<?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">geores</journal-id><journal-title-group><journal-title xml:lang="ru">Георесурсы</journal-title><trans-title-group xml:lang="en"><trans-title>Georesources</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1608-5043</issn><issn pub-type="epub">1608-5078</issn><publisher><publisher-name>Georesursy LLC</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18599/grs.2026.3.15</article-id><article-id custom-type="elpub" pub-id-type="custom">geores-768</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><subj-group subj-group-type="section-heading" xml:lang="en"><subject>RESEARCH ARTICLES</subject></subj-group></article-categories><title-group><article-title>Автоматизированное прослеживание сейсмических отражающих горизонтов по разреженной экспертной разметке методами глубокого обучения: апробация на клиноформных ачимовских отложениях севера Западной Сибири</article-title><trans-title-group xml:lang="en"><trans-title>Reinforcement-Learning Tracking of Seismic Horizons From Sparse Expert Interpretation: A Case Study on the Achimov Clinoform Deposits of Northern West Siberia</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-3276-7508</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Богоедов</surname><given-names>Д. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Bogoedov</surname><given-names>D. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Даниил Александрович Богоедов – руководитель отдела R&amp;D; специалист</p><p>Москва</p></bio><bio xml:lang="en"><p>Daniil Bogoedov – Head of R&amp;D</p><p>Moscow</p></bio><email xlink:type="simple">d.bogoedov@geoplat.com</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>Безухов</surname><given-names>Н. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Bezukhov</surname><given-names>N. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Никита Сергеевич Безухов – ведущий специалист по Data Science</p><p>Москва</p></bio><bio xml:lang="en"><p>Nikita Bezukhov – Lead Data Scientist</p><p>Moscow</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Павлюк</surname><given-names>А. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Pavliuk</surname><given-names>A. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Анастасия Игоревна Павлюк – руководитель проектов</p><p>Москва</p></bio><bio xml:lang="en"><p>Anastasia Pavliuk – Head of Projects</p><p>Moscow</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Авдеев</surname><given-names>П. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Avdeev</surname><given-names>P. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Павел Александрович Авдеев – старший менеджер отдела продаж</p><p>Москва</p></bio><bio xml:lang="en"><p>Pavel Avdeev – Senior Sales Manager</p><p>Moscow</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Базанов</surname><given-names>А. К.</given-names></name><name name-style="western" xml:lang="en"><surname>Bazanov</surname><given-names>A. K.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Андрей Константинович Базанов – директор по развитию бизнеса</p><p>Москва</p></bio><bio xml:lang="en"><p>Andrey Bazanov – Chief Business Development Officer (CBDO)</p><p>Moscow</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ефремов</surname><given-names>И. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Efremov</surname><given-names>I. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Иван Игоревич Ефремов – генеральный директор</p><p>Москва</p></bio><bio xml:lang="en"><p>Igor Efremov – Chief Executive Officer (CEO)</p><p>Moscow</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шакиров</surname><given-names>Р. Р.</given-names></name><name name-style="western" xml:lang="en"><surname>Shakirov</surname><given-names>R. R.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Равиль Рамильевич Шакиров – директор департаментаподготовки ресурсной базы</p><p>Тюмень</p></bio><bio xml:lang="en"><p>Ravil R. Shakirov – Head of the Resource Base Department</p><p>Tyumen</p></bio><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шаповалов</surname><given-names>М. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Shapovalo</surname><given-names>M. Yu.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Михаил Юрьевич Шаповалов – кандидат геол.-минерал. наук, старший эксперт</p><p>Тюмень</p></bio><bio xml:lang="en"><p>Mikhail Yu. Shapovalov – Cand Sci. (Geology and Mineralogy), Senior Expert</p><p>Tyumen</p></bio><xref ref-type="aff" rid="aff-3"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>ООО «ГРИДПОИНТ ДАЙНАМИКС»; &#13;
Сколковский институт науки и технологий</institution><country>Россия</country></aff><aff xml:lang="en"><institution>GridPoint Dynamics LLC; Skolkovo Institute of Science and Technology (Skoltech)</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>ООО «ГРИДПОИНТ ДАЙНАМИКС»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>GridPoint Dynamics LLC</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>ООО «НОВАТЭК НТЦ»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>NOVATEK NTC LLC</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>08</day><month>10</month><year>2026</year></pub-date><volume>28</volume><issue>3</issue><fpage>107</fpage><lpage>116</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Богоедов Д.А., Безухов Н.С., Павлюк А.И., Авдеев П.А., Базанов А.К., Ефремов И.И., Шакиров Р.Р., Шаповалов М.Ю., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Богоедов Д.А., Безухов Н.С., Павлюк А.И., Авдеев П.А., Базанов А.К., Ефремов И.И., Шакиров Р.Р., Шаповалов М.Ю.</copyright-holder><copyright-holder xml:lang="en">Bogoedov D.A., Bezukhov N.S., Pavliuk A.I., Avdeev P.A., Bazanov A.K., Efremov I.I., Shakirov R.R., Shapovalo M.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://www.geors.ru/jour/article/view/768">https://www.geors.ru/jour/article/view/768</self-uri><abstract><p>Структурная корреляция отражающих горизонтов остаётся одной из наиболее трудоёмких операций интерпретации сейсморазведки 3D, особенно в клиноформных неокомских разрезах Западной Сибири, где целевые отражения характеризуются изменчивой динамикой, выклиниванием и осложнены разрывными нарушениями. Прослеживание сейсмического горизонта является последовательной задачей, поэтому в работе оно формализовано как марковский процесс принятия решений и решено методом обучения с подкреплением. Агент, наблюдая локальный сейсмический контекст и историю уже проставленных пиков, на каждом шаге выбирает смещение горизонта на соседней трассе, а функция награды кодирует геофизические критерии: сходство волновой формы с опорным отражением по нормированной взаимной корреляции, фазовую согласованность, гладкость и ослабление штрафа за негладкость в зонах разрывных нарушений. Метод реализован в виде двухэтапной схемы: на первом этапе агент выполняет корреляцию по системе опорных сечений с задаваемым шагом, формируя сеть опорных точек горизонта, на втором – уплотняет результат до сплошной поверхности по всему объёму. Агент обучен в синтетической среде: сначала имитацией известных эталонных траекторий, затем дообучением с подкреплением; на вход подаётся разметка на одном или двух пересекающихся сечениях, а в сложных зонах вводится доразметка. Апробация на ачимовских отложениях одного из месторождений севера Западной Сибири показала согласованность с ручной корреляцией в пределах 10 мс на выдержанных интервалах. Обсуждаются ограничения и направления развития.</p></abstract><trans-abstract xml:lang="en"><p>Structural correlation of reflection horizons remains one of the most labour-intensive operations in 3D seismic interpretation, particularly within the clinoform Neocomian sections of West Siberia, where target reflections show variable dynamics, pinch-outs and are complicated by faulting. Because horizon tracking is inherently sequential, we formulate it as a Markov decision process and solve it with reinforcement learning. Observing a local seismic context and the history of previously picked samples, an agent chooses, at each step, the vertical shift of the horizon on the adjacent trace; the reward function encodes geophysical criteria – waveform similarity to the reference reflection, phase consistency, lateral smoothness and fault tolerance. The method is implemented as a two-stage scheme: a policy first correlates the horizon over a grid of reference sections with a user-defined spacing, building a reliable network of anchors, and then densifies the result into a continuous surface across the whole volume. The agent is trained in a synthetic environment produced by forward full-wavefield modelling, with imitation pretraining on reference horizon trajectories; one or two intersecting reference sections suffice as input, and additional interpretation is introduced in complex zones. Tested on Achimov deposits of a field in Northern West Siberia, the approach agrees with manual correlation within 10 ms over conformable intervals. Limitations and directions for development are discussed.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>отражающий горизонт</kwd><kwd>сейсмическая корреляция</kwd><kwd>обучение с подкреплением</kwd><kwd>марковский процесс принятия решений</kwd><kwd>синтетические данные</kwd><kwd>клиноформа</kwd><kwd>ачимовская толща</kwd><kwd>Западная Сибирь</kwd></kwd-group><kwd-group xml:lang="en"><kwd>reflection horizon</kwd><kwd>seismic correlation</kwd><kwd>reinforcement learning</kwd><kwd>Markov decision process</kwd><kwd>synthetic data</kwd><kwd>clinoform</kwd><kwd>Achimov formation</kwd><kwd>West Siberia</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Наумов А.Л. (1977). К методике реконструкции рельефа дна Западно-Сибирского раннемелового бассейна. Геология и геофизика, 18(10), с. 38–47.</mixed-citation><mixed-citation xml:lang="en">Abubakar A., Di H., Li Z., Maniar H., Zhao T. (2024). An artificial intelligence workflow for horizon volume generation from 3D seismic data. The Leading Edge, 43(4), pp. 235–243. https://doi.org/10.1190/tle43040235.1</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Нежданов А.А., Пономарёв В.А., Туренков Н.А., Горбунов С.А. (2000). Геология и нефтегазоносность ачимовской толщи Западной Сибири. М.: Изд-во Академии горных наук, 247 с.</mixed-citation><mixed-citation xml:lang="en">Luo Y., Zhang G., Zhang J., Li Y., Lin Y., Li B., Liang C., Li L. (2023). Sequence-constrained multitask horizon tracking. Geophysics, 88(2), pp. IM15–IM27.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Abubakar A., Di H., Li Z., Maniar H., Zhao T. (2024). An artificial intelligence workflow for horizon volume generation from 3D seismic data. The Leading Edge, 43(4), pp. 235–243. https://doi.org/10.1190/tle43040235.1</mixed-citation><mixed-citation xml:lang="en">Mattos A.B., Civitarese D., Szwarcman D., Oliveira M., Zaytsev S., Semin D.G., Oliveira D.A.B. (2021). Enabling robust horizon picking from small training sets. IEEE Transactions on Geoscience and Remote Sensing, 59(6), pp. 5317–5324. https://doi.org/10.1109/TGRS.2020.3010124</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Luo Y., Zhang G., Zhang J., Li Y., Lin Y., Li B., Liang C., Li L. (2023). Sequence-constrained multitask horizon tracking. Geophysics, 88(2), pp. IM15–IM27.</mixed-citation><mixed-citation xml:lang="en">Mnih V., Kavukcuoglu K., Silver D., Rusu A.A., Veness J., Bellemare M.G., Graves A., Riedmiller M., Fidjeland A.K., Ostrovski G., Petersen S., Beattie C., Sadik A., Antonoglou I., King H., Kumaran D., Wierstra D., Legg S., Hassabis D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), pp. 529–533. https://doi.org/10.1038/nature14236</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Mattos A.B., Civitarese D., Szwarcman D., Oliveira M., Zaytsev S., Semin D.G., Oliveira D.A.B. (2021). Enabling robust horizon picking from small training sets. IEEE Transactions on Geoscience and Remote Sensing, 59(6), pp. 5317–5324. https://doi.org/10.1109/TGRS.2020.3010124</mixed-citation><mixed-citation xml:lang="en">Naumov A.L. (1977). On the methodology for reconstructing the bottom relief of the West Siberian Early Cretaceous basin. Russian Geology and Geophysics, 18(10), pp. 38–47. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Mnih V., Kavukcuoglu K., Silver D., Rusu A.A., Veness J., Bellemare M.G., Graves A., Riedmiller M., Fidjeland A.K., Ostrovski G., Petersen S., Beattie C., Sadik A., Antonoglou I., King H., Kumaran D., Wierstra D., Legg S., Hassabis D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), pp. 529–533. https://doi.org/10.1038/nature14236</mixed-citation><mixed-citation xml:lang="en">Nezhdanov A.A., Ponomarev V.A., Turenkov N.A., Gorbunov S.A. (2000). Geology and petroleum potential of the Achimov strata of West Siberia. Moscow: Academy of Mining Sciences Publ., 247 p. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Ronneberger O., Fischer P., Brox T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, 9351, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28</mixed-citation><mixed-citation xml:lang="en">Ronneberger O., Fischer P., Brox T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, 9351, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Schulman J., Wolski F., Dhariwal P., Radford A., Klimov O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. https://doi.org/10.48550/arXiv.1707.06347</mixed-citation><mixed-citation xml:lang="en">Schulman J., Wolski F., Dhariwal P., Radford A., Klimov O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. https://doi.org/10.48550/arXiv.1707.06347</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Sheng S. (2023). Automatic horizon picking using multiple seismic attributes and Markov decision process. Remote Sensing, 15(3), 552. https://doi.org/10.3390/rs15030552</mixed-citation><mixed-citation xml:lang="en">Sheng S. (2023). Automatic horizon picking using multiple seismic attributes and Markov decision process. Remote Sensing, 15(3), 552. https:// doi.org/10.3390/rs15030552 Stark T.J. (2004). Relative geologic time (age) volumes – relating every seismic sample to a geologically reasonable horizon. The Leading Edge, 23(9), pp. 928–932. https://doi.org/10.1190/1.1803499</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Stark T.J. (2004). Relative geologic time (age) volumes – relating every seismic sample to a geologically reasonable horizon. The Leading Edge, 23(9), pp. 928–932. https://doi.org/10.1190/1.1803499</mixed-citation><mixed-citation xml:lang="en">Su M., Qian F., Cui S., Yuan C., Cui X. (2023). Research on a 3D seismic horizon automatic-tracking method based on corrugated global diffusion. Applied Sciences, 13(10), 6155. https://doi.org/10.3390/app13106155</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Su M., Qian F., Cui S., Yuan C., Cui X. (2023). Research on a 3D seismic horizon automatic-tracking method based on corrugated global diffusion. Applied Sciences, 13(10), 6155. https://doi.org/10.3390/app13106155</mixed-citation><mixed-citation xml:lang="en">Sutton R.S., Barto A.G. (2018). Reinforcement learning: an introduction. 2nd ed. Cambridge, MA: MIT Press, 552 p.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Sutton R.S., Barto A.G. (2018). Reinforcement learning: an introduction. 2nd ed. Cambridge, MA: MIT Press, 552 p.</mixed-citation><mixed-citation xml:lang="en">Tschannen V., Delescluse M., Ettrich N., Keuper J. (2020). Extracting horizon surfaces from 3D seismic data using deep learning. Geophysics, 85(3), pp. N17–N26. https://doi.org/10.1190/geo2019-0569.1</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Tschannen V., Delescluse M., Ettrich N., Keuper J. (2020). Extracting horizon surfaces from 3D seismic data using deep learning. Geophysics, 85(3), pp. N17–N26. https://doi.org/10.1190/geo2019-0569.1</mixed-citation><mixed-citation xml:lang="en">Wu H., Zhang B., Lin T., Cao D., Lou Y. (2019). Semiautomated seismic horizon interpretation using the encoder–decoder convolutional neural network. Geophysics, 84(5), pp. B403–B417. https://doi.org/10.1190/geo2018-0672.1</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Wu H., Zhang B., Lin T., Cao D., Lou Y. (2019). Semiautomated seismic horizon interpretation using the encoder–decoder convolutional neural network. Geophysics, 84(5), pp. B403–B417. https://doi.org/10.1190/geo2018-0672.1</mixed-citation><mixed-citation xml:lang="en">Wu X., Hale D. (2015). Horizon volumes with interpreted constraints. Geophysics, 80(2), pp. IM21–IM33. https://doi.org/10.1190/geo2014-0212.1</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Wu X., Hale D. (2015). Horizon volumes with interpreted constraints. Geophysics, 80(2), pp. IM21–IM33. https://doi.org/10.1190/geo2014-0212.1</mixed-citation><mixed-citation xml:lang="en">Yang L., Sun S.Z. (2020). Seismic horizon tracking using a deep convolutional neural network. Journal of Petroleum Science and Engineering, 187, 106709. https://doi.org/10.1016/j.petrol.2019.106709</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Yang L., Sun S.Z. (2020). Seismic horizon tracking using a deep convolutional neural network. Journal of Petroleum Science and Engineering, 187, 106709. https://doi.org/10.1016/j.petrol.2019.106709</mixed-citation><mixed-citation xml:lang="en">Yang L., Sun S.Z. (2020). Seismic horizon tracking using a deep convolutional neural network. Journal of Petroleum Science and Engineering, 187, 106709. https://doi.org/10.1016/j.petrol.2019.106709</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>
