Solar-Terrestrial Physics Solar-Terrestrial Physics Solar-Terrestrial Physics 2500-0535 113766 10.12737/stp-121202602 rjxvbm Results of current research Results of current research Results of current research Application of machine learning methods to determine spectral characteristics of radiation in the “Solntse-Terahertz” experiment Application of machine learning methods to determine spectral characteristics of radiation in the “Solntse-Terahertz” experiment Тульников Егор Дмитриевич Tulnikov Egor Dmitrievich tulnikov.ed@yandex.ru https://orcid.org/0000-0002-2242-1055 Махмутов Владимир Салимгереевич Makhmutov Vladimir Salimgereevich mahmutovvs@lebedev.ru

доктор физико-математических наук;

doctor of physical and mathematical sciences;

 https://orcid.org/0000-0003-4302-0020 Филиппов Максим Валентинович Philippov Maxim Valentinovich filippovmv@lebedev.ru

кандидат физико-математических наук;

candidate of physical and mathematical sciences;

 Физический институт им. П.Н. Лебедева РАН Москва Россия P.N. Lebedev Physical Institute RAS Moscow Russian Federation Физический институт им. П.Н. Лебедева РАН Москва Россия P.N. Lebedev Physical Institute RAS Moscow Russian Federation Физический институт им. П.Н. Лебедева РАН Москва Россия P.N. Lebedev Physical Institute RAS Moscow Russian Federation 25 03 2026 25 03 2026 12 1 11 17 04 08 2025 11 11 2025 https://zh-szf.ru/en/nauka/article/113766/view

This paper explores the possibility of using machine learning methods for analyzing observations from the “Solntse-Terahertz” scientific equipment, developed at the Lebedev Physical Institute for installation on the Russian segment of the ISS. The scientific equipment consists of eight detectors, with target frequencies ranging from 0.4 to 12.0 THz. One of the primary goals of the experiment is to study solar flares whose spectra in this range often have a U-shaped form. The primary focus in determining the spectral parameters is on identifying spectral indices of the decaying and rising parts of the spectrum, as well as the position of the turnover point. The algorithms were trained using model data on the intensity of radiation passing through optical paths of the instrument. The data was obtained by numerical integration methods. The analysis has shown that the Stacking algorithm demonstrates the highest accuracy in determining the spectral parameters and can be integrated into the data processing system for future experiment on the ISS, enabling the automatic preliminary restoration of solar flare spectrum parameters.

This paper explores the possibility of using machine learning methods for analyzing observations from the “Solntse-Terahertz” scientific equipment, developed at the Lebedev Physical Institute for installation on the Russian segment of the ISS. The scientific equipment consists of eight detectors, with target frequencies ranging from 0.4 to 12.0 THz. One of the primary goals of the experiment is to study solar flares whose spectra in this range often have a U-shaped form. The primary focus in determining the spectral parameters is on identifying spectral indices of the decaying and rising parts of the spectrum, as well as the position of the turnover point. The algorithms were trained using model data on the intensity of radiation passing through optical paths of the instrument. The data was obtained by numerical integration methods. The analysis has shown that the Stacking algorithm demonstrates the highest accuracy in determining the spectral parameters and can be integrated into the data processing system for future experiment on the ISS, enabling the automatic preliminary restoration of solar flare spectrum parameters.

 Sun flare submillimeter radiation machine learning Sun flare submillimeter radiation machine learning

Altman N.S. An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician. 1992, vol. 46, no. 3, pp. 175–185. Altman N.S. An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician. 1992, vol. 46, no. 3, pp. 175–185. Breiman L. Random forests. Machine Learning. 2001, vol. 45, pp. 5–32. Breiman L. Random forests. Machine Learning. 2001, vol. 45, pp. 5–32. Chen T., Guestrin C. Xgboost: A scalable tree boosting system. Proc. of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, 2016, pp. 785–794. DOI: 10.1145/2939672.2939785. Chen T., Guestrin C. Xgboost: A scalable tree boosting system. Proc. of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, 2016, pp. 785–794. DOI: 10.1145/2939672.2939785. Cortes C., Vapnik V. Support-vector networks. Machine Learning. 1995, vol. 20, pp. 273–297. Cortes C., Vapnik V. Support-vector networks. Machine Learning. 1995, vol. 20, pp. 273–297. Cristiani G., De Castro C.G.G., Luoni M.L., et al. Observed flux density enhancement at submillimeter wavelengths during an X-class flare. Adv. Space Res. 2007, vol. 39, iss. 9, pp. 1445–1450. DOI: 10.1016/j.asr.2007.02.039. Cristiani G., De Castro C.G.G., Luoni M.L., et al. Observed flux density enhancement at submillimeter wavelengths during an X-class flare. Adv. Space Res. 2007, vol. 39, iss. 9, pp. 1445–1450. DOI: 10.1016/j.asr.2007.02.039. Cristiani G., De Castro C.G.G., Mandrini C.H., et al. Asymmetric precipitation in a coronal loop as explanation of a singular observed spectrum. Adv. Space Res. 2009, vol. 44, iss. 11, pp. 1314–1320. DOI: 10.1016/j.asr.2009.06.012. Cristiani G., De Castro C.G.G., Mandrini C.H., et al. Asymmetric precipitation in a coronal loop as explanation of a singular observed spectrum. Adv. Space Res. 2009, vol. 44, iss. 11, pp. 1314–1320. DOI: 10.1016/j.asr.2009.06.012. De Castro C.G.G., Kaufmann P., Raulin J.P. Recent results on solar activity at submillimeter wavelengths. Adv. Space Res. 2005, vol. 35, iss. 10, pp. 1769–1773. DOI: 10.1016/j.asr.2005.03.083. De Castro C.G.G., Kaufmann P., Raulin J.P. Recent results on solar activity at submillimeter wavelengths. Adv. Space Res. 2005, vol. 35, iss. 10, pp. 1769–1773. DOI: 10.1016/j.asr.2005.03.083. Duncan N., Saint-Hilaire P., Shih A.Y., et al. First flight of the Gamma-Ray Imager/Polarimeter for Solar flares (GRIPS) instrument. Space Telescopes and Instrumentation 2016: Ultraviolet to Gamma Ray. Edinburgh, 2016, vol. 9905, p. 876. DOI: 10.1117/12.2233859. Duncan N., Saint-Hilaire P., Shih A.Y., et al. First flight of the Gamma-Ray Imager/Polarimeter for Solar flares (GRIPS) instrument. Space Telescopes and Instrumentation 2016: Ultraviolet to Gamma Ray. Edinburgh, 2016, vol. 9905, p. 876. DOI: 10.1117/12.2233859. Hosmer Jr D.W., Lemeshow S., Sturdivant R.X. Applied logistic regression. John Wiley & Sons, Inc., 2013. 510 p. Hosmer Jr D.W., Lemeshow S., Sturdivant R.X. Applied logistic regression. John Wiley & Sons, Inc., 2013. 510 p. Jolliffe I.T., Cadima J. Principal component analysis: a review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2016, vol. 374:20150202, iss. 2065. DOI: 10.1098/rsta.2015.0202. Jolliffe I.T., Cadima J. Principal component analysis: a review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2016, vol. 374:20150202, iss. 2065. DOI: 10.1098/rsta.2015.0202. Kalinin E.V., Philippov M.V., Makhmutov V.S., et al. A study of the characteristics of a terahertz radiation detector for the Solntse-Terahertz scientific apparatus. Cosmic Res. 2021, vol. 59, iss. 1, pp. 1–5. DOI: 10.1134/S0010952521010032. Kalinin E.V., Philippov M.V., Makhmutov V.S., et al. A study of the characteristics of a terahertz radiation detector for the Solntse-Terahertz scientific apparatus. Cosmic Res. 2021, vol. 59, iss. 1, pp. 1–5. DOI: 10.1134/S0010952521010032. Kaufmann P., Raulin J.P, De Castro C.G.G., et al. A new solar burst spectral component emitting only in the terahertz range. ApJ. Lett. 2004, vol. 603, iss. 2, pp. L121–L124. DOI: 10.1086/383186. Kaufmann P., Raulin J.P, De Castro C.G.G., et al. A new solar burst spectral component emitting only in the terahertz range. ApJ. Lett. 2004, vol. 603, iss. 2, pp. L121–L124. DOI: 10.1086/383186. Kaufmann P., Abrantes A., Bortolucci E.C., et al. THz solar observations on board of a trans-Antarctic stratospheric balloon flight. 41st International Conference on Infrared, Millimeter, and Terahertz waves (IRMMW-THz). Copenhagen, 2016, p. 1. DOI: 10.1109/IRMMW-THz.2016.7758395. Kaufmann P., Abrantes A., Bortolucci E.C., et al. THz solar observations on board of a trans-Antarctic stratospheric balloon flight. 41st International Conference on Infrared, Millimeter, and Terahertz waves (IRMMW-THz). Copenhagen, 2016, p. 1. DOI: 10.1109/IRMMW-THz.2016.7758395. Ke G., Meng Q., Finley T., et al. Lightgbm: A highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing Systems (NIPS–2017), Long Beach, 2017, vol. 30. Ke G., Meng Q., Finley T., et al. Lightgbm: A highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing Systems (NIPS–2017), Long Beach, 2017, vol. 30. Krucker S., De Castro C.G.G., Hudson H.S., et al. Solar flares at submillimeter wavelengths. Astron. Astrophys. Rev. 2013, vol. 21, iss. 1, pp. 1–45. DOI: 10.1007/s00159-013-0058-3. Krucker S., De Castro C.G.G., Hudson H.S., et al. Solar flares at submillimeter wavelengths. Astron. Astrophys. Rev. 2013, vol. 21, iss. 1, pp. 1–45. DOI: 10.1007/s00159-013-0058-3. Kvashnin A.A., Logachev V.I., Philippov M.V., et al. Optical system design of the detector for solar terahertz emission measurements. Space Engineering and Technology. 2021, vol. 35, iss. 4, pp. 22–30. DOI: 10.33950/spacetech-2308-7625-2021-4-22-30. Kvashnin A.A., Logachev V.I., Philippov M.V., et al. Optical system design of the detector for solar terahertz emission measurements. Space Engineering and Technology. 2021, vol. 35, iss. 4, pp. 22–30. DOI: 10.33950/spacetech-2308-7625-2021-4-22-30. Pedregosa F., Varoquaux G., Gramfort A., et al. Scikit-learn: Machine learning in Python. J. Machine Learning Res. 2011, vol. 12, pp. 2825–2830. DOI: 10.5555/1953048.2078195. Pedregosa F., Varoquaux G., Gramfort A., et al. Scikit-learn: Machine learning in Python. J. Machine Learning Res. 2011, vol. 12, pp. 2825–2830. DOI: 10.5555/1953048.2078195. Philippov M.V., Makhmutov V.S., Razumeyko M.V. Scientific equipment for the Sun-Terahertz space experiment: study of the temperature effect in the Golay cell. Measurement Techniques. 2024a, vol. 67, iss. 3, pp. 195–202. DOI: 10.1007/s11018-024-02335-9. Philippov M.V., Makhmutov V.S., Razumeyko M.V. Scientific equipment for the Sun-Terahertz space experiment: study of the temperature effect in the Golay cell. Measurement Techniques. 2024a, vol. 67, iss. 3, pp. 195–202. DOI: 10.1007/s11018-024-02335-9. Philippov M.V., Makhmutov V.S., Maksumov O.S., et al. Electronics Unit for “Sun-Terahertz” Scientific Equipment. Instrum. Exp Tech. 2024b, vol. 67, iss. 3, pp. 545–553. DOI: 10.1134/S0020441224700829. Philippov M.V., Makhmutov V.S., Maksumov O.S., et al. Electronics Unit for “Sun-Terahertz” Scientific Equipment. Instrum. Exp Tech. 2024b, vol. 67, iss. 3, pp. 545–553. DOI: 10.1134/S0020441224700829. Prokhorenkova L., Gusev G., Vorobev A., et al. CatBoost: unbiased boosting with categorical features. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018). Montréal, 2018, vol. 31. Prokhorenkova L., Gusev G., Vorobev A., et al. CatBoost: unbiased boosting with categorical features. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018). Montréal, 2018, vol. 31. Quinlan J.R. Induction of decision trees. Machine Learning. 1986, vol. 1, pp. 81–106. Quinlan J.R. Induction of decision trees. Machine Learning. 1986, vol. 1, pp. 81–106. Tsap Y.T., Smirnova V.V., Morgachev, A.S., et al. On the origin of 140 GHz emission from the 4 July 2012 solar flare. Adv. Space Res. 2016, vol. 57, iss. 7, pp. 1449–1455. DOI: 10.1016/j.asr.2015.12.037. Tsap Y.T., Smirnova V.V., Morgachev, A.S., et al. On the origin of 140 GHz emission from the 4 July 2012 solar flare. Adv. Space Res. 2016, vol. 57, iss. 7, pp. 1449–1455. DOI: 10.1016/j.asr.2015.12.037. Tulnikov E.D., Logachev V.I., Makhmutov V.S., at el. Characteristics of the optical system of the Solntse-Terahertz scientific equipment. Cosmic Res. 2024, vol. 62, iss. 6, pp. 551–557. DOI: 10.1134/S0010952524600434. Tulnikov E.D., Logachev V.I., Makhmutov V.S., at el. Characteristics of the optical system of the Solntse-Terahertz scientific equipment. Cosmic Res. 2024, vol. 62, iss. 6, pp. 551–557. DOI: 10.1134/S0010952524600434. Tulnikov E.D., Makhmutov V.S., Philippov M.V. Review of studying submillimeter radiation from the Sun and astrophysical sources. Bull. Russian Academy of Sciences: Physics. 2025, vol. 89, iss. 6, pp. 854-857. DOI: 10.1134/S1062873825711298. Tulnikov E.D., Makhmutov V.S., Philippov M.V. Review of studying submillimeter radiation from the Sun and astrophysical sources. Bull. Russian Academy of Sciences: Physics. 2025, vol. 89, iss. 6, pp. 854-857. DOI: 10.1134/S1062873825711298. Wedemeyer S., Bastian T., Brajša R., et al. Solar science with the Atacama Large Millimeter/Submillimeter Array — a new view of our Sun. Space Sci. Rev. 2016, vol. 200, pp. 1–73. DOI: 10.1007/s11214-015-0229-9. Wedemeyer S., Bastian T., Brajša R., et al. Solar science with the Atacama Large Millimeter/Submillimeter Array — a new view of our Sun. Space Sci. Rev. 2016, vol. 200, pp. 1–73. DOI: 10.1007/s11214-015-0229-9. Wolpert D.H. Stacked generalization. Neural Networks. 1992, vol. 5, iss. 2, pp. 241–259. Wolpert D.H. Stacked generalization. Neural Networks. 1992, vol. 5, iss. 2, pp. 241–259.