<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD with OASIS Tables with MathML3 v1.4 20241031//EN" "https://jats.nlm.nih.gov/archiving/1.4/JATS-archive-oasis-article1-4-mathml3.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" dtd-version="1.4" article-type="research-article" xml:lang="en"><front><journal-meta><journal-title-group><journal-title xml:lang="ru">Математическая физика и компьютерное моделирование</journal-title></journal-title-group><issn publication-format="print">2587-6325</issn><issn publication-format="electronic">2587-6902</issn></journal-meta><article-meta><article-id pub-id-type="doi">10.15688/mpcm.jvolsu.2025.2.4</article-id><article-categories><subj-group><subject>Other</subject></subj-group></article-categories><title-group><article-title xml:lang="ru">НЕЙРОСЕТЕВОЙ ЭМУЛЯТОР ОТКЛИКА СПИНОВОГО АНСАМБЛЯ НА ПОСЛЕДОВАТЕЛЬНОСТЬ РАДИОИМПУЛЬСОВ</article-title><trans-title-group xml:lang="en"><trans-title>NEURAL NETWORK EMULATOR OF SPIN ENSEMBLE RESPONSE TO A SEQUENCE OF RADIO PULSES</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Перченко</surname><given-names>Сергей Владимирович</given-names></name><name xml:lang="en"><surname>Perchenko</surname><given-names>Sergey</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><email>perchenko@volsu.ru</email><contrib-id contrib-id-type="orcid">0000-0003-4643-3015</contrib-id></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Станкевич</surname><given-names>Дмитрий Александрович</given-names></name><name xml:lang="en"><surname>Stankevich</surname><given-names>Dmitriy</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><email>stankevich@volsu.ru</email><contrib-id contrib-id-type="orcid">0000-0003-0208-903X</contrib-id></contrib><aff-alternatives id="aff1"><aff xml:lang="en"><institution>Volgograd State University</institution></aff><aff xml:lang="ru"><institution>Волгоградский государственный университет</institution></aff></aff-alternatives></contrib-group><pub-date pub-type="epub" iso-8601-date="2025-08-07"><day>07</day><month>08</month><year>2025</year></pub-date><volume>28</volume><issue>2</issue><fpage>39</fpage><lpage>50</lpage><history><date date-type="received" iso-8601-date="2025-03-01"><day>01</day><month>03</month><year>2025</year></date><date date-type="accepted" iso-8601-date="2025-05-21"><day>21</day><month>05</month><year>2025</year></date></history><permissions><license xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:title="CC BY 4.0"><ali:license_ref>https://creativecommons.org/licenses/by/4.0/</ali:license_ref><license-p xml:lang="ru">CC BY 4.0</license-p></license></permissions><self-uri xlink:href="https://mp.jvolsu.com/index.php/ru/archive-ru/512-mathematical-physics-and-computer-simulation-2025-vol-28-no-2/modelirovanie-informatika-i-upravlenie/1149-perchenko-s-v-stankevich-d-a-nejrosetevoj-emulyator-otklika-spinovogo-ansamblya-na-posledovatelnost-radioimpulsov" xlink:title="https://mp.jvolsu.com/index.php/ru/archive-ru/512-mathematical-physics-and-computer-simulation-2025-vol-28-no-2/modelirovanie-informatika-i-upravlenie/1149-perchenko-s-v-stankevich-d-a-nejrosetevoj-emulyator-otklika-spinovogo-ansamblya-na-posledovatelnost-radioimpulsov">https://mp.jvolsu.com/index.php/ru/archive-ru/512-mathematical-physics-and-computer-simulation-2025-vol-28-no-2/modelirovanie-informatika-i-upravlenie/1149-perchenko-s-v-stankevich-d-a-nejrosetevoj-emulyator-otklika-spinovogo-ansamblya-na-posledovatelnost-radioimpulsov</self-uri><abstract xml:lang="en"><p>The paper proposes a method of developing a neural network emulator of the response of a spin ensemble to a sequence of radio pulses. The emulator was trained using a set containing sequences of RF pulses and responses of the homonuclear spin system calculated by numerical solution of the Bloch equations using the Runge-Kutta method. The deep neural network architecture with recurrent cells is investigated in detail. It is shown that the response of the spin system is adequately represented by two-layer networks with GRU and LSTM cells when the number of cells in a layer is relatively small (less than 64). The best results are obtained for the two-layer architecture in which each of the layers contains 32 GRU cells. To test the generalization ability of the network, its training and validation were performed on different data sets. The training set contained 640 images representing the responses of the spin system to a sequence of two RF pulses with a rectangular envelope. The test set consisted of responses to a sequence of 10 RF pulses. The quality criterion of the prediction was the energy of the difference between the predicted and true responses normalized by the energy of the true response. It is shown that the resulting response prediction error is less than 1%. A full cycle of neural network training on a personal computer of average performance requires no more than 10 min.</p></abstract><abstract xml:lang="ru" abstract-type="summary"><p>В статье предложен способ построения нейросетевого эмулятора отклика спинового ансамбля на последовательность радиоимпульсов. При обучении эмулятора используется множество, содержащее последовательности РЧ-импульсов и отклики на них гомоядерной спиновой системы, рассчитанные с помощью численного решения уравнений Блоха методом Рунге-Кутты. Подробно исследована глубокая нейросетевая архитектура с рекуррентными ячейками. Показано, что отклик спиновой системы адекватно описывают уже двухслойные сети с ячейками GRU и LSTM при сравнительно малом (менее 64) числе ячеек в слое. Наилучшие результаты получены для двухслойной архитектуры, в которой каждый из слоев содержит 32 ячейки GRU. После обучения сети на наборе данных, содержащих 640 обучающих образов, представляющих отклики спиновой системы на последовательность из двух РЧ-импульсов, проверялась обобщающая способность сети на множестве, содержащем последовательности из 10 РЧ-импульсов. Показано, что результирующая ошибка предсказания отклика составляет менее 1 %. На полный цикл обучения нейронной сети на персональном компьютере средней производительности требуется не более 10 минут.</p></abstract><kwd-group xml:lang="ru"><kwd>магнитно-резонансная спектроскопия</kwd><kwd>рекуррентная</kwd><kwd>нейронная сеть</kwd><kwd>нелинейный отклик</kwd><kwd>LSTM</kwd><kwd>GRU</kwd></kwd-group><kwd-group xml:lang="en"><kwd>magnetic resonance spectroscopy</kwd><kwd>recurrent neural network</kwd><kwd>nonlinear response</kwd><kwd>LSTM</kwd><kwd>GRU</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено за счет средств гранта Российского научного фонда № 24- 22-20025  (https://rscf.ru/project/24-22-20025/)  и  за  счет  средств  бюджета  Волгоградской области .</funding-statement></funding-group></article-meta></front><back><ref-list><ref id="ref1"><mixed-citation publication-type="other" xml:lang="ru">Николенко, С. Глубокое обучение / С. Николенко, А. Кадурин, Е. Архангельская. — СПб. : Питер, 2018. — 480 c.</mixed-citation></ref><ref id="ref2"><mixed-citation publication-type="other" xml:lang="ru">Попов, И. Е. Анализ термометрических данных головного мозга, полученных методом микроволновой радиотермометрии / И. Е. Попов, А. Е. Крылова // Математическая физика и компьютерное моделирование. — 2023. — Т. 26, № 2. — C. 32–42. — DOI: https://doi.org/10.15688/mpcm.jvolsu.2023.2.3</mixed-citation></ref><ref id="ref3"><mixed-citation publication-type="other" xml:lang="ru">Разработка классификатора фотоизображений патологий для ультрамалого набора данных / А. А. Адамов, И. А. Гнодян, А. И. Дятчина, В. Н. Храмов // Математическая физика и компьютерное моделирование. — 2023. — Т. 26, № 1. — C. 33–48. — DOI: https://doi.org/10.15688/mpcm.jvolsu.2023.1.3</mixed-citation></ref><ref id="ref4"><mixed-citation publication-type="other" xml:lang="ru">Эрнст, Р. ЯМР в одном и двух измерениях / Р. Эрнст, Дж. Боденхаузен, А. Вокаун. — М. : Мир, 1990. — 711 c.</mixed-citation></ref><ref id="ref5"><mixed-citation publication-type="other" xml:lang="ru">Deep Learning and Its Applications in Nuclear Magnetic Resonance Spectroscopy / P. Luo, X. Zheng, M. Qiu, Y. Gou, Z. Yang, X. Qu, Z. Chen, Y. Lin // Progress in Nuclear Magnetic Resonance Spectroscopy. — 2025. — Vol. 146–147. — P. 101556. — DOI: https://doi.org/10.1016/j.pnmrs.2024.101556</mixed-citation></ref><ref id="ref6"><mixed-citation publication-type="other" xml:lang="ru">Li, P. Research on Radar Signal Recognition Based on Automatic Machine Learning / P. Li // Neural Computing &amp; Applications. — 2020. — Vol. 32. — P. 1959–1969. — DOI: https://doi.org/10.1007/s00521-019-04494-1</mixed-citation></ref><ref id="ref7"><mixed-citation publication-type="other" xml:lang="ru">LSTM: A Search Space Odyssey / K. Greff, R. K. Srivastava, J. Koutnik, B. R. Steunebrink, J. Schmidhuber // IEEE Transactions on Neural Networks and Learning Systems. — 2017. — Vol. 28. — № 10. — P. 2222–2232. — DOI: https://doi.org/10.1109/TNNLS.2016.2582924</mixed-citation></ref><ref id="ref8"><mixed-citation publication-type="other" xml:lang="ru">Machine Learning and the Physical Sciences / G. Carleo, I. Cirac, K. Cranmer, L. Daudet, M. Schuld, M. Tishby, L. Vogt-Maranto, L. Zdeborova // Reviews of Modern Physics. — 2019. — Vol. 91. — P. 045002. — DOI: https://doi.org/10.1103/RevModPhys.91.045002</mixed-citation></ref><ref id="ref9"><mixed-citation publication-type="other" xml:lang="ru">Medsker, L. Recurrent Neural Networks: Design and Applications / L. Medsker, L. C. Jain. — Boca Raton : CRC Press, Inc., 1999. — 416 p.</mixed-citation></ref><ref id="ref10"><mixed-citation publication-type="other" xml:lang="ru">Nevzorov, A. A. A Method of Wavefront Distortions Correction for an Atmospheric Optical Link with a Small Volume of Information Transmitted Through a Service Channel / A. A. Nevzorov, D. A. Stankevich // Computer Optics. — 2020. — Vol. 44. — P. 848–851. — DOI: https://doi.org/10.18287/2412-6179-CO-733</mixed-citation></ref><ref id="ref11"><mixed-citation publication-type="other" xml:lang="ru">Physics-Informed Machine Learning / G. E. Karniadakis, I. G. Kevrekidis, L. Lu, P. Perdikaris, S. Wang, L. Yang // Nature Reviews Physics. — 2021. — № 3. — P. 422–440. — DOI: https://doi.org/10.1038/s42254-021-00314-5</mixed-citation></ref><ref id="ref12"><mixed-citation publication-type="other" xml:lang="ru">Response Prediction for Linear and Nonlinear Structures Based on Data-Driven Deep Learning / Y. Liao, H. Tang, R. Li, L. Ran, L. Xie // Applied Sciences. — 2023. — Vol. 13, № 10. — P. 5918. — DOI: https://doi.org/10.3390/app13105918</mixed-citation></ref><ref id="ref13"><mixed-citation publication-type="other" xml:lang="ru">Review and Prospect: Deep Learning in Nuclear Magnetic Resonance Spectroscopy / P. Luo, X. Zheng, M. Qiu, Y. Gou, Z. Yang, X. Qu, Z. Chen, Y. Lin // Chem. Eur. J. — 2020. — Vol. 26. — P. 10391. — DOI: https://doi.org/10.1002/chem.202000246</mixed-citation></ref><ref id="ref14"><mixed-citation publication-type="other" xml:lang="en">Nikolenko S., Kadurin A., Arkhangelskaya E. Glubokoe obuchenie [Deep Learning]. Saint Petersburg, Piter Publ., 2018. 480 p.</mixed-citation></ref><ref id="ref15"><mixed-citation publication-type="other" xml:lang="en">Popov I.E., Krylova A.E. Analiz termometricheskikh dannykh golovnogo mozga, poluchennykh metodom mikrovolnovoy radiotermometrii [Analysis of Brain Thermometric Data Obtained by Microwave Radiothermometry]. Matematicheskaya fizika i kompyuternoe modelirovanie, 2023, vol. 26, no. 2, pp. 32-42. DOI: https://doi.org/10.15688/mpcm.jvolsu.2023.2.3</mixed-citation></ref><ref id="ref16"><mixed-citation publication-type="other" xml:lang="en">Adamov A.A., Gnodyan I.A., Dyatchina A.I., Khramov V.N. Razrabotka klassifikatora fotoizobrazheniy patologiy dlya ultramalogo nabora dannykh [Development of a Classifier of Photo Images of Pathologies for an Ultra-Small Data Set]. Matematicheskaya fizika i kompyuternoe modelirovanie, 2023, vol. 26, no. 1, pp. 33-48. DOI: https://doi.org/10.15688/mpcm.jvolsu.2023.1.3</mixed-citation></ref><ref id="ref17"><mixed-citation publication-type="other" xml:lang="en">Ernst R., Bodenkhauzen Dzh., Vokaun A. YaMR v odnom i dvukh izmereniyakh [Principles of Nuclear Magnetic Resonance in One and Two Dimensions]. Moscow, Mir Publ., 1990. 711 p.</mixed-citation></ref><ref id="ref18"><mixed-citation publication-type="other" xml:lang="en">Luo P., Zheng X., Qiu M., Gou Y., Yang Z., Qu X., Chen Z., Lin Y. Deep Learning and Its Applications in Nuclear Magnetic Resonance Spectroscopy. Progress in Nuclear Magnetic Resonance Spectroscopy, 2025, vol. 146–147, pp. 101556. DOI: https://doi.org/10.1016/j.pnmrs.2024.101556</mixed-citation></ref><ref id="ref19"><mixed-citation publication-type="other" xml:lang="en">Li P. Research on Radar Signal Recognition Based on Automatic Machine Learning. Neural Computing &amp; Applications, 2020, vol. 32, pp. 1959-1969. DOI: https://doi.org/10.1007/s00521-019-04494-1</mixed-citation></ref><ref id="ref20"><mixed-citation publication-type="other" xml:lang="en">Greff K., Srivastava R.K., Koutnik J., Steunebrink B.R., Schmidhuber J. LSTM: A Search Space Odyssey. IEEE Transactions on Neural Networks and Learning Systems, 2017, vol. 28, no. 10, pp. 2222-2232. DOI: https://doi.org/10.1109/TNNLS.2016.2582924</mixed-citation></ref><ref id="ref21"><mixed-citation publication-type="other" xml:lang="en">Carleo G., Cirac I., Cranmer K., Daudet L., Schuld M., Tishby M., Vogt-Maranto L., Zdeborova L. Machine Learning and the Physical Sciences. Reviews of Modern Physics, 2019, vol. 91, p. 045002. DOI: https://doi.org/10.1103/RevModPhys.91.045002</mixed-citation></ref><ref id="ref22"><mixed-citation publication-type="other" xml:lang="en">Medsker L., Jain L.C. Recurrent Neural Networks: Design and Applications. Boca Raton, CRC Press, Inc., 1999. 416 p.</mixed-citation></ref><ref id="ref23"><mixed-citation publication-type="other" xml:lang="en">Nevzorov A.A., Stankevich D.A. A Method of Wavefront Distortions Correction for an Atmospheric Optical Link with a Small Volume of Information Transmitted Through a Service Channel. Computer Optics, 2020, vol. 44, pp. 848-851. DOI: https://doi.org/10.18287/2412- 6179-CO-733</mixed-citation></ref><ref id="ref24"><mixed-citation publication-type="other" xml:lang="en">Karniadakis G.E., Kevrekidis I.G., Lu L., Perdikaris P., Wang S., Yang L. Physics- Informed Machine Learning. Nature Reviews Physics, 2021, no. 3, pp. 422-440. DOI: https://doi.org/10.1038/s42254-021-00314-5</mixed-citation></ref><ref id="ref25"><mixed-citation publication-type="other" xml:lang="en">Liao Y., Tang H., Li R., Ran L., Xie L. Response Prediction for Linear and Nonlinear Structures Based on Data-Driven Deep Learning. Applied Sciences, 2023, vol. 13, no. 10, pp. 5918. DOI: https://doi.org/10.3390/app13105918</mixed-citation></ref><ref id="ref26"><mixed-citation publication-type="other" xml:lang="en">Luo P., Zheng X., Qiu M., Gou Y., Yang Z., Qu X., Chen Z., Lin Y. Review and Prospect: Deep Learning in Nuclear Magnetic Resonance Spectroscopy. Chem. Eur. J., 2020, vol. 26, p. 10391. DOI: https://doi.org/10.1002/chem.202000246</mixed-citation></ref></ref-list></back></article>
