RSS feeds
РусскийEnglish
Issue 12, 2025
Volume year page
Issues Authors PACS Subscription For authors

Issues

 / 

2025

 / 

April

←  →

On the 270th Anniversary of the M.V. Lomonosov Moscow State University (MSU). Physics of our days


Machine learning methods in solar physics

† 
Lomonosov Moscow State University, Faculty of Mechanics and Mathematics, Leninskiye Gory 1, MSU, Main Building, Moscow, 119991, Russian Federation

The development of machine learning methods and their success in a wide range of problems have had a significant impact on the design and implementation of solar physics research. Large data sets have emerged as an intrinsic value in which the efforts of experts and significant technological resources are invested. The research itself has acquired an interdisciplinary nature and is concentrated around advanced computing centers. Large-scale problems can now be posed whose mathematical formulation was unclear yesterday. In this review, we present the main ideas underlying modern machine learning models, the databases prepared for machine learning tasks, and data processing tools. A major part of this review is devoted to a discussion of models proposed in the context of specific solar physics problems and their extension to other applications.

Fulltext pdf (3.1 MB)
Fulltext is also available at DOI: 10.3367/UFNe.2025.02.039872
Keywords: solar physics, solar activity, machine learning, databases
PACS: 07.05.Mh, 84.35.+i, 96.60.−j (all)
DOI: 10.3367/UFNe.2025.02.039872
URL: https://ufn.ru/en/articles/2025/4/e/
001513421700004
2-s2.0-105006712172
2025PhyU...68..374I
Citation: Illarionov E A "Machine learning methods in solar physics" Phys. Usp. 68 374–392 (2025)
BibTexBibNote ® (generic)BibNote ® (RIS)MedlineRefWorks

Received: 5th, August 2024, 22nd, February 2025

Оригинал: Илларионов Е А «Методы машинного обучения в физике Солнца» УФН 195 395–415 (2025); DOI: 10.3367/UFNr.2025.02.039872

References (169) ↓

  1. Markov A A "Primer statisticheskogo issledovaniya nad tekstom "Evgeniya Onegina", illyustriruyushchii svyaz’ ispytanii v tsep’ (An example of a statistical study of the text of "Eugene Onegin", illustrating the link of trials in a chain)" Izv. Imperatorskoi Akad. Nauk 7 (3) 153 (1913)
  2. Vaswani A et al arXiv:1706.03762
  3. Devlin J et al arXiv:1810.04805
  4. Brown T B et al arXiv:2005.14165
  5. Dosovitskiy A et al arXiv:2010.11929
  6. Yan W et al arXiv:2104.10157
  7. Lin T et al arXiv:2106.04554
  8. Bommasani R et al arXiv:2108.07258
  9. Vokhmyanin M, Arlt R, Zolotova N Solar Phys. 295 (3) 39 (2020)
  10. Rimmele T R et al Solar Phys. 295 (12) 172 (2020)
  11. Clette F et al Solar Phys. 298 (3) 44 (2023)
  12. Lemen J R et al Solar Phys. 275 (1-2) 17 (2012)
  13. Kolmogorov A N Dokl. Akad. Nauk SSSR 108 179 (1956)
  14. Liu Z et al arXiv:2404.19756
  15. Cybenko G Math. Control Signals Syst. 2 303 (1989)
  16. Hornik K, Stinchcombe M, White H Neural Networks 2 (5) 359 (1989)
  17. Funahashi K-I Neural Networks 2 (3) 183 (1989)
  18. Pinkus A Acta Numerica 8 143 (1999)
  19. DeVore R, Hanin B, Petrova G Acta Numerica 30 327 (2021)
  20. Murphy K P Machine Learning: A Probabilistic Perspective (Cambridge, MA: MIT Press, 2021)
  21. Bishop C M Pattern Recognition And Machine Learning (Information Science and Statistics) (New York: Springer-Verlag, 2006)
  22. Hastie T, Tibshirani R, Friedman J The Elements Of Statistical Learning: Data Mining, Inference, And Prediction (Springer Series in Statistics) (New York: Springer, 2009)
  23. Johnson J, Alahi A, Fei-Fei L arXiv:1603.08155
  24. Bakhvalov N S, Zhidkov N P, Kobel’kov G M Chislennye Metody (Numerical Methods) (Moscow: Nauka, 1987)
  25. Raissi M, Perdikaris P, Karniadakis G E J. Comput. Phys. 378 686 (2019)
  26. Goodfellow I, Bengio Y, Courville A Deep Learning (Cambridge, MA: MIT Press, 2016)
  27. Chen R T Q et al arXiv:1806.07366
  28. Pontryagin L S et al The Mathematical Theory Of Optimal Processes (New York: Interscience Publ., 1962); Translated from Russian, Pontryagin L S et al Matematicheskaya Teoriya Optimal’nykh Protsessov (Moscow: Fizmatgiz, 1961)
  29. Pearson K Philos. Mag. 2 (11) 559 (1901)
  30. Johnstone I M, Paul D Proc. IEEE 106 1277 (2018)
  31. Kingma D P, Welling M arXiv:1312.6114
  32. Kingma D P, Welling M Found. Trends Machine Learn. 12 (4) 307 (2019)
  33. Rezende D, Mohamed Sh Proc. of the 32nd Intern. Conf. on Machine Learning, Lille, France, 7-9 Jul 2015 (Proc. of Machine Learning Research) Vol. 37 (Eds F Bach, D Blei) (MLR Press, 2015) p. 1530
  34. Kobyzev I, Prince S J D, Brubaker M A IEEE Trans. Pattern Analysis Machine Intelligence 43 3964 (2021)
  35. Goodfellow I J et al arXiv:1406.2661
  36. Arjovsky M, Chintala S, Bottou L arXiv:1701.07875
  37. Kovachki N et al arXiv:2108.08481
  38. Jouppi N P et al arXiv:1704.04760
  39. Zeiler M D arXiv:1212.5701
  40. Kingma D P, Ba J arXiv:1412.6980
  41. Duchi J, Hazan E, Singer Y J. Machine Learning Res. 12 2121 (2011)
  42. Chen X et al arXiv:2302.06675
  43. McMahan B Proc. of the Fourteenth Intern. Conf. on Artificial Intelligence and Statistics (Proc. of Machine Learning Research) Vol. 15 (Eds G Gordon, D Dunson, M Dudík) (MLR Press, 2011) p. 525
  44. Bottou L On-Line Learning In Neural Networks (Ed. D Saad) (Cambridge: Cambridge Univ. Press, 1999) p. 9
  45. Polyak B T, Juditsky A B SIAM J. Control Optim. 30 838 (1992)
  46. Zhu C et al ACM Trans. Math. Software 23 550 (1997)
  47. Riedmiller M, Braun H IEEE Intern. Conf. on Neural Networks, 28 March 1993 - 01 April 1993, San Francisco, CA, USA (Piscataway, NJ: IEEE, 1993) p. 586
  48. Rall L B (Ed.) Automatic Differentiation: Techniques And Applications (Lecture Notes in Computer Science) Vol. 120 (Berlin: Springer-Verlag, 1981)
  49. Baydin A G et al J. Machine Learning Res. 18 (153) 1 (2018)
  50. Rumelhart D E, Hinton G E, Williams R J Nature 323 533 (1986)
  51. Hecht-Nielsen R Intern. 1989 Joint Conf. on Neural Networks, IJCNN, Washington DC, 18-22 June 1989 Vol. 1 (Piscataway, NJ: IEEE, 1989) p. 593
  52. Schmidhuber J Neural Networks 61 85 (2015)
  53. Yao Y, Rosasco L, Caponnetto A Constr. Approx. 26 289 (2007)
  54. Hurlburt N et al Solar Phys. 275 67 (2012)
  55. Müller D et al Astron. Astrophys. 606 A10 (2017)
  56. Sadykov V M et al Astrophys. J. Suppl. 231 (1) 6 (2017)
  57. Illarionov E, Kosovichev A, Tlatov A Astrophys. J. 903 115 (2020)
  58. Zhao Z et al Sci. Data 10 178 (2023)
  59. Kucuk A, Banda J M, Angryk R A Sci. Data 4 170096 (2017)
  60. Galvez R et al Astrophys. J. Suppl. 242 (1) 7 (2019)
  61. Illarionov E A, Tlatov A G Izv. Krym. Astrofiz. Observ. 114 (1) 118 (2018)
  62. Bolzern R, Aerni M "A machine learning image dataset for the prediction of solar flares" (2024)
  63. Kosovichev A G et al AGU Fall Meeting 2023, San Francisco, CA, 11-15 December 2023, id. SH33C-307, Poster No. 307
  64. Palmroos C et al Front. Astron. Space Sci. 9 395 (2022)
  65. Bobra M G et al Solar Phys. 289 3549 (2014)
  66. Bobra M G et al Astrophys. J. Suppl. 256 26 (2021)
  67. Rotti S A, Martens P C H, Aydin B Astrophys. J. Suppl. 249 (2) 20 (2020)
  68. Boucheron L E et al Sci. Data 10 825 (2023)
  69. Gallagher P T, Moon Y-J, Wang H Solar Phys. 209 171 (2002)
  70. Illarionov E, Tlatov A Solar Phys. 297 (2) 19 (2022)
  71. Angryk R A et al Sci. Data 7 (1) 227 (2020)
  72. Freeland S L, Handy B N Solar Phys. 182 (2) 497 (1998)
  73. Barnes W T et al J. Open Source Software 5 (55) 2801 (2020)
  74. McGregor S et al Workshop on Deep Learning for Physical Sciences, DLPS 2017, NIPS 2017, Long Beach, CA, USA, 2017
  75. Shneider C et al arXiv:2108.06394
  76. The SunPy Community, Barnes W T et al Astrophys. J. 890 68 (2020)
  77. Illarionov E A, Tlatov A G Mon. Not. R. Astron. Soc. 481 5014 (2018)
  78. Ronneberger O, Fischer P, Brox T Medical Image Computing and Computer-Assisted Intervention — MICCAI 2015. 18th Intern. Conf., Munich, Germany, October 5-9, 2015, Proc. Pt. 3 (Lecture Notes in Computer Science) Vol. 9351 (Eds N Navab et al) (Cham: Springer, 2015) p. 234; Ronneberger O, Fischer P, Brox T arXiv:1505.04597
  79. Reiss M A et al Astrophys. J. 913 28 (2021)
  80. Reiss M A et al Astrophys. J. Suppl. 271 6 (2024)
  81. Verbeeck C et al Astron. Astrophys. 561 A29 (2014)
  82. Garton T M, Gallagher P T, Murray S A J. Space Weather Space Clim. 8 A02 (2018)
  83. Zhu G et al Solar Phys. 294 117 (2019)
  84. Jiang H et al Astrophys. J. Suppl. 250 5 (2020)
  85. Mackovjak Š et al Mon. Not. R. Astron. Soc. 508 3111 (2021)
  86. Díaz Castillo S M et al Front. Astron. Space Sci. 9 896632 (2022)
  87. Jarolim R et al Astron. Astrophys. 652 A13 (2021)
  88. Baek J-H et al Solar Phys. 296 160 (2021)
  89. Ahmadzadeh A et al arXiv:1912.02743
  90. Guo X et al Solar Phys. 297 104 (2022)
  91. Diercke A et al Astron. Astrophys. 686 A213 (2024)
  92. McIntosh P S Solar Phys. 125 251 (1990)
  93. Makarenko N G, Knyazeva I S, Karimova L M Astron. Lett. 38 531 (2012); Makarenko N G, Knyazeva I S, Karimova L M Pis’ma Astron. Zh. 38 597 (2012)
  94. Sadykov V M et al 2021 Intern. Conf. on Content-Based Multimedia Indexing CBMI, 28-30 June 2021, Lille, France (Piscataway, NJ: IEEE, 2021) p. 1
  95. Giger M, Csillaghy A Space Weather 22 e2023SW003516 (2024)
  96. Brown E et al "Learning the solar latent space: sigma-variational autoencoders for multiple channel solar imaging" Fourth Workshop on Machine Learning and the Physical Sciences, NeurIPS 2021
  97. Wang J et al Front. Astron. Space Sci. 10 1082737 (2023)
  98. Ahmadzadeh A et al Astrophys. J. Suppl. 254 23 (2021)
  99. Bobra M G, Couvidat S Astrophys. J. 798 135 (2015)
  100. Barnes G et al Astrophys. J. 829 89 (2016)
  101. Leka K D et al Astrophys. J. Suppl. 243 36 (2019)
  102. Leka K D et al Astrophys. J. 881 101 (2019)
  103. Park S-H et al Astrophys. J. 890 124 (2020)
  104. Georgoulis M K et al J. Space Weather Space Clim. 11 39 (2021)
  105. Whitman K et al Adv. Space Res. 72 5161 (2023)
  106. Sadykov V et al arXiv:2107.03911
  107. Ali A et al Astrophys. J. Suppl. 270 15 (2024)
  108. Lipton Z C, Berkowitz J, Elkan C arXiv:1506.00019
  109. Sherstinsky A Physica D 404 132306 (2020)
  110. Nandy D Solar Phys. 296 54 (2021)
  111. Wang Q-J, Li J-C, Guo L-Q Res. Astron. Astrophys. 21 (1) 012 (2021)
  112. Bizzarri I et al Mon. Not. R. Astron. Soc. 515 5062 (2022)
  113. Prasad A et al Solar Phys. 298 50 (2023)
  114. Obridko V N, Nagovitsyn Yu A Solnechnaya Aktivnost’, Tsiklichnost’ I Metody Prognoza (Solar Activity, Cyclicity, And Prediction Methods) (St. Petersburg: VVM, 2017)
  115. Myagkova I, Shiroky V, Dolenko S E3S Web Conf. 20 02011 (2017)
  116. Efitorov A O et al Cosmic Res. 56 434 (2018); Efitorov A O et al Kosmich. Issled. 56 420 (2018)
  117. Tlatov A G, Illarionov E A, Berezin I A, Shramko A D Cosmic Res. 58 444 (2020); Tlatov A G, Illarionov E A, Berezin I A, Shramko A D Kosmich. Issled. 58 479 (2020)
  118. Bernoux G et al J. Geophys. Res. Space Phys. 127 e2022JA030868 (2022)
  119. Vladimirov R D et al Geomagn. Aeronom. 63 (2) 190 (2023)
  120. Telloni D et al Astrophys. J. 952 111 (2023)
  121. Upendran V et al Space Weather 18 (9) e02478 (2020)
  122. Brown E J E et al Space Weather 20 (3) e2021SW002976 (2022)
  123. Son J et al Astrophys. J. Suppl. 267 45 (2023)
  124. Petrukovich A A et al Phys. Usp. 63 801 (2020); Petrukovich A A et al Usp. Fiz. Nauk 190 859 (2020)
  125. Vitinskii Yu I Solnechnaya Aktivnost’ (Solar Activity) (Moscow: Nauka, 1983)
  126. Translated into Russian, McIntosh P S Solar Activity Observations And Predictions (Progress in Astronautics and Aeronautics) Vol. 30 (Eds P S McIntosh, M Dryer) (Cambridge, MA: MIT Press, 1972) p. 65
  127. McIntosh P S "Synoptic maps composites observed from McIntosh" (1964)
  128. Makarov V I, Fatianov M P, Sivaraman K R Solar Phys. 85 215 (1983)
  129. Makarov V I, Sivaraman K R Solar Phys. 85 227 (1983)
  130. Kisielius V, Illarionov E Solar Phys. 299 (5) 69 (2024)
  131. Metcalf T R et al Astrophys. J. 439 474 (1995)
  132. Jarolim R et al Nat. Astron. 7 1171 (2023)
  133. Baty H, Vigon V Mon. Not. R. Astron. Soc. 527 2575 (2024)
  134. Moschou S P et al Machine Learn. Sci. Technol. 4 035032 (2023)
  135. Kim T et al Nat. Astron. 3 397 (2019)
  136. Park E et al Astrophys. J. Lett. 884 L23 (2019)
  137. Son J et al Astrophys. J. 920 101 (2021)
  138. Jeong H-J et al Astrophys. J. Suppl. 262 (2) 50 (2022)
  139. Lawrance B et al Astrophys. J. 937 (2) 111 (2022)
  140. Díaz Baso C J, Asensio Ramos A Astron. Astrophys. 614 A5 (2018)
  141. Díaz Baso C J, de la Cruz Rodrtguez J, Danilovic S Astron. Astrophys. 629 A99 (2019)
  142. Rahman S et al Astrophys. J. Lett. 897 L32 (2020)
  143. Xu C et al Solar Phys. 299 36 (2024)
  144. Muñoz-Jaramillo A et al Astrophys. J. Suppl. 271 46 (2024)
  145. Song W et al Astron. Astrophys. 686 A272 (2024)
  146. Salvatelli V et al Astrophys. J. 937 100 (2022)
  147. Illarionov E, Arlt R Solar Phys. 297 79 (2022)
  148. Rani V et al Arch. Computat. Methods Eng. 30 2761 (2023)
  149. Huang S-C et al Npj Digit. Med. 6 74 (2023)
  150. Shwartz Ziv R, LeCun Y Entropy 26 (3) 252 (2024)
  151. Zhao Z et al Expert Syst. Appl. 242 122807 (2024)
  152. Sokoloff D D Phys. Usp. 58 601 (2015); Sokoloff D D Usp. Fiz. Nauk 185 643 (2015)
  153. Käpylä P J et al Space Sci. Rev. 219 58 (2023)
  154. Brandenburg A, Sokoloff D, Subramanian K Space Sci. Rev. 169 123 (2012)
  155. Brandenburg A et al Space Sci. Rev. 219 55 (2023)
  156. Petrosyants M, Trifonov V, Illarionov E, Koroteev D Comput. Geosci. 28 605 (2024)
  157. Williams J, Wolfram U, Ozel A Phys. Fluids 34 113315 (2022)
  158. Peng W, Yuan Z, Wang J Phys. Fluids 34 025111 (2022)
  159. Rosofsky S G, Huerta E A Mach. Learn. Sci. Technol. 4 035002 (2023)
  160. Lu L, Jin P, Karniadakis G E Nat. Mach. Intell. 3 218 (2021); Lu L, Jin P, Karniadakis G E arXiv:1910.03193
  161. Li Z et al arXiv:2010.08895
  162. Kovachki N et al J. Mach. Learn. Res. 24 (89) 1 (2023)
  163. Azizzadenesheli K et al Nat. Rev. Phys. 6 320 (2024)
  164. Anirudh R et al IEEE Trans. Plasma Sci. 51 1750 (2023)
  165. Asensio Ramos A et al Living Rev. Solar Phys. 20 4 (2023)
  166. Illarionov E A, Sadykov V M Zemlya Vselennaya (4) 35 (2021)
  167. Camporeale E, Wing S, Johnson J R (Eds) Machine Learning Techniques For Space Weather (Cambridge, MA: Elsevier, 2018)
  168. Bobra M G, Mason J P "Machine Learning, Statistics, and Data Mining for Heliophysics" (2020)
  169. Xu L, Yan Y, Huang X Deep Learning In Solar Astronomy (SpringerBriefs in Computer Science) 1st ed. (Singapore: Springer, 2022)
© 1918–2025 Uspekhi Fizicheskikh Nauk
Email: ufn@ufn.ru Editorial office contacts About the journal Terms and conditions