Signal Separation from Thermal Neutrons in Electron–Neutron Detectors Using Convolutional Neural Nets in the ENDA Experiment

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

The electron–neutron detector array (ENDA) is being created in China within the large high-altitude air shower observatory (LHAASO) project. The concept of the array is to simultaneously record the electromagnetic and hadronic components of extensive air showers (EAS) with EN detectors. To estimate the number of hadrons in an EAS, the array detectors record secondary thermal neutrons delayed relative to the shower front. Some of the delayed pulses are created by the simultaneous passage of several charged particles through the scintillator (the signal from one particle lies below the detection threshold) and by the photomultiplier noise. We propose a neutron pulse separation method for EN detectors using convolutional neural networks and make a comparison with the baseline method being currently applied at the installation.

About the authors

K. O Kurinov

Institute for Nuclear Research, Russian Academy of Sciences

Email: kyrinov.ko@gmail.com
117312, Moscow, Russia

D. A Kuleshov

Institute for Nuclear Research, Russian Academy of Sciences

Email: kyrinov.ko@gmail.com
117312, Moscow, Russia

A. A Lagutkina

Moscow Institute of Physics and Technology

Email: kyrinov.ko@gmail.com
141701, Dolgoprudnyi, Moscow oblast, Russia

Yu. V Sten'kin

Institute for Nuclear Research, Russian Academy of Sciences; Moscow Institute of Physics and Technology

Email: kyrinov.ko@gmail.com
117312, Moscow, Russia; 141701, Dolgoprudnyi, Moscow oblast, Russia

O. B Shchegolev

Institute for Nuclear Research, Russian Academy of Sciences; Moscow Institute of Physics and Technology

Author for correspondence.
Email: kyrinov.ko@gmail.com
117312, Moscow, Russia; 141701, Dolgoprudnyi, Moscow oblast, Russia

References

  1. Yu. V. Stenkin, Nucl. Phys. B Proc. Suppl. 196, 293 (2009).
  2. O. B. Shchegolev, V. V. Alekseenko, D. A. Kuleshov et al., J. Phys. Conf. Ser. 1690 (2020).
  3. Yu. V. Stenkin, V. V. Alekseenko, Danzengluobu et al., Bull.Russ. Acad. Sci. Phys. 85, 405 (2021).
  4. О. Б. Щеголев, В. В. Алексеенко, Ю. В. Стенькин и др., Изв. РАН, сер. физ. 83, 691 (2019).
  5. Ю. В. Стенькин, О. Б. Щеголев, Изв. РАН, сер. физ. 81, 541 (2017).
  6. Yu. V. Stenkin, V. V. Alekseenko, D. M. Gromushkin et al., Chinese Phys. C 37, 015001 (2013).
  7. G. Ranucci, Nucl. Instr. Meth. A 354, 389 (1995).
  8. F. Pino, L. Stevanato, D. Cester et al., J. Instrument. 10, T08005 (2015).
  9. J. K. Polack, M. Flaska, A. Enqvist et al., Nucl. Instr. Meth. A 795, 253 (2015).
  10. E. Doucet, T. Brown, P. Chowdhury et al., Nucl. Instr. Meth. A 954, 161201 (2020).
  11. T. S. Sanderson, C. D. Scott, M. Flaska et al., IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC), 199 (2012).
  12. J. Gri ths, S. Kleinegesse, D. Saunders et al., Machine Learning: Science and Technology 1, 045022 (2020).
  13. Д. М. Громушкин, А. А. Петрухин, Ю. В. Стенькин и др., Изв. РАН, сер. физ. 73, 425 (2009).
  14. Ю. В. Стенькин, В. В. Алексеенко, А. С. Багрова и др., Изв. РАН, сер. физ. 81, 179 (2017).
  15. W. S. Cleveland, American Statistician 35, 54 (1981).
  16. P. Refaeilzadeh, L. Tang, and H. Liu, Encyclopedia of Database Systems 5, 532 (2009).
  17. A. Paszke, S. Gross, F. Massa et al., Advances in Neural Information Processing Systems 32, 8026 (2019).
  18. J. Deng, J. Guo, T. Liu et al., arXiv: 1801.07698.
  19. L. Van der Maaten and G. Hinton, J. Machine Learning Res. 9, 2579 (2008).
  20. D. P. Kingma and J. Ba, arXiv:1412.6980.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2023 Russian Academy of Sciences