<?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">geophystech</journal-id><journal-title-group><journal-title xml:lang="ru">Геофизические технологии</journal-title><trans-title-group xml:lang="en"><trans-title>Russian Journal of Geophysical Technologies</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">2619-1563</issn><publisher><publisher-name>IPGG SB RAS</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18303/2619-1563-2024-1-6</article-id><article-id custom-type="elpub" pub-id-type="custom">geophystech-343</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>Статьи</subject></subj-group></article-categories><title-group><article-title>Адаптивная оптимизация обучающей выборки при нейросетевом подходе к подавлению численной дисперсии в данных сейсмического моделирования</article-title><trans-title-group xml:lang="en"><trans-title>Adaptive training dataset generation for neural network numerical dispersion mitigation approach in seismic modeling</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-0581-7741</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гадыльшина</surname><given-names>К. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Gadylshina</surname><given-names>K. А.</given-names></name></name-alternatives><bio xml:lang="ru"><p>ГАДЫЛЬШИНА Ксения Александровна – младший научный сотрудник лаборатории вычислительной физики горных пород,</p><p>630090, Новосибирск, просп. Акад. Коптюга, 3.</p></bio><bio xml:lang="en"><p>3, Koptyug Ave., Novosibirsk, 630090.</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-3544-4878</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Лисица</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Lisitsa</surname><given-names>V. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>ЛИСИЦА Вадим Викторович – доктор физико-математических наук, заведующий лабораторией вычислительной физики горных пород,</p><p>630090, Новосибирск, просп. Акад. Коптюга, 3.</p></bio><bio xml:lang="en"><p>3, Koptyug Ave., Novosibirsk, 630090.</p></bio><email xlink:type="simple">LisitsaVV@ipgg.sbras.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7247-6911</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Гадыльшин</surname><given-names>К. Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Gadylshin</surname><given-names>K. G.</given-names></name></name-alternatives><bio xml:lang="ru"><p>ГАДЫЛЬШИН Кирилл Геннадьевич – кандидат физико-математических наук, старший научный сотрудник лаборатории вычислительной физики горных пород,</p><p>630090, Новосибирск, просп. Акад. Коптюга, 3.</p></bio><bio xml:lang="en"><p>3, Koptyug Ave., Novosibirsk, 630090.</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1439-4552</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Вишневский</surname><given-names>Д. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Vishnevsky</surname><given-names>D. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>ВИШНЕВСКИЙ Дмитрий Михайлович – научный сотрудник лаборатории вычислительной физики горных пород,</p><p>630090, Новосибирск, просп. Акад. Коптюга, 3.</p></bio><bio xml:lang="en"><p>3, Koptyug Ave., Novosibirsk, 630090.</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Костин</surname><given-names>В. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Kostin</surname><given-names>V. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>КОСТИН Виктор Иванович – кандидат физико-математических наук, старший научный сотрудник лаборатории вычислительной физики горных пород,</p><p>630090, Новосибирск, просп. Акад. Коптюга, 3,</p></bio><bio xml:lang="en"><p>3, Koptyug Ave., Novosibirsk, 630090.</p></bio><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Институт нефтегазовой геологии и геофизики им. А.А. Трофимука СО РАН<country>Россия</country></aff><aff xml:lang="en">Trofimuk Institute of Petroleum Geology and Geophysics SB RAS<country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>16</day><month>07</month><year>2024</year></pub-date><volume>0</volume><issue>1</issue><issue-title>Спецвыпуск</issue-title><fpage>6</fpage><lpage>18</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Гадыльшина К.А., Лисица В.В., Гадыльшин К.Г., Вишневский Д.М., Костин В.И., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Гадыльшина К.А., Лисица В.В., Гадыльшин К.Г., Вишневский Д.М., Костин В.И.</copyright-holder><copyright-holder xml:lang="en">Gadylshina K.А., Lisitsa V.V., Gadylshin K.G., Vishnevsky D.M., Kostin V.I.</copyright-holder><license 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://www.rjgt.ru/jour/article/view/343">https://www.rjgt.ru/jour/article/view/343</self-uri><abstract><p>Представлен новый подход к построению обучающей выборки для NDM-net (Numerical dispersion mitigation neural network) – искусственной нейронной сети, применяющейся для подавления численной ошибки в результатах численного сейсмического моделирования. На первом этапе небольшое количество сейсмограмм, рассчитанных с использованием грубой и мелкой сеток, используется для обучения сети, сопоставляющей неточные данные, полученные в результате расчета на крупной сетке, с высококачественными данными с мелкой сетки. Затем сеть NDM-net обрабатывает весь набор данных, предварительно рассчитанных с использованием грубой сетки, для уменьшения численной ошибки. Самая трудоемкая часть предлагаемого алгоритма – генерация набора обучающих данных. Возникает необходимость минимизировать количество сейсмограмм в наборе обучающих данных без потери качества обучения. Выбор обучающих данных осуществляется с фиксацией расстояния Хаусдорфа между набором обучающих данных и всем набором данных. При этом уровень предельного расстояния варьируется в зависимости от используемой для моделирования сейсмогеологической модели. Показано, что адаптивная стратегия предпочтительнее фиксированного ограничения метрики Хаусдорфа, поскольку она позволяет сократить набор обучающих данных без потери точности работы обученной сети NDM-net.</p></abstract><trans-abstract xml:lang="en"><p>We introduce a novel method for developing the training dataset for the Numerical Dispersion Mitigation network (NDM-net), aimed at diminishing numerical inaccuracies in seismic modeling. Our strategy involves using a limited set of seismograms, produced with coarse and fine grids, to train the network. This training enables the network to transform less accurate coarse-grid data into higher-quality fine-grid data. Subsequently, the network is employed on a more extensive set of seismograms, initially computed with the coarse grid, to lower numerical errors. Creating the training dataset is the most demanding aspect of this method, requiring a balance between the number of seismograms used and maintaining training effectiveness. We propose a method to create the training dataset that maintains a specific Hausdorff distance with the complete dataset. However, this distance can vary based on the seismic-geological model used in simulations. Our work shows that an adaptive approach in setting the Hausdorff distance limit is more advantageous than a fixed limit, as it reduces the training dataset size without compromising accuracy.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>сейсмическое моделирование</kwd><kwd>численная дисперсия</kwd><kwd>глубокое обучение</kwd></kwd-group><kwd-group xml:lang="en"><kwd>seismic modeling</kwd><kwd>numerical dispersion</kwd><kwd>deep learning</kwd></kwd-group><funding-group xml:lang="ru"><funding-statement>Работа выполнена при поддержке Российского научного фонда, грант № 22-11-00004.</funding-statement></funding-group><funding-group xml:lang="en"><funding-statement>The work was supported by the Russian Science Foundation, Project No. 22-11-00004.</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">Gadylshin K., Lisitsa V., Gadylshina K., Vishnevsky D. Optimization of the training dataset for numerical dispersion mitigation neural network // Lecture Notes in Computer Science. 2022a. Vol. 13378 LNCS. P. 295–309. doi: 10.1007/978-3-031-10562-3_22.</mixed-citation><mixed-citation xml:lang="en">Gadylshin K., Lisitsa V., Gadylshina K., Vishnevsky D. Optimization of the training dataset for numerical dispersion mitigation neural network // Lecture Notes in Computer Science. 2022a. Vol. 13378 LNCS. P. 295–309. doi: 10.1007/978-3-031-10562-3_22.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Gadylshin K., Vishnevsky D., Gadylshina K., Lisitsa V. Numerical dispersion mitigation neural network for seismic modeling // Geophysics. 2022b. Vol. 87 (3). P. T237–T249. doi: 10.1190/geo2021-0242.1.</mixed-citation><mixed-citation xml:lang="en">Gadylshin K., Vishnevsky D., Gadylshina K., Lisitsa V. Numerical dispersion mitigation neural network for seismic modeling // Geophysics. 2022b. Vol. 87 (3). P. T237–T249. doi: 10.1190/geo2021-0242.1.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Koene E.F.M., Robertsson J.O.A., Broggini F., Andersson F. Eliminating time dispersion from seismic wave modeling // Geophysical Journal International. 2017. Vol. 213 (1). P. 169–180. doi: 10.1093/gji/ggx563.</mixed-citation><mixed-citation xml:lang="en">Koene E.F.M., Robertsson J.O.A., Broggini F., Andersson F. Eliminating time dispersion from seismic wave modeling // Geophysical Journal International. 2017. Vol. 213 (1). P. 169–180. doi: 10.1093/gji/ggx563.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Levander A.R. Fourth-order finite-difference P-SV seismograms // Geophysics. 1988. Vol. 53 (11). P. 1425–1436. doi: 10.1190/1.1442422.</mixed-citation><mixed-citation xml:lang="en">Levander A.R. Fourth-order finite-difference P-SV seismograms // Geophysics. 1988. Vol. 53 (11). P. 1425–1436. doi: 10.1190/1.1442422.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Lisitsa V., Podgornova O., Tcheverda V. On the interface error analysis for finite difference wave simulation // Computational Geosciences. 2010. Vol. 14 (4). P. 769–778. doi: 10.1007/s10596-010-9187-1.</mixed-citation><mixed-citation xml:lang="en">Lisitsa V., Podgornova O., Tcheverda V. On the interface error analysis for finite difference wave simulation // Computational Geosciences. 2010. Vol. 14 (4). P. 769–778. doi: 10.1007/s10596-010-9187-1.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Mittet R. Second-order time integration of the wave equation with dispersion correction procedures // Geophysics. 2019. Vol. 84 (4). P. T221–T235. doi: 10.1190/geo2018-0770.1.</mixed-citation><mixed-citation xml:lang="en">Mittet R. Second-order time integration of the wave equation with dispersion correction procedures // Geophysics. 2019. Vol. 84 (4). P. T221–T235. doi: 10.1190/geo2018-0770.1.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Moczo P., Kristek J., Vavrycuk V., Archuleta R.J., Halada L. 3D heterogeneous staggered-grid finitedifference modeling of seismic motion with volume harmonic and arithmetic averaging of elastic moduli and densities // Bulletin of the Seismological Society of America. 2002. Vol. 92 (8). P. 3042–3066. doi: 10.1785/0120010167.</mixed-citation><mixed-citation xml:lang="en">Moczo P., Kristek J., Vavrycuk V., Archuleta R.J., Halada L. 3D heterogeneous staggered-grid finitedifference modeling of seismic motion with volume harmonic and arithmetic averaging of elastic moduli and densities // Bulletin of the Seismological Society of America. 2002. Vol. 92 (8). P. 3042–3066. doi: 10.1785/0120010167.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Siahkoohi A., Louboutin M., Herrmann F.J. The importance of transfer learning in seismic modeling and imaging // Geophysics. 2019. Vol. 84 (6). P. A47–A52. doi: 10.1190/geo2019-0056.1.</mixed-citation><mixed-citation xml:lang="en">Siahkoohi A., Louboutin M., Herrmann F.J. The importance of transfer learning in seismic modeling and imaging // Geophysics. 2019. Vol. 84 (6). P. A47–A52. doi: 10.1190/geo2019-0056.1.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Virieux J. P-SV wave propagation in heterogeneous media: Velocity-stress finite-difference method // Geophysics. 1986. Vol. 51 (4). P. 889–901. doi: 10.1190/1.1442147.</mixed-citation><mixed-citation xml:lang="en">Virieux J. P-SV wave propagation in heterogeneous media: Velocity-stress finite-difference method // Geophysics. 1986. Vol. 51 (4). P. 889–901. doi: 10.1190/1.1442147.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Virieux J., Calandra H., Plessix R.-E. A review of the spectral, pseudo-spectral, finite-difference and finite-element modelling techniques for geophysical imaging // Geophysical Prospecting. 2011. Vol. 59 (5). P. 794–813. doi: 10.1111/j.1365-2478.2011.00967.x.</mixed-citation><mixed-citation xml:lang="en">Virieux J., Calandra H., Plessix R.-E. A review of the spectral, pseudo-spectral, finite-difference and finite-element modelling techniques for geophysical imaging // Geophysical Prospecting. 2011. Vol. 59 (5). P. 794–813. doi: 10.1111/j.1365-2478.2011.00967.x.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Vishnevsky D., Lisitsa V., Tcheverda V., Reshetova G. Numerical study of the interface errors of finitedifference simulations of seismic waves // Geophysics. 2014. Vol. 79 (4). P. T219–T232. doi: 10.1190/geo2013-0299.1.</mixed-citation><mixed-citation xml:lang="en">Vishnevsky D., Lisitsa V., Tcheverda V., Reshetova G. Numerical study of the interface errors of finitedifference simulations of seismic waves // Geophysics. 2014. Vol. 79 (4). P. T219–T232. doi: 10.1190/geo2013-0299.1.</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>
