Abstract
In this paper, we use artificial neural networks (ANNs) techniques to reconstruct the mass composition of high energy cosmic rays. We train artificial neural networks using a high-performance computing cluster with 12 Nvidia Tesla V100 GPUs from the Laboratorio Nacional de Supercómputo del Sureste de México (LNS), and a database of approximately 4.8 million Monte Carlo (MC) simulations of extensive air showers (EAS) using the hadronic interaction model Sibyll 2.3 with two primaries: Protons and Irons, between the energy ranges of 1017 to 1019 eV. The longitudinal development profile of EAS produced by ultra-high energy cosmic rays carries physical information related to the interaction properties of the primary particles with atmospheric nuclei. We extract from the MC values of the longitudinal profile of air showers trough atmospheric depth on different energy ranges, the variable called Xmax (depth of EAS maximum development), which is strongly correlated with the composition of the primary cosmic ray, in order to predict Xmax values for very high-energy cosmic rays by using ANNs. These methods can be used to train a neural network with real EAS events and predict outcomes where statistical limitations with normal means cannot say much.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dunn, W.L., Shultis, J.K.: The basis of Monte Carlo. Explor. Monte Carlo Methods 21–46 (2012). https://doi.org/10.1016/b978-0-444-51575-9.00002-6
Abu-Zayyad, T., et al.: The cosmic-ray energy spectrum observed with the surface detector of the telescope array experiment. Astrophys. J. Lett. 768(1), L1 (2013). https://doi.org/10.1088/2041-8205/768/1/l1
Carvalho Jr., W.R., Alvarez-Muñiz, J.: Determination of cosmic-ray primary mass on an event-by-event basis using radio detection. Astropart. Phys. 109, 41–49 (2019). https://doi.org/10.1016/j.astropartphys.2019.02.005
Gaisser, T.K., Hillas, A.M.: Reliability of the method of constant intensity cuts for reconstructing the average development of vertical showers. In: Proceedings 15th International Cosmic Ray Conference, vol. 8, pp. 353–357 (1977)
Erdmann, M., Glombitza, J., Walz, D.: A deep learning-based reconstruction of cosmic ray-induced air showers. Astropart. Phys. 97, 46–53 (2018). https://doi.org/10.1016/j.astropartphys.2017.10.006
Guillén, A., et al.: Deep learning techniques applied to the physics of extensive air showers. Astropart. Phys. 111, 12–22 (2019). https://doi.org/10.1016/j.astropartphys.2019.03.001
Paschalis, P., Sarlanis, C., Mavromichalaki, H.: Artificial neural network approach of cosmic ray primary data processing. Solar Phys. 282(1), 303–318 (2012). https://doi.org/10.1007/s11207-012-0125-3
Bergmann, T., et al.: One-dimensional hybrid approach to extensive air shower simulation. Astroparticle Phys. 26(6), 420–432 (2007). https://doi.org/10.1016/j.astropartphys.2006.08.005
Pierog, T., et al.: First results of fast one-dimensional hybrid simulation of EAS using conex. Nuclear Phys. B – Proc. Suppl. 151(1), 159–162 (2006). https://doi.org/10.1016/j.nuclphysbps.2005.07.029
Ahn, E., Engel, R., Gaisser, T.K., Lipari, P., Stanev, T.: Cosmic ray interaction event generator SIBYLL 2.1. Phys. Rev. D 80(9), 094003 (2009). https://doi.org/10.1103/physrevd.80.094003
Laboratorio Nacional de Supercómputo del Sureste de México - LNS. Benemérita Universidad Autónoma de Puebla (n.d.). http://www.lns.org.mx/
Brownlee, J.: Deep Learning with Python: Develop Deep Learning Models on Theano and TensorFlow Using Keras. Machine Learning Mastery (2016)
Hsu, C.W., Chang, C.C., Lin, C.J.: A practical guide to support vector classification (2003). http://ntur.lib.ntu.edu.tw/bitstream/246246/2006092712291477314/1/guide.pdf
Stathakis, D.: How many hidden layers and nodes? Int. J. Remote Sens. 30(8), 2133–2147 (2009). https://doi.org/10.1080/01431160802549278
Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.: On large-batch training for deep learning: generalization gap and sharp minima (2016). https://arxiv.org/abs/1609.04836
Acknowledgments
The authors thankfully acknowledge computer resources, technical advice and support provided by Laboratorio Nacional de Supercómputo del Sureste de México (LNS), a member of the CONACYT national laboratories.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Varela, E., Gabriel, I., Quiroz, A., Báez, L.A., Salazar, H., Villaseñor, L. (2019). Artificial Neural Networks for the Study of Cosmic Rays. In: Ruiz, P., Agredo-Delgado, V. (eds) Human-Computer Interaction. HCI-COLLAB 2019. Communications in Computer and Information Science, vol 1114. Springer, Cham. https://doi.org/10.1007/978-3-030-37386-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-37386-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37385-6
Online ISBN: 978-3-030-37386-3
eBook Packages: Computer ScienceComputer Science (R0)