<?xml version="1.0"?>
<!DOCTYPE article
PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.4 20190208//EN"
       "JATS-journalpublishing1.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" article-type="research-article" dtd-version="1.4" xml:lang="en">
 <front>
  <journal-meta>
   <journal-id journal-id-type="publisher-id">Solar-Terrestrial Physics</journal-id>
   <journal-title-group>
    <journal-title xml:lang="en">Solar-Terrestrial Physics</journal-title>
    <trans-title-group xml:lang="ru">
     <trans-title>Solar-Terrestrial Physics</trans-title>
    </trans-title-group>
   </journal-title-group>
   <issn publication-format="online">2500-0535</issn>
  </journal-meta>
  <article-meta>
   <article-id pub-id-type="publisher-id">51424</article-id>
   <article-id pub-id-type="doi">10.12737/stp-91202307</article-id>
   <article-categories>
    <subj-group subj-group-type="toc-heading" xml:lang="ru">
     <subject>Results of current research</subject>
    </subj-group>
    <subj-group subj-group-type="toc-heading" xml:lang="en">
     <subject>Results of current research</subject>
    </subj-group>
    <subj-group>
     <subject>Results of current research</subject>
    </subj-group>
   </article-categories>
   <title-group>
    <article-title xml:lang="en">Application of convolution neural networks for critical frequency fₒF2 prediction</article-title>
    <trans-title-group xml:lang="ru">
     <trans-title>Применение сверточных нейронных сетей для прогнозирования критической частоты fₒF2</trans-title>
    </trans-title-group>
   </title-group>
   <contrib-group content-type="authors">
    <contrib contrib-type="author">
     <name-alternatives>
      <name xml:lang="ru">
       <surname>Салимов</surname>
       <given-names>Борис Гудратович</given-names>
      </name>
      <name xml:lang="en">
       <surname>Salimov</surname>
       <given-names>Boris Gudratovich</given-names>
      </name>
     </name-alternatives>
     <email>salimov@iszf.irk.ru</email>
     <xref ref-type="aff" rid="aff-1"/>
    </contrib>
    <contrib contrib-type="author">
     <contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-3837-8207</contrib-id>
     <name-alternatives>
      <name xml:lang="ru">
       <surname>Бернгардт</surname>
       <given-names>Олег Игоревич</given-names>
      </name>
      <name xml:lang="en">
       <surname>Berngardt</surname>
       <given-names>Oleg Igorevich</given-names>
      </name>
     </name-alternatives>
     <email>berng@iszf.irk.ru</email>
     <bio xml:lang="ru">
      <p>кандидат физико-математических наук;</p>
     </bio>
     <bio xml:lang="en">
      <p>candidate of physical and mathematical sciences;</p>
     </bio>
     <xref ref-type="aff" rid="aff-2"/>
    </contrib>
    <contrib contrib-type="author">
     <contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0125-1130</contrib-id>
     <name-alternatives>
      <name xml:lang="ru">
       <surname>Хмельнов</surname>
       <given-names>Алексей Евгеньевич</given-names>
      </name>
      <name xml:lang="en">
       <surname>Hmelnov</surname>
       <given-names>Aleksey Evgenyevich</given-names>
      </name>
     </name-alternatives>
     <email>hmelnov@icc.ru</email>
     <bio xml:lang="ru">
      <p>кандидат технических наук;</p>
     </bio>
     <bio xml:lang="en">
      <p>candidate of technical sciences;</p>
     </bio>
     <xref ref-type="aff" rid="aff-3"/>
    </contrib>
    <contrib contrib-type="author">
     <contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0847-3553</contrib-id>
     <name-alternatives>
      <name xml:lang="ru">
       <surname>Ратовский</surname>
       <given-names>Константин Геннадьевич</given-names>
      </name>
      <name xml:lang="en">
       <surname>Ratovsky</surname>
       <given-names>Konstantin Gennadyevich</given-names>
      </name>
     </name-alternatives>
     <email>ratovsky@iszf.irk.ru</email>
     <bio xml:lang="ru">
      <p>кандидат физико-математических наук;</p>
     </bio>
     <bio xml:lang="en">
      <p>candidate of physical and mathematical sciences;</p>
     </bio>
     <xref ref-type="aff" rid="aff-4"/>
    </contrib>
    <contrib contrib-type="author">
     <name-alternatives>
      <name xml:lang="ru">
       <surname>Кусонский</surname>
       <given-names>Олег Александрович</given-names>
      </name>
      <name xml:lang="en">
       <surname>Kusonsky</surname>
       <given-names>Oleg Aleksandrovich</given-names>
      </name>
     </name-alternatives>
     <email>zavlab@arti.igfuroran.ru</email>
     <bio xml:lang="ru">
      <p>кандидат геолого-минералогических наук;</p>
     </bio>
     <bio xml:lang="en">
      <p>candidate of geological and mineralogical sciences;</p>
     </bio>
     <xref ref-type="aff" rid="aff-5"/>
    </contrib>
   </contrib-group>
   <aff-alternatives id="aff-1">
    <aff>
     <institution xml:lang="ru">Институт солнечно-земной физики СО РАН</institution>
     <city>Иркутск</city>
     <country>Россия</country>
    </aff>
    <aff>
     <institution xml:lang="en">Institute of Solar Terrestrial Physics SB RAS</institution>
     <city>Irkutsk</city>
     <country>Russian Federation</country>
    </aff>
   </aff-alternatives>
   <aff-alternatives id="aff-2">
    <aff>
     <institution xml:lang="ru">Институт солнечно-земной физики СО РАН</institution>
     <city>Иркутск</city>
     <country>Россия</country>
    </aff>
    <aff>
     <institution xml:lang="en">Institute of Solar-Terrestrial Physics SB RAS</institution>
     <city>Irkutsk</city>
     <country>Russian Federation</country>
    </aff>
   </aff-alternatives>
   <aff-alternatives id="aff-3">
    <aff>
     <institution xml:lang="ru">Институт динамики систем и теории управления им. В.М. Матросова СО РАН</institution>
     <city>Иркутск</city>
     <country>Россия</country>
    </aff>
    <aff>
     <institution xml:lang="en">Matrosov Institute for System Dynamics and Control Theory SB RAS</institution>
     <city>Irkutsk</city>
     <country>Russian Federation</country>
    </aff>
   </aff-alternatives>
   <aff-alternatives id="aff-4">
    <aff>
     <institution xml:lang="ru">Институт солнечно-земной физики СО РАН</institution>
     <city>Иркутск</city>
     <country>Россия</country>
    </aff>
    <aff>
     <institution xml:lang="en">Institute of Solar-Terrestrial Physics SB RAS</institution>
     <city>Irkutsk</city>
     <country>Russian Federation</country>
    </aff>
   </aff-alternatives>
   <aff-alternatives id="aff-5">
    <aff>
     <institution xml:lang="ru">Институт геофизики УрО РАН</institution>
     <city>Екатеринбург</city>
     <country>Россия</country>
    </aff>
    <aff>
     <institution xml:lang="en">Institute of Geophysics, Ural Branch RAS</institution>
     <city>Ekaterinburg</city>
     <country>Russian Federation</country>
    </aff>
   </aff-alternatives>
   <pub-date publication-format="print" date-type="pub" iso-8601-date="2023-03-28T07:08:17+03:00">
    <day>28</day>
    <month>03</month>
    <year>2023</year>
   </pub-date>
   <pub-date publication-format="electronic" date-type="pub" iso-8601-date="2023-03-28T07:08:17+03:00">
    <day>28</day>
    <month>03</month>
    <year>2023</year>
   </pub-date>
   <volume>9</volume>
   <issue>1</issue>
   <fpage>56</fpage>
   <lpage>67</lpage>
   <history>
    <date date-type="received" iso-8601-date="2022-06-27T00:00:00+03:00">
     <day>27</day>
     <month>06</month>
     <year>2022</year>
    </date>
    <date date-type="accepted" iso-8601-date="2022-11-17T00:00:00+03:00">
     <day>17</day>
     <month>11</month>
     <year>2022</year>
    </date>
   </history>
   <self-uri xlink:href="https://naukaru.ru/en/nauka/article/51424/view">https://naukaru.ru/en/nauka/article/51424/view</self-uri>
   <abstract xml:lang="ru">
    <p>Ионосфера оказывает важное влияние на качество работы средств радиосвязи, радиолокации и глобального позиционирования. Одной из важных характеристик, описывающих состояние ионосферы, является критическая частота fₒF2. Ее прогноз позволяет обеспечить режимы эффективной работы технических радиосредств, а также рассчитать поправки, необходимые для повышения точности их функционирования. Традиционно для прогноза fₒF2 применяются различные физические и эмпирические модели. В данной работе предлагается эмпирическая методика прогноза, использующая методы машинного обучения и историю наблюдений. В ее основе лежит регрессионный подход к прогнозу по известной суточной квазипериодичности ионосферных параметров, связанной с солнечной освещенностью. Алгоритмически этот подход реализуется в виде сверточных нейронных сетей с двумерной сверткой. Исходные данные для анализа представляются в виде двумерных матриц солнечное время — дата. Модель обучена на данных среднеширотного ионозонда в Иркутске (РФ) и протестирована на данных нескольких среднеширотных ионозондов: Арти (РФ), Варшава (Польша), Мохе (Китай). Показано, что основной вклад в прогнозное значение fₒF2 вносят данные ближайших нескольких дней перед прогнозом, вклад остальных дней сильно убывает. Построенная модель обладает метриками качества прогноза fₒF2 (коэффициент корреляции Пирсона 0.928, корень среднеквадратичной ошибки 0.598 МГц, средняя абсолютная ошибка в процентах 10.45 %, коэффициент детерминации 0.861) и может быть применена для ее прогноза в средних широтах.</p>
   </abstract>
   <trans-abstract xml:lang="en">
    <p>Ionosphere has an important impact on the quality of radio communication, radar, and global positioning. One of the essential characteristics describing the state of the ionosphere is its critical frequency fₒF2. Its prediction provides effective modes of operation of technical radio equipment as well as enables calculation of the corrections needed to improve the accuracy of its functioning. Different physical and empirical models are generally used for fₒF2 prediction. This paper proposes an empirical prediction technique based on machine learning methods and observational history. It relies on a regression approach to the prediction based on the known daily quasi-periodicity of ionospheric parameters related to solar illumination. Algorithmically, this approach is implemented in the form of convolutional neural networks with two-dimensional convolution. The input data for the analysis is presented as two-dimensional solar time — date matrices. The model was trained on data from the mid-latitude ionosonde in Irkutsk (RF) and tested using data from several mid-latitude ionosondes: Arti (RF), Warsaw (Poland), Mohe (China). It is shown that the main contribution to the prediction value of fₒF2 is made by the data on the nearest few days before the prediction; the contribution of the remaining days strongly decreases. This model has the following forecast quality metrics (Pearson correlation coefficient 0.928, root mean square error 0.598 MHz, mean absolute error in percent 10.45 %, coefficient of determination 0.861) and can be applied to fₒF2 forecast in middle latitudes.</p>
   </trans-abstract>
   <kwd-group xml:lang="ru">
    <kwd>ионосфера</kwd>
    <kwd>машинное обучение</kwd>
    <kwd>нейронные сети</kwd>
    <kwd>fₒF2</kwd>
   </kwd-group>
   <kwd-group xml:lang="en">
    <kwd>ionosphere</kwd>
    <kwd>machine learning</kwd>
    <kwd>neural networks</kwd>
    <kwd>fₒF2</kwd>
   </kwd-group>
   <funding-group>
    <funding-statement xml:lang="ru">Исследование выполнено при финансовой поддержке Минобрнауки России</funding-statement>
    <funding-statement xml:lang="en">The work was financially supported by the Ministry of Science and Higher Education of the Russian Federation</funding-statement>
   </funding-group>
  </article-meta>
 </front>
 <body>
  <p></p>
 </body>
 <back>
  <ref-list>
   <ref id="B1">
    <label>1.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Бархатов Н.А., Ревунов С.Е., Урядов В.П. Технология искусственных нейронных сетей для прогнозирования критической частоты ионосферного слоя F2. Изв. вузов. Радиофизика. 2005. Т. 48, № 1. С. 1-15.</mixed-citation>
     <mixed-citation xml:lang="en">Abadi M., Barham P., Chen J., Chen Z., Davis A., Dean J., Devin M., Ghemawat S. TensorFlow: A system for large-scale machine learning. Proc. OSDI. 2016, pp. 265-283. DOI: 10.5281/ zenodo.4724125.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B2">
    <label>2.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Ратовский К.Г., Потехин А.П., Медведев А.В., Куркин В.И. Современный цифровой ионозонд DPS-4 и его возможности. Солнечно-земная физика. 2004. Вып. 5. С. 102-104.</mixed-citation>
     <mixed-citation xml:lang="en">Barkhatov N.A., Revunov S.E., Urjadov V.P. Artificial neural network technology for forecasting critical frequency of ionospheric layer F2. Proceedings of Higher Educational Institutions. Radiophysics. 2005, vol. 48, iss. 1, pp. 1-15. (In Russian).</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B3">
    <label>3.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Салимов Б.Г., Хмельнов А.Е. Предсказание критической частоты ионосферы foF2 с помощью нейронной рекуррентной LSTM сети. Материалы rонференции «Ляпуновские чтения»:. Иркутск, 7-11 декабря 2020 г. Иркутск: ИДСТУ СО РАН, 2020. С. 60-61.</mixed-citation>
     <mixed-citation xml:lang="en">Bilitza D., Mckinnell L.-A., Reinisch B., Fuller-Rowell T. The International Reference Ionosphere (IRI) today and in the future. J. Geodesy. 2011, vol. 85. DOI: 10.1007/s00190-010-0427-x.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B4">
    <label>4.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Смирнов В.Ф., Степанов А.Е. Новые возможности в исследованиях высокоширотной ионосферы: дигизонд DPS-4 - первые результаты по измерениям локализации и динамики крупномасштабных структур ионосферы в Якутске. Солнечно-земная физика. 2004. Вып. 5 (118). С. 105-106.</mixed-citation>
     <mixed-citation xml:lang="en">Boulch A., Cherrier N., Castaings T. Ionospheric activity prediction using convolutional recurrent neural networks. 2018. DOI: 10.48550/arXiv.1810.13273.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B5">
    <label>5.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Харгривс Дж. К. Верхняя атмосфера и солнечно-земные связи. Введение в физику околоземной космической среды. Ленинград, Гидрометеоиздат, 1982. 351 с.</mixed-citation>
     <mixed-citation xml:lang="en">Breiman L. Bagging Predictors. Technical Report. 1994, No. 421.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B6">
    <label>6.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Abadi M., Barham P., Chen J., et al., TensorFlow: A system for large-scale machine learning. Proc. OSDI. 2016. P. 265-283. DOI: 10.5281/zenodo.4724125.</mixed-citation>
     <mixed-citation xml:lang="en">Bring J. How to standardize regression coefficients. The American Statistician. 1994, vol. 48, no. 3, pp. 209-213. DOI: 10.2307/2684719.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B7">
    <label>7.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Bilitza D., Mckinnell L.-A., Reinisch B., Fuller-Rowell T. The International Reference Ionosphere (IRI) today and in the future. J. Geodesy. 2011. Vol. 85. DOI: 10.1007/s00190-010-0427-x.</mixed-citation>
     <mixed-citation xml:lang="en">Consultative Committee on International Radio (CCIR) Atlas of Ionospheric Characteristics Report 340. International Telecommunication Union, Geneva, Switzerland, 1967.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B8">
    <label>8.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Boulch A., Cherrier N., Castaings T. Ionospheric activity prediction using convolutional recurrent neural networks. 2018. DOI: 10.48550/arXiv.1810.13273.</mixed-citation>
     <mixed-citation xml:lang="en">Galkin I.A., Reinisch B., Vesnin A.M., Huang X. Assimilation of sparse continuous groundbased ionosonde data into IRI using NECTAR model morphing. The 1st URSI Atlantic Radio Science Conference (URSI AT-RASC). Las Palmas, 2015, pp. 1-8. DOI: 10.1109/URSI-AT-RASC.2015.7303112.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B9">
    <label>9.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Breiman L. Bagging Predictors. Technical Report. 1994. No. 421.</mixed-citation>
     <mixed-citation xml:lang="en">Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016, 800 p.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B10">
    <label>10.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Bring J. How to standardize regression coefficients. The American Statistician. 1994. Vol. 48, no. 3. P. 209-213. DOI: 10.2307/2684719.</mixed-citation>
     <mixed-citation xml:lang="en">Hargrivs J.K. Upper atmosphere and solar-terrestrial connections. Introduction to Physics of the Near-Earth Space Environment. Leningrad, Gidrometeoizdat, 1982, 351 p. (In Russian).</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B11">
    <label>11.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Consultative Committee on International Radio (CCIR) Atlas of Ionospheric Characteristics Report 340. International Telecommunication Union, Geneva, Switzerland, 1967.</mixed-citation>
     <mixed-citation xml:lang="en">Kingma D.P., Ba J.A. A Method for Stochastic Optimization. International Conference on Learning Representations. 2014. DOI: 10.48550/arXiv.1412.6980.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B12">
    <label>12.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Galkin I.A., Reinisch B., Vesnin A.M., Huang X. Assimilation of sparse continuous groundbased ionosonde data into IRI using NECTAR model morphing. The 1st URSI Atlantic Radio Science Conference (URSI AT-RASC). Las Palmas, 2015. P. 1-8, DOI: 10.1109/URSI-AT-RASC.2015.7303112.</mixed-citation>
     <mixed-citation xml:lang="en">Lundberg S., Lee, S.-I. A Unified Approach to Interpreting Model Predictions. arXiv. 2017. DOI: 10.48550/ARXIV. 1705.07874.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B13">
    <label>13.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016. 800 p.</mixed-citation>
     <mixed-citation xml:lang="en">Opitz D., Maclin R. Popular ensemble methods: An empirical study. J. Artificial Intelligence Res. 1999, vol. 11, pp. 169-198. DOI: 10.1613/jair.614.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B14">
    <label>14.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Kingma D.P., Ba J.А. A Method for Stochastic Optimization. International Conference on Learning Representations. 2014. DOI: 10.48550/arXiv.1412.6980.</mixed-citation>
     <mixed-citation xml:lang="en">Ratovsky K.G., Potekhin A.P., Medvedev A.V., Kurkin V.I. Modern Digital Ionosonde DPS-4 and its capabilities. Solar-Terr. Phys. 2004, iss. 5, pp. 102-104. (In Russian).</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B15">
    <label>15.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Lundberg S., Lee S.-I. A Unified Approach to Interpreting Model Predictions. arXiv. 2017. DOI: 10.48550/ARXIV. 1705.07874.</mixed-citation>
     <mixed-citation xml:lang="en">Rush C., Fox M., Bilitza D., Davies K., McNamara L., Stewart F., PoKempner M. Ionospheric mapping - an update of foF2 coefficients. Telecommun. J. 1989, vol. 56, iss. 3, pp. 179-182.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B16">
    <label>16.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Opitz D., Maclin R. Popular ensemble methods: an empirical study. J. Artificial Intelligence Res. 1999. Vol. 11. P. 169-198. DOI: 10.1613/jair.614.</mixed-citation>
     <mixed-citation xml:lang="en">Salimov B.G., Khmelnov A.E. Prediction of the critical frequency of the ionosphere foF2 using a neural recurrent LSTM network. Proc. Conference “Lyapunovskie Chteniya”. ISDC SB RAS, Irkutsk, 2020, pp. 60-61. (In Russian).</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B17">
    <label>17.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Rush C., Fox M., Bilitza D., et al. Ionospheric mapping - an update of foF2 coefficients. Telecommun. J. 1989. Vol. 56. P. 179-182.</mixed-citation>
     <mixed-citation xml:lang="en">Sivavaraprasad G., Lakshmi Mallika I., Sivakrishna K., Venkata Ratnam D. A novel hybrid machine learning model to forecast ionospheric TEC over low-latitude GNSS stations. Adv. Space Res. 2022, vol. 69, iss. 3, pp. 1366-1379. DOI: 10.1016/j.asr.2021.11.033.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B18">
    <label>18.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Sivavaraprasad G., Lakshmi Mallika I., Sivakrishna K., Venkata Ratnam D. A novel hybrid Machine learning model to forecast ionospheric TEC over low-latitude GNSS stations. Adv. Space Res. 2022. Vol. 69, iss. 3. P. 1366-1379. DOI: 10.1016/j.asr.2021.11.033.</mixed-citation>
     <mixed-citation xml:lang="en">Smirnov V.F., Stepanov A.E. New capabilities in studies of the high-latitude ionosphere: DPS-4 digisonde first results on measurements of localization and dynamics of large-scale ionospheric structures in Yakutsk. Solar-Terr. Phys. 2004, no. 5 (118), pp. 105-106. (In Russian).</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B19">
    <label>19.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">Yu S., Ma J. Deep learning for geophysics: Current and future trends. Rev. Geophys. 2021. Vol. 59, iss. 3. e2021RG000742. DOI: 10.1029/2021RG000742.</mixed-citation>
     <mixed-citation xml:lang="en">Yu S., Ma J. Deep learning for geophysics: Current and future trends. Rev. Geophys. 2021, vol. 59, iss. 3, e2021RG000742. DOI: 10.1029/2021RG000742.</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B20">
    <label>20.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">URL: http://irimodel.org/IRI-2016 (дата обращения 27 июня 2019 г.).</mixed-citation>
     <mixed-citation xml:lang="en">URL: http://irimodel.org/IRI-2016 (accessed June 27, 2019).</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B21">
    <label>21.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">URL: https://ckp-rf.ru/catalog/ckp/3056 (дата обращения 3 октября 2018 г.).</mixed-citation>
     <mixed-citation xml:lang="en">URL: https://ckp-rf.ru/catalog/ckp/3056 (accessed October 3, 2018).</mixed-citation>
    </citation-alternatives>
   </ref>
   <ref id="B22">
    <label>22.</label>
    <citation-alternatives>
     <mixed-citation xml:lang="ru">URL: https://omniweb.gsfc.nasa.gov/form/dx1.html (дата обращения 31 августа 2020 г.).</mixed-citation>
     <mixed-citation xml:lang="en">URL: https://omniweb.gsfc.nasa.gov/form/dx1.html (accessed August 31, 2020).</mixed-citation>
    </citation-alternatives>
   </ref>
  </ref-list>
 </back>
</article>
