Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data

Ilya Lagoida; Sergei Voronov; Natalia Barbashina; Ivan Astapov

doi:10.12737/szf-123202606

UDC 523.98 UDC 528.029.69

2 more Collapse

MACHINE-LEARNING METHOD FOR RECONSTRUCTING NEAR-EARTH LOW-ENERGY COSMIC RAY FLUXES FROM GROUND-BASED SOPO NEUTRON MONITOR DATA Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data

АА Аа

Published in Solnechno-Zemnaya Fizika · Volume 12, Issue 3 · Pages 61–70 · Rubric: Results of current research

DOI: https://doi.org/10.12737/szf-123202606 · EDN: SXZEVM

Received: 10.12.2025 Accepted: 26.02.2026 Published: 19.09.2026

Authors

Ilya Lagoida

Sergei Voronov

Natalia Barbashina

Ivan Astapov

Ilya Lagoida

Academic degree: candidate of physical and mathematical sciences

National Research Nuclear University MEPhI Russian Federation · Moscow

Sergei Voronov

National Research Nuclear University MEPhI Russian Federation · Moscow

Natalia Barbashina

National Research Nuclear University MEPhI Russian Federation · Moscow

Ivan Astapov

National Research Nuclear University MEPhI Russian Federation · Moscow

ABSTRACT

Nowadays, there are a large number of ground-based neutron monitors. These detectors measure neutron fluxes produced by the interaction of primary cosmic rays (CR) with Earth’s atmosphere. Since their invention in the 1950s, they have become very popular for studying variations of CR intensity on different time scales. These detection systems are stable and therefore can conduct continuous measurements for decades. However, they exhibit low sensitivity to cosmic ray fluxes with energies ≤1 GeV, whereas heliospheric variations of these fluxes are most pronounced at lower energies. The rapid growth of the space industry has made it possible to perform direct measurements of CR fluxes by a variety of scientific instruments installed on board spacecraft. Satellite-borne detectors measure cosmic ray fluxes across a wide energy range, from tens of keV up to tens of TeV. Nonetheless, experimental data collected by spacecraft is not always immediately accessible and is often published with a significant delay. Moreover, the radiation in outer space is gradually reducing the efficiency and stability of satellite systems, so their operating time in orbit is limited. Ground-based detectors are less susceptible to radiation damage, and their data is always available for scientific research. Therefore, developing methods to reconstruct top-of-atmosphere CR fluxes from ground-based detector data is increasingly urgent. This paper presents the method for calibrating the high-latitude SOPO neutron monitor by machine-learning algorithms, using data on cosmic proton fluxes with energy >500 MeV from the P11 channel of the proton sensor installed aboard the GOES-16 satellite. The machine model obtained as the result of training was employed to reconstruct the low-energy cosmic ray flux from SOPO data. Then it was compared with actual data from the GOES-16 proton sensor.

KEYWORDS

cosmic rays, Forbush decreases, geomagnetic storm, solar activity

Funding

The work was financially supported by the Ministry of Science and Higher Education of the Russian Federation (Government Assignment No. FSWU-2023-0086)

Text

Text (RU) (PDF)

Read Download

1. Aguilar M., Cavasonza L.A., Ambrosi G., et al. Periodicities in the daily proton fluxes from 2011 to 2019 measured by the Alpha Magnetic Spectrometer on the International Space Station from 1 to 100 GV. Phys. Rev. Lett. 2021, vol. 127, iss. 27, p. 271102. https://doi.org/10.1103/PhysRevLett.127.271102.

2. Alanko K., Usoskin I.G., Mursula K., et al. Heliospheric modulation strength: effective neutron monitor energy. Adv. Space Res. 2003, vol. 32, iss. 4, pp. 615–620. https://doi.org/10.1016/S0273-1177(03)00348-X.

3. Aspinall M.D., Alton T.L., Binnersley C.L., et al. A new ground level neutron monitor for space weather assessment. Scientific Rep. 2024, vol. 14, iss. 1, p. 7174. https://doi.org/10.1038/s41598-024-57583-0.

4. Banerjee C., Mukherjee T., Pasiliao Jr.E. An empirical study on generalizations of the ReLU activation function. Proc. ACM southeast conference. Kennesaw, GA, USA, 2019, pp. 164–167. https://doi.org/10.1145/3299815.3314450.

5. Battiston R. High precision cosmic ray physics with AMS-02 on the International Space Station. La Rivista del Nuovo Cimento. 2020, vol. 43, iss. 7, pp. 319–384. https://doi.org/10.1007/s40766-020-00007-2.

6. Blasi P. The origin of galactic cosmic rays. Astron. Astrophys. Rev. 2013, vol. 21, iss. 1, pp. 1–73. https://doi.org/10.1007/s00159-013-0070-7.

7. Bruno A. Calibration of the GOES 13/15 high‐energy proton detectors based on the PAMELA solar energetic particle observations. Space Weather. 2017, vol. 15, iss. 9, pp. 1191–1202. https://doi.org/10.1002/2017SW001672.

8. Bruno A., Bazilevskaya G.A., Boezio M., et al. Solar energetic particle events observed by the PAMELA mission. Astrophys. J. 2018, vol. 862, iss. 2, p. 97. https://doi.org/10.3847/1538-4357/aacc26.

9. Bykov A.M., Ellison D.C., Marcowith A., et al. Cosmic ray production in supernovae. Space Sci. Rev. 2018, vol. 214, iss. 1, p. 41. https://doi.org/10.1007/s11214-018-0479-4.

10. Caballero‐Lopez R.A., Moraal H. Limitations of the force field equation to describe cosmic ray modulation. J. Geophys. Res.: Space Phys. 2004, vol. 109, iss. A1, p. A01101. https://doi.org/10.1029/2003JA010098.

11. Calligaro C., Gatti U. Rad-hard Semiconductor Memories. River Publishers, 2018, 416 p. https://doi.org/10.1201/9781003339182-1.

12. Cane H.V. Coronal mass ejections and Forbush decreases. Space Sci. Rev. 2000, vol. 93, iss. 1, pp. 55–77. https://doi.org/10.1023/A:1026532125747.

13. Chu W., Yang Y., Xu S., et al. Study on long-term variation characteristics of geomagnetic cutoff rigidities of energetic protons caused by long-term variation of geomagnetic field. Frontiers in Earth Science. 2022, vol. 10, p. 818788. https://doi.org/10.3389/feart.2022.818788.

14. Curto J.J. Geomagnetic solar flare effects: A review. J. Space Weather and Space Climate. 2020, vol. 10, p. 27. https://doi.org/10.1051/swsc/2020027.

15. Desai M., Giacalone J. Large gradual solar energetic particle events. Living Rev. in Solar Phys. 2016, vol. 13, iss. 1, p. 3. https://doi.org/10.1007/s41116-016-0002-5.

16. Dong X.L., Yao Y.H., Guo Y.Q., et al. New understanding of nuclei spectra properties observed by the AMS-02 experiment. Phys. Rev. D. 2024, vol. 109, iss. 6, p. 063027. https://doi.org/10.1103/PhysRevD.109.063027.

17. Gabici S. Low-energy cosmic rays: Regulators of the dense interstellar medium. Astron. Astrophys. Rev. 2022, vol. 30, iss. 1, p. 4. https://doi.org/10.1007/s00159-022-00141-2.

18. Gleeson L.J., Axford W.I. Solar modulation of galactic cosmic rays. Astrophys. J. 1968, vol. 154, p. 1011. https://doi.org/10.1086/149822.

19. Goodman S.J., Schmit T.J., Daniels J., et al. The GOES-R series: A new generation of geostationary environmental satellites. Elsevier, 2020, pp. 243–250. https://10.1016/B978-0-12-814327-8.00019-3.

20. Gopalswamy N., Yashiro S., Michalek G., et al. The SOHO/LASCO CME catalog. Earth, Moon, and Planets. 2009, vol. 104, iss. 1, pp. 295–313. https://doi.org/10.1007/s11038-008-9282-7.

21. Hatton C.J., Carmichael H. Experimental investigation of the NM-64 neutron monitor. Canadian J. Phys. 1964, vol. 42, iss. 12, pp. 2443–2472. https://doi.org/10.1139/p64-222.

22. Hu S., Semones E. Calibration of the GOES 6–16 high-energy proton detectors based on modelling of ground level enhancement energy spectra. J. Space Weather and Space Climate. 2022, vol. 12, p. 5. https://doi.org/10.1051/swsc/2022003.

23. Kilpua E., Koskinen H.E., Pulkkinen T.I. Coronal mass ejections and their sheath regions in interplanetary space. Living Rev. Solar Phys. 2017, vol. 14, iss. 1, p. 5. https://doi.org/10.1007/s41116-017-0009-6.

24. Kingma D.P., Ba J. Adam: A method for stochastic optimization. Proc. International Conference on Learning Representations (ICLR). San Diego, CA, USA, 2014. https://doi.org/10.48550/arXiv.1412.6980.

25. Koldobskiy S.A, Usoskin I.G. Reconstruction of solar modulation potential from AMS-02 daily data for the period 2011–2019 and its intercomparison with indirect cosmic-ray measurements. Proc. 38th International Cosmic Ray Conference. Nagoya, Japan, 2024, p. 1325. https://doi.org/10.22323/1.444.1325.

26. Kress B.T., Rodriguez J.V., Boudouridis A., et al. Observations from NOAA’s newest solar proton sensor. Space Weather. 2021, vol. 19, iss. 12, p. e2021SW002750. https://doi.org/10.1029/2021SW002750.

27. Lagoida I.A., Voronov S.A., Mikhailov V.V. Features of Forbush decreases according to satellite and ground based detectors. Physics of Atomic Nuclei. 2024, vol. 87, iss. 2, pp. 86–92. https://doi.org/10.1134/S1063778824020133.

28. Lau M.M., Hann L.K. Review of adaptive activation function in deep neural networks. Proc. Conference on Biomedical Engineering and Sciences (IECBES). Sarawak, Malaysia, 2018, pp. 686–690. https://doi.org/10.1109/IECBES.2018.8626714.

29. Lederer J. Activation functions in artificial neural networks: A systematic overview. arXiv preprint arXiv:2101.09957. 2021. https://arxiv.org/abs/2101.09957.

30. Mertens C.J., Tobiska W.K. Space weather radiation effects on high-altitude/latitude aircraft. Space Weather Effects and Applications. Wiley, 2021, pp. 79–110. https://doi.org/10.1002/9781119815570.ch4.

31. Miroshnichenko L.I. Solar cosmic rays: 75 years of research. Physics-Uspekhi. 2018, vol. 61, iss. 4, p. 323. https://doi.org/10.3367/UFNe.2017.03.038091.

32. Mishev A.L., Koldobskiy S.A., Kovaltsov G.A., et al. Updated neutron‐monitor yield function: Bridging between in situ and ground‐based cosmic ray measurements. J. Geophys. Res.: Space Phys. 2020, vol. 125, iss. 2, p. e2019JA027433. https://doi.org/10.1029/2019JA027433.

33. Mishev A.L., Poluianov S. About the altitude profile of the atmospheric cut-off of cosmic rays: new revised assessment. Solar Phys. 2021, vol. 296, iss. 8, p. 129. https://doi.org/10.1007/s11207-021-01875-5.

34. Moraal H. Cosmic-ray modulation equations. Space Sci. Rev. 2013, vol. 176, iss. 1, pp. 299–319. https://doi.org/10.1007/s11214-011-9819-3.

35. Netrapalli P. Stochastic gradient descent and its variants in machine learning. J. Indian Institute of Science. 2019, vol. 99, iss. 2, pp. 201–213. https://doi.org/10.1007/s41745-019-0098-4.

36. Nielsen M.A. Neural Networks and Deep Learning. San Francisco, CA, USA, Determination press, 2015, 281 p.

37. Oh S.Y., Bieber J.W., Clem J., et al. South Pole neutron monitor forecasting of solar proton radiation intensity. Space Weather. 2012, vol. 10, iss. 5, p. S05004. https://doi.org/10.1029/2012SW000795.

38. Picozza P., Spillantini P., Marcelli L. Cosmic ray direct measurements. Nuclear and Particle Physics Proc. 2018, vol. 297, pp. 207–215. https://doi.org/10.1016/j.nuclphysbps.2018.07.030.

39. Poluianov S., Batalla O. Cosmic-ray atmospheric cutoff energies of polar neutron monitors. Adv. Space Res. 20–22, vol. 70, iss. 9, pp. 2610–2617. https://doi.org/10.1016/j.asr.2022.03.037.

40. Potgieter M.S. Solar modulation of cosmic rays. Living Rev. in Solar Phys. 2013, vol. 10, iss. 1, p. 3. https://doi.org/10.12942/lrsp-2013-3.

41. Potgieter M.S. The charge-sign dependent effect in the solar modulation of cosmic rays. Adv. Space Res. 2014, vol. 53, iss. 10, pp. 1415–1425. https://doi.org/10.1016/j.asr.2013.04.015.

42. Ptuskin V. Propagation of galactic cosmic rays. Astroparticle Physics. 2012, vol. 39, pp. 44–51. https://doi.org/10.1016/j.astropartphys.2011.11.004.

43. Riggi F. The Detection of Extensive Air Showers. Springer, 2023, pp. 155–171. https://doi.org/10.1007/978-3-031-24762-0.

44. Rozelot J.P., Elchin S, Babayev E.S. Variability of the Sun and Sun-like Stars: From Asteroseismology to Space Weather. EDP Sciences, 2018, 238 p. https://doi.org/10.1051/978-2-7598-2196-9.

45. Siruk S.A., Alexandrin S.U., Lagoida I.A., et al. Mountainous regions of the Russian Arctic as a platform for space weather research Sol.-Terr. Phys. 2025, vol. 11, iss. 2, pp. 139–143. DOI:https://doi.org/10.12737/stp-112202513.

46. Strauss D.T., Poluianov S., Van Der Merwe C., et al. The mini-neutron monitor: A new approach in neutron monitor design. J. Space Weather and Space Climate. 2020, vol. 10, p. 39. https://doi.org/10.1051/swsc/2020038.

47. Tomsia M., Cieśla J., Śmieszek J., et al. Long-term space missions effects on the human organism: what we do know and what requires further research. Annals of Agricultural and Environmental Medicine. 2024, vol. 31, iss. 2, pp. 175–181. https://doi.org/10.26444/aaem/186595.

48. Usoskin I.G., Alanko‐Huotari K., Kovaltsov G.A., et al. Helio-spheric modulation of cosmic rays: Monthly reconstruction for 1951–2004. J. Geophys. Res.: Space Phys. 2005, vol. 110, iss. A12, p. A12108. https://doi.org/10.1029/2005JA011250.

49. Väisänen P., Usoskin I., Kähkönen R., et al. Revised reconstruction of the heliospheric modulation potential for 1964–2022. J. Geophys. Res.: Space Phys. 2023, vol. 128, iss. 4, p. e2023JA031352. https://doi.org/10.1029/2023JA031352.

50. Wang Q., Ma Y., Zhao K. A comprehensive survey of loss functions in machine learning. Annals of Data Science. 2022, vol. 9, iss. 2, pp. 187–212. https://doi.org/10.1007/s40745-020-00253-5.

51. Zhang N., Shen S.L., Zhou A., et al. Investigation on performance of neural networks using quadratic relative error cost function. IEEE Access. 2019, vol. 7, pp. 106642–106652. https://doi.org/10.1109/ACCESS.2019.2930520.

52. URL: https://www.airbus.com/en/newsroom/press-releases/2025-11-airbus-update-on-a320-family-precautionary-fleet-action (accessed May 12, 2026).

53. URL: https://omniweb.gsfc.nasa.gov/form/dx1.html (accessed May 12, 2026).

54. URL: https://github.com/fchollet/keras (accessed May 12, 2026).

PDF Text JATS XML

Editor-in-Chief

Geliy Zherebtsov

solater@iszf.irk.ru

Deputy Editor-in-Chief

Aleksandr Stepanov

stepanov@gaoran.ru

Deputy Editor-in-Chief

Alexander Potapov

potapov@iszf.irk.ru

Executive Secretary of Editorial Board

Natalia Polyushkina

npol@iszf.irk.ru

downloads

GOST

Lagoida I. A., Voronov S. A., Barbashina N. S., Astapov I. I. Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data // Solnechno-Zemnaya Fizika. 2025. no. 3. pp. 61-70. DOI: https://doi.org/10.12737/szf-123202606. EDN: SXZEVM. (Date of access 26.09.2026).

MLA

Ilya Lagoida, Voronov S. A., Barbashina N. S., Astapov I. I.. "Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data." Solnechno-Zemnaya Fizika 12.3 (2025): 61-70. DOI: https://doi.org/10.12737/szf-123202606. EDN: SXZEVM.

APA

Lagoida I. A., Voronov S. A., Barbashina N. S., Astapov I. I. (2025). Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data. Solnechno-Zemnaya Fizika, 12(3), 61-70. https://doi.org/10.12737/szf-123202606 EDN: SXZEVM.

Chicago

Ilya Lagoida, Voronov S. A., Barbashina N. S., Astapov I. I.. "Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data." Solnechno-Zemnaya Fizika 12, no. 3 (2025): 61-70. https://doi.org/10.12737/szf-123202606. EDN: SXZEVM.

WIKI

{{cite journal | author = Lagoida I. A., Voronov S. A., Barbashina N. S., Astapov I. I. | title = Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data | journal = Solnechno-Zemnaya Fizika | year = 2025 | volume = 12 | issue = 3 | pages = 61-70 | doi = 10.12737/szf-123202606 }} EDN: SXZEVM

Copy

Export: BibTeX EndNote RefMan RusMARC

MACHINE-LEARNING METHOD FOR RECONSTRUCTING NEAR-EARTH LOW-ENERGY COSMIC RAY FLUXES FROM GROUND-BASED SOPO NEUTRON MONITOR DATA Machine-learning method for reconstructing near-Earth low-energy cosmic ray fluxes from ground-based SOPO neutron monitor data

Confirmation