<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" 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" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">npe</journal-id><journal-title-group><journal-title xml:lang="ru">Ядерная физика и инжиниринг</journal-title><trans-title-group xml:lang="en"><trans-title>Nuclear Physics and Engineering</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2079-5629</issn><issn pub-type="epub">2079-5637</issn><publisher><publisher-name>МИФИ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.56304/S2079562923010116</article-id><article-id custom-type="elpub" pub-id-type="custom">npe-323</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>Математическое моделирование в ядерных технологиях</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Mathematical Modeling in Nuclear Technologies</subject></subj-group></article-categories><title-group><article-title>ПРИМЕНЕНИЕ МЕТОДОВ МАШИННОГО ОБУЧЕНИЯ В ЭКСПЕРИМЕНТЕ БАЙКАЛ-GVD</article-title><trans-title-group xml:lang="en"><trans-title>Application of Machine Learning Methods in the Baikal-GVD Experiment</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Харук</surname><given-names>И. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kharuk</surname><given-names>I. V.</given-names></name></name-alternatives><email xlink:type="simple">ivan.kharuk@phystech.edu</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Мацейко</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Matseiko</surname><given-names>А. V.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Леонов</surname><given-names>А. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Leonov</surname><given-names>А. Yu.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Институт ядерных исследований Российской академии наук, Москва, 117312 Россия&#13;
&#13;
Московский физико-технический институт, Долгопрудный, 141700 Россия</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Institute for Nuclear Research, Russian Academy of Sciences, Moscow, 117312 Russia&#13;
&#13;
Moscow Institute of Physics and Technology, Dolgoprudny, 141700 Russia</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>05</day><month>07</month><year>2024</year></pub-date><volume>15</volume><issue>1</issue><fpage>36</fpage><lpage>42</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Харук И.В., Мацейко А.В., Леонов А.Ю., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Харук И.В., Мацейко А.В., Леонов А.Ю.</copyright-holder><copyright-holder xml:lang="en">Kharuk I.V., Matseiko А.V., Leonov А.Y.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://npe.elpub.ru/jour/article/view/323">https://npe.elpub.ru/jour/article/view/323</self-uri><abstract><p>Эксперимент Байкал-GVD – это нейтринный телескоп, расположенный в озере Байкал, Россия. По состоянию на 2022 г., его эффективный объем составляет 0.5 км3, что делает его крупнейшим нейтринным телескопом в северном полушарии и вторым по величине в мире. В настоящей работе представлен обзор методов машинного обучения, разработанных для анализа данных эксперимента Байкал-GVD. А именно, обсуждаются нейронные сети, разработанные для: (1) подавления шумовых срабатываний оптических модулей, (2) выделения событий, индуцированных нейтрино, а также оценки их потока, и (3) восстановления угла прилета нейтрино. Показано, что нейронные сети сравнимы или превосходят по точности стандартные алгоритмические процедуры реконструкции событий для аналогичных задач.</p></abstract><trans-abstract xml:lang="en"><p>The Baikal-GVD experiment is a neutrino telescope located in Lake Baikal, Russia. As of 2022, it has an effective volume of 0.5 km3, which makes it the largest neutrino telescope in the Northern Hemisphere and the second largest in the world. This article presents an overview of machine learning methods developed to analyze data from the Baikal-GVD experiment. Specifically, we discuss neural networks developed to (1) suppress noise responses of optical modules, (2) identify neutrino-induced events and estimate their flux, and (3) recover the neutrino arrival angle. It is shown that neural networks are comparable or superior in accuracy to standard algorithmic event reconstruction procedures for similar problems.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>нейтрино</kwd><kwd>Байкал-GVD</kwd><kwd>машинное обучение</kwd><kwd>нейронные сети</kwd><kwd>анализ данных</kwd></kwd-group><kwd-group xml:lang="en"><kwd>neutrinos</kwd><kwd>Baikal-GVD</kwd><kwd>machine learning</kwd><kwd>neural networks</kwd><kwd>data analysis</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Данная работа была сделана при поддержке гранта Российского Научного Фонда номер 22-22-20063.</funding-statement><funding-statement xml:lang="en">This work was supported by the Russian Science Foundation, project no. 22-22-20063.</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Aartsen M.G. et al.&lt;/em&gt; // Science. 2013. V. 342. P. 1242856. https://arxiv.org/abs/1311.5238.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Aartsen M.G. et al.&lt;/em&gt; // Science. 2013. V. 342. P. 1242856. https://arxiv.org/abs/1311.5238.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Belolaptikov I. et al.&lt;/em&gt; // Proc. PoS ICRC2021. P. 002. https://arxiv.org/abs/2109.14344.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Belolaptikov I. et al.&lt;/em&gt; // Proc. PoS ICRC2021. P. 002. https://arxiv.org/abs/2109.14344.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Allakhverdyan V.A. et al.&lt;/em&gt; // Phys. Rev. D. 2023. V. 107. P. 042005. https://arxiv.org/abs/2211.09447.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Allakhverdyan V.A. et al.&lt;/em&gt; // Phys. Rev. D. 2023. V. 107. P. 042005. https://arxiv.org/abs/2211.09447.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Aiello S. et al.&lt;/em&gt; // Astropart. Phys. 2019. V. 111. P. 100−110. https://arxiv.org/abs/1810.08499.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Aiello S. et al.&lt;/em&gt; // Astropart. Phys. 2019. V. 111. P. 100−110. https://arxiv.org/abs/1810.08499.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Aartsen M.G., Abbasi R., Ackermann M. et al.&lt;/em&gt; // J. Phys. G. 2021. V. 48. P. 060501.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Aartsen M.G., Abbasi R., Ackermann M. et al.&lt;/em&gt; // J. Phys. G. 2021. V. 48. P. 060501.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Malyshkin Y. et al.&lt;/em&gt; // Nucl. Instrum. Methods. Phys. Res. B. 2023. V. 1050. P. 168117.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Malyshkin Y. et al.&lt;/em&gt; // Nucl. Instrum. Methods. Phys. Res. B. 2023. V. 1050. P. 168117.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Choma N., Monti F., Gerhardt L., et al.&lt;/em&gt; // https://arxiv.org/abs/1809.06166.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Choma N., Monti F., Gerhardt L., et al.&lt;/em&gt; // https://arxiv.org/abs/1809.06166.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Huennefeld M.&lt;/em&gt; // Proc. PoS ICRC2017. P. 1057.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Huennefeld M.&lt;/em&gt; // Proc. PoS ICRC2017. P. 1057.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Huennefeld M.&lt;/em&gt; // EPJ Web of Conf. 2019. V. 207. P. 05005.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Huennefeld M.&lt;/em&gt; // EPJ Web of Conf. 2019. V. 207. P. 05005.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Reck S., Guderian D., Vermarien G., Domi A.&lt;/em&gt; // J. Instrum. 2021. V. 16. P. C10011. https://arxiv.org/abs/2107.13375.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Reck S., Guderian D., Vermarien G., Domi A.&lt;/em&gt; // J. Instrum. 2021. V. 16. P. C10011. https://arxiv.org/abs/2107.13375.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Aiello S., Albert A., Garre S.A., et al.&lt;/em&gt; // J. Instrum. 2020. V. 15. P. P10005.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Aiello S., Albert A., Garre S.A., et al.&lt;/em&gt; // J. Instrum. 2020. V. 15. P. P10005.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Ronneberger O., Fischer P., Brox T.&lt;/em&gt; // Proc. Intl. Conf. on Medical Image Computing and Computer-Assisted Intervention. P. 234−241.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Ronneberger O., Fischer P., Brox T.&lt;/em&gt; // Proc. Intl. Conf. on Medical Image Computing and Computer-Assisted Intervention. P. 234−241.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Avrorin A.D. et al.&lt;/em&gt; // Proc. PoS ICRC2021 P. 1063. https://arxiv.org/abs/2108.00208.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Avrorin A.D. et al.&lt;/em&gt; // Proc. PoS ICRC2021 P. 1063. https://arxiv.org/abs/2108.00208.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Lin T.-Y., Goyal P., Girshick R., He K., Doll’ar P.&lt;/em&gt; // Proc. IEEE Intl. Conf. on Computer Vision. P. 2980−2988.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Lin T.-Y., Goyal P., Girshick R., He K., Doll’ar P.&lt;/em&gt; // Proc. IEEE Intl. Conf. on Computer Vision. P. 2980−2988.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">&lt;em&gt;Wang Y., Sun Y., Liu Z., Sarma S.E., Bronstein M.M., Solomon J.M.&lt;/em&gt; // ACM Trans. Graph. 2019. V. 38. P. 1−12.</mixed-citation><mixed-citation xml:lang="en">&lt;em&gt;Wang Y., Sun Y., Liu Z., Sarma S.E., Bronstein M.M., Solomon J.M.&lt;/em&gt; // ACM Trans. Graph. 2019. V. 38. P. 1−12.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
