Abstract
The Hyper-Kamiokande (Hyper-K) observatory, the successor to the Super-Kamiokande (Super-K) experiment, will be the largest underground water Cherenkov neutrino observatory in the world. Hyper-K will be utilized to observe high energy neutrinos coming from the Sun, supernovas, and a neutrino beam from the Japan Proton Accelerator Research Complex (J-PARC). Hyper-K’s ultimate goal is to measure neutrino properties accurately, leading to quantifying the associated Charge-Parity violation in the leptonic sector, and thus to enhance the current understanding of the matter-antimatter asymmetry in the universe. Due to Hyper-K’s construction beginning in 2020, nowadays it’s a suitable time to perform Monte-Carlo simulations and test different Machine Learning (ML) analysis techniques such as Convolutional Neural Networks (CNN) for prototype development, besides exploring different detector configurations. The present chapter describes the participation of Mexico in the Hyper-K observatory, focusing on how ML and supercomputing can be used to design sensors, like the ones found in multi-photomultiplier tube (mPMT) arrays, to be tested on experiments and Hyper-K prototypes. Preliminary results show that ML techniques are good at distinguishing between muon and electron neutrino candidates, displaying comparable results to those of the likelihood analysis used on Super-K.
S. Cuen-Rochin, E. de la Fuente, A. K. Tomatani-Sanchez:
International representative of México on Hyper-K Collaboration
In memoriam of Dr. Luis Alberto Gutiérrez Díaz de León\(^\dagger \) (1975–2020)
J. L. Flores: Chair of the PRODEP-SEP cuerpo académico UDG-CA-499 (Hyper-K).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Referring to Neutrinos, Cosmic-Rays, and Gamma-Rays.
- 2.
Quarks and leptons are fermions. Fermions are the fundamental blocks composing matter. Bosons are the carriers of the fundamental forces described in the Standard Model of particle physics.
- 3.
Optical blue-violet light (peaking at \(\lambda \sim 420~\mathrm{nm}\)) radiated in a medium described by the refraction index (n), such that the irradiating particle travels with a speed (c\(_p\)) greater than the speed of the light in a medium (c). The speed of light in water is \(\frac{3}{4}c\). If c\(_p > \frac{3}{4}c\), Cherenkov light is produced in water in a cone-shaped geometry, with an aperture angle of \(41^{\circ }\).
- 4.
Formerly managed by CUCEI-UdeG, organized by Secretaria académica and División de Ciencias Básicas with E. de la Fuente (UDG-CA-499. Also for UdeG@HAWC Observatory).
- 5.
This office was the CGTI-UdeG, with general coordinator (head) at that time: Dr. Luis Alberto Gutíerrez Díaz de León\(^\dagger \) (RIP: 1975–2020), promotor of CADS at UdeG.
- 6.
Managed by the Coordinación General de Servicios Administrativos e Infraestructura Tecnológica (CGSAIT)-UdeG since 2020: http://cads.cgti.udg.mx/.
- 7.
- 8.
- 9.
- 10.
The scientific topics can be summarized as CP Violation, mass hierarchy determination (where the neutrino-nucleus scattering physics is revolutionized), neutrino astronomy (Sun and Supernova), and the proton decay discovery (information about the unification scale and gauge group).
- 11.
- 12.
- 13.
Ran by Mtra. María Guadalupe Cid Escobedo as provost of CGSAIT, and Ing. German Ramírez Arias, head of database and operations office at the CGSAIT.
- 14.
- 15.
- 16.
The lack of generality and hence failure to classify unclassified datasets displayed by a learning algorithm (due to the training prescriptions and configurations), leading to learned patterns too closely or exactly resembling those associated with a particular set of data.
- 17.
An epoch is one complete iteration of the dataset through the learning network.
References
M.G. Aartsen et al., Multimessenger observations of a flaring blazar coincident with high-energy neutrino IceCube-170922A. Science 361, 147–151 (2018)
A.U. Abeysekara et al., Very-high-energy particle acceleration powered by the jets of the microquasar SS 433. Nature 562, 82–85 (2018)
A.U. Abeysekara et al., Multiple galactic sources with emission above 56 TeV detected by HAWC. Phys. Rev. Lett. 124, 021102 (2020)
A.U. Abeysekara et al., Constraints on Lorentz invariance violation from HAWC observations of gamma rays above 100 TeV. Phys. Rev. Lett. 124, 131101 (2020)
T. Kajita et al., Establishing atmospheric neutrino oscillations with Super-Kamiokande. Nucl. Phys. B 908, 14–29 (2016)
T. Kajita, Kamiokande and Super-Kamiokande collaborations, Proceedings Supplements of Atmospheric neutrino results from Super-Kamiokande and Kamiokande -Evidence for\({\nu }_{\mu } \)oscillations-Nuclear Physics B 77 (1999), pp. 123-132
M. Fukugita, T. Yanagida, Barygenesis without grand unification. Phys. Lett. B 174, 45–47 (1986)
J. Migenda, The hyper-Kamiokande collaboration, Supernova Model Discrimination with Hyper-Kamiokande Astrophys. J. Accepted (2020). arXiv: 2101.05269
S. Fukuda, Super-Kamiokande collaboration. Super-Kamiokande Detector Nucl. Instrum. Methods Phys. Res. Sect. A 501, 418–462 (2017)
Hyper-Kamiokande Proto-Collaboration. Hyper-Kamiokande Design Report. http://arxiv.org/abs/1805.04163arxiv:1805.04163 (2018), pp. 1–325
Hyper-K Collaboration Proposal for A Water Cherenkov Test Beam Experiment for Hyper-Kamiokande and Future Large-scale Water-based Detectors Scientific Committee Paper. Report number CERN-SPSC-2020-005 (2020), SPSC-P-365, https://cds.cern.ch/record/2712416
S. Cuen-Rochin, Multi-photomultiplier tube module development for the next generation Hyper-Kamiokande neutrino experiment. In the 20th International Workshop on Next generation Nucleon Decay and Neutrino Detectors (NNN19), The University of Medellin, November 7-9 (2019). https://indico.cern.ch/event/835190/contributions/3613897/
K. Abe, The T2K collaboration. T2K Exp. Nucl. Instrum. Methods Phys. Res. Sect. A 659, 106–135 (2011)
The Worldwide LHC Computing Grid. In CERN computing web site (2020). Retrieved from https://home.cern/science/computing/worldwide-lhc-computing-grid
T. Mitchell, Machine learning. 1st Edn (McGraw Hill Higher Education, 1997)
C.M. Bishop, Pattern Recognition and Machine Learning, 2nd edn (Springer, 2006)
E. Alpaydin, Introduction to Machine Learning, 2nd edn. (The MIT Press, 2014)
I. Goodfellow, Y. Bengio, A. Courville, Deep Learning (Adaptive Computation and Machine Learning series), 1st edn. (The MIT Press, 2016)
Hyper-K Canada, Machine Learning Workshop. University of Victoria, April 15-17 (2019). https://mlw.hyperk.ca/
S. Chintala, Neural network tutorial, in Deep Learning with pytorch: A 60 minute blitz. Retrived from https://pytorch.org/tutorials/beginner/blitz/neural_networks_tutorial.html (2020)
Y. LeCun, et al., Gradient-based learning applied to document recognition, in Proceedings of the IEEE, (1998). http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf
F. Psihas, M. Groh, C. Tunnell, K. Warburton. A review on machine learning for neutrino experiments. Int. J. Modern Phys. (2020). arXiv:2008.01242v1
S. Brice, The results of a neural network statistical event class analysis. Sudbury Neutrino Observatory Technical Report, SNO-STR-96-001 (1996)
ImageNet. http://www.image-net.org/
K. Simonyan, A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition (2015). arXiv:1409.1556
C. Szegedy, S. Ioffe, V. Vanhoucke, A. Alemi, Inception-v4, Inception-ResNet and the Impact of Residual Connectios on Learning (2016). arXiv:1602.07261
A. Aurisano, et al., A Convolutional Neural Network Neutrino Event Classifier (2016). arXiv:1604.01444v3
N. Choma, et al., Graph Neural Networks for IceCube Signal Classification (2018). arXiv:1809.06166
R. Li, Z. You, Y. Zhang, Deep learning for signal and background discrimination in liquid based neutrino experiment. J. Phys. Conf. Ser. 1085, 042037 (2018)
C. Fanelli, Machine Learning for Imaging Cherenkov Detectors (2020). https://doi.org/10.1088/1748-0221/15/02/C02012
J. Renner et al., Background rejection in NEXT using deep neural networks. J. Instrum. 12, T01004–T01004 (2017)
F. Psihas et al., Context-enriched identification of particles with a convolutional network for neutrino events. Phys. Rev. D 100, 073005 (2019)
Cedar—CC Doc. Retrieved from https://docs.computecanada.ca/wiki/Cedar in 2020
T. Dealtry, A. Himmel, J. Hoppenau, J. Lozier, Water Cherenkov Simulator (WCSim). Retrieved from https://github.com/WCSim/WCSim (2020)
D. P. Kingma, J. Ba, Adam: a method for stochastic optimization, in The 3rd International Conference on Learning Representations (ICLR). Ithaca, NY: arXiv.org, San Diego, CA, USA (2015)
Neutrino Physics and Machine Learning (NPML): Lightning Talks https://indico.slac.stanford.edu/event/377/timetable/ 17 and 19 Jun (2020)
Acknowledgements
The authors thank the anonymous referees for useful comments that enhance the work. EdelaF thanks to Prof. Takaki Kajita for accepting the invitation to visit Mexico, and SEP-PRODEP UDG-CA-499 for financial and logistic support during the sabbatical year (2021). He also thanks Ruth Padilla, Oscar Blanco, Humberto Pulido, Gilberto Gómez, for all academic and partial financial support to attend to the 10th Hyper-K Proto-collaboration Meeting at the University of Tokyo, as well as Guillermo Torales and José Luis García-Luna (UdeG-CA-499) for useful collaborative work. SCR and EdelaF are very thankful for the invitation to the 10th Hyper-Kamiokande Proto-Collaboration Meeting to Masato Shiozawa and Akira Kanoka. We also thank Francesca Di Lodovico, Yoshitaka Itow, and the rest of the steering committee for accepting the participation of Mexico in Hyper-K. We thanks Thomas Lindner, Matej Pavin, and John Walker for his guidance in mPMT development. We also thank Dean Karlen, Patrick de Perio, Nick Prouse, Kazuhiro Terao, Wojciech Fedorko and the WatChMaL(Water Cherenkov Machine Learning: working group developing machine learning for water Cherenkov detectors https://www.watchmal.org/) group for organizing and generating the simulated data for the Machine Learning Workshop at the University of Victoria (2019) from which we learned how to apply ML techniques to particle identification. We also thanks Carlos Téllez and Alfredo Figarola from ITESM-Campus Guadalajara. We are very grateful for the thoughtful suggestions, comments, and editing of Richard Mischke that helped to improve our manuscript.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Cuen-Rochin, S. et al. (2021). Machine Learning Application for Particle Physics: Mexico’s Involvement in the Hyper-Kamiokande Observatory. In: Oliva, D., Houssein, E.H., Hinojosa, S. (eds) Metaheuristics in Machine Learning: Theory and Applications. Studies in Computational Intelligence, vol 967. Springer, Cham. https://doi.org/10.1007/978-3-030-70542-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-70542-8_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70541-1
Online ISBN: 978-3-030-70542-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)