyper-Kamiokande Collaboration), Hyper-Kamiokande design report, arXiv:1805.04163.
  37. A. Abusleme et al. (JUNO Collaboration), JUNO physics and detector, Prog. Part. Nucl. Phys. 123, 103927 (2022).
  38. M. Askins et al. (Theia Collaboration), THEIA: An advanced optical neutrino detector, Eur. Phys. J. C 80, 416 (2020).
  39. F. J. Yu, https://github.com/felixyu7/nt_mlreco (2024).
  40. J. Lazar, S. Meighen-Berger, C. Haack, D. Kim, S. Giner, and C. A. Argüelles, prometheus: An open-source neutrino telescope simulation, Comput. Phys. Commun. 304, 109298 (2024).
  41. P. Iakubovskii, Segmentation models pytorch, https://github.com/qubvel/segmentation_models.pytorch (2019).
  42. F. J. Yu, J. Lazar, and C. A. Argüelles, Trigger-level event reconstruction for neutrino telescopes using sparse submanifold convolutional neural networks, Phys. Rev. D 108, 063017 (2023).
  43. R. Abbasi et al. (IceCube Collaboration), An improved mapping of ice layer undulations for the IceCube neutrino observatory, Proc. Sci. ICRC2023 (2023) 975 [arXiv:2307.13951].

Outline

Information

Phys. Rev. D 111, L041301– Published 5 February, 2025
  • Received 3 September 2024
  • Accepted 6 January 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