<?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">vmait</journal-id><journal-title-group><journal-title xml:lang="ru">Computational Mathematics and Information Technologies</journal-title><trans-title-group xml:lang="en"><trans-title>Computational Mathematics and Information Technologies</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">2587-8999</issn><publisher><publisher-name>Донской государственный технический университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.23947/2587-8999-2024-8-4-43-48</article-id><article-id custom-type="elpub" pub-id-type="custom">vmait-177</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>Information Technologies (Информационные технологии)</subject></subj-group></article-categories><title-group><article-title>Идентификация морских разливов нефти  на основе нейросетевых технологий</article-title><trans-title-group xml:lang="en"><trans-title>Identification of Marine Oil Spills Using Neural Network Technologies</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7744-015X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сидорякина</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Sidoryakina</surname><given-names>V. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Валентина Владимировна Сидорякина - кандидат физико-математических наук, доцент кафедры математики и информатики;  доцент кафедры математики и физики</p><p>344003, г. Ростов-на-Дону, пл. Гагарина, 1</p><p>347936, г. Таганрог, ул. Инициативная, 48</p><p> </p></bio><bio xml:lang="en"><p>Valentina V. Sidoryakina - Cand. Sci. (Phys. – math.), Associate Professor at the Department of Mathematics and Computer Science; Associate Professor at the Department of Mathematics and Physics</p><p>1, Gagarin Sq., Rostov-on-Don, 344003 F</p><p>347936,  Taganrog, Initsiativnaya Str., 48</p></bio><email xlink:type="simple">cvv9@mail.ru</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>Соломаха</surname><given-names>Д. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Solomakha</surname><given-names>D. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Денис Анатольевич Соломаха - студент кафедры математики и информатики</p><p>344003, г. Ростов-на-Дону, пл. Гагарина, 1</p></bio><bio xml:lang="en"><p>Denis A. Solomakha - 4th year student at the Department of Mathematics and Computer Science</p><p>1, Gagarin Sq., Rostov-on-Don, 344003</p></bio><email xlink:type="simple">solomakha.05@yandex.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Донской государственный технический университет;  Таганрогский институт имени А.П. Чехова (филиал) Ростовского государственного экономического университета (РИНХ)</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Don State Technical University;  Taganrog Institute named after A.P. Chekhov (branch) of RSUE (RINH)</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Донской государственный технический университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Don State Technical University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>23</day><month>01</month><year>2025</year></pub-date><volume>8</volume><issue>4</issue><fpage>43</fpage><lpage>48</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Сидорякина В.В., Соломаха Д.А., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Сидорякина В.В., Соломаха Д.А.</copyright-holder><copyright-holder xml:lang="en">Sidoryakina V.V., Solomakha D.A.</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.cmit-journal.ru/jour/article/view/177">https://www.cmit-journal.ru/jour/article/view/177</self-uri><abstract><sec><title>Введение</title><p>Введение. Обнаружение разливов нефти является важной задачей в деле мониторинга состояния морской экосистемы, защиты и минимизации последствий аварийных ситуаций. Для оперативной оценки и реагирования на чрезвычайные ситуации необходима разработка быстрых и точных методов обнаружения и картирования разливов нефти в море. Данные аэрофотосъемки с высоким пространственным разрешением предоставляют исследователям возможность удаленного наблюдения за цветностью вод. Улучшению и автоматизации процедур интерпретации и анализа снимков способствуют технологии искусственного интеллекта. Целью настоящей работы является разработка подходов к идентификации разлившейся на водной поверхности нефти с использованием нейросетей и машинного обучения.</p></sec><sec><title>Материалы и методы</title><p>Материалы и методы. Методами компьютерного анализа изображений и машинного обучения созданы алгоритмы, способные автоматически идентифицировать морские разливы нефти. Для задачи сегментации изображений применялась сверточная нейронная сеть U-Net. Для разработки архитектуры нейросети была использована библиотека PyTorch, написанная на языке Python. В качестве оптимизатора нейросети был выбран AdamW. Обучение нейронной сети проводилось с помощью датасета, созданного на основе 8700 изображений.</p></sec><sec><title>Результаты исследования</title><p>Результаты исследования. Оценка производительности обнаружения разлитой нефти на водной поверхности выполнена на основе метрик IoU, Precision, Recall, Accuracy и F1 score. Проведенные расчеты с использованием указанных метрик демонстрируют точность идентификации около 83–88 %, что позволяет сделать вывод об эффективности используемых алгоритмов.</p></sec><sec><title>Обсуждение и заключение</title><p>Обсуждение и заключение. Сверточная сеть U-Net успешно обучена и способна давать высокую точность при обнаружении морских разливов нефти на заданном датасете. Перспективами дальнейших работ авторов является создание алгоритмов с использованием более сложной нейросетевой модели и методов аугментации изображений.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>Introduction</title><p>Introduction. Detecting oil spills is a critical task in monitoring the marine ecosystem, protecting it, and minimizing the consequences of emergency situations. The development of fast and accurate methods for detecting and mapping oil spills at sea is essential for prompt assessment and response to emergencies. High-resolution aerial photography provides researchers with a tool for remote monitoring of water discoloration. Artificial intelligence technologies contribute to improving and automating the interpretation and analysis of such images. This study aims to develop approaches for identifying oil spilled on water surfaces using neural networks and machine learning techniques.</p></sec><sec><title>Materials and Methods</title><p>Materials and Methods. Algorithms capable of automatically identifying marine oil spills were developed using computer image analysis and machine learning methods. The U-Net convolutional neural network was employed for image segmentation tasks. The neural network architecture was designed using the PyTorch library implemented in Python. The AdamW optimizer was chosen for training the network. The neural network was trained on a dataset comprising 8,700 images.</p></sec><sec><title>Results</title><p>Results. The performance of oil spill detection on water surfaces was evaluated using metrics such as IoU, Precision, Recall, Accuracy, and F1 score. Calculations based on these metrics demonstrated identification accuracy of approximately 83–88%, confirming the efficiency of the algorithms used.</p><p>Discussion and Conclusion. The U-Net convolutional network was successfully trained and demonstrated high accuracy in detecting marine oil spills on the given dataset. Future work will focus on developing algorithms using more advanced neural network models and image augmentation methods.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>морские системы</kwd><kwd>обнаружение разлива нефти</kwd><kwd>аэрофотоснимки</kwd><kwd>глубокое обучение</kwd><kwd>сегментация изображений</kwd><kwd>U-Net</kwd><kwd>оптимизатор AdamW</kwd></kwd-group><kwd-group xml:lang="en"><kwd>marine systems</kwd><kwd>oil spill detection</kwd><kwd>aerial photography</kwd><kwd>deep learning</kwd><kwd>image segmentation</kwd><kwd>U-Net</kwd><kwd>AdamW optimizer</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено за счет гранта Российского научного фонда № 23‒21‒00509,  https://rscf.ru/project/23-21-00509</funding-statement><funding-statement xml:lang="en">The study was supported by the Russian Science Foundation grant No. 23‒21‒00509, https://rscf.ru/project/23-21-00509</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">Сидорякина В.В. Математическая модель процесса распространения нефтяных загрязнений в прибрежных морских системах. Computational Mathematics and Information Technologies. 2023;7(4):39–46. https://doi.org/10.23947/2587-8999-2023-7-4-39-46</mixed-citation><mixed-citation xml:lang="en">Sidoryakina V.V. Mathematical model of the process of oil pollution spreading in coastal marine systems. Computational Mathematics and Information Technologies. 2023;7(4):39–46. (In Russ.). https://doi.org/10.23947/2587-8999-2023-7-4-39-46</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Sidoryakina V., Filina A. A set of tools for predictive modeling of the spatial distribution of oil pollution. E3S Web of Conferences. 2024;592:04017. https://doi.org/10.1051/e3sconf/202459204017</mixed-citation><mixed-citation xml:lang="en">Sidoryakina V., Filina A. A set of tools for predictive modeling of the spatial distribution of oil pollution. E3S Web of Conferences. 2024;592:04017. https://doi.org/10.1051/e3sconf/202459204017</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Муратов М.В., Конов Д.С., Петров Д.И., Петров И.Б. Применение сверточных нейронных сетей для поиска и определения физических характеристик неоднородностей в геологической среде по сейсмическим данным. Математические заметки СВФУ. 2023;30(1):101–113. https://doi.org/10.25587/SVFU.2023.87.50.008</mixed-citation><mixed-citation xml:lang="en">Muratov M.V., Konov D.S., Petrov D.I., Petrov I.B. Application of convolutional neural networks for searching and determining physical characteristics of heterogeneities in the geological environment based on seismic data. Mathematical notes of NEFU. 2023;30(1):101–113. (In Russ.). https://doi.org/10.25587/SVFU.2023.87.50.008</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Huang X., Zhang B., Perrie W., Lu Y., Wang C. A novel deep learning method for marine oil spill detection from satellite synthetic aperture radar imagery. Marine Pollution Bulletin. 2022;179:11366. https://doi.org/10.1016/j.marpolbul.2022.113666</mixed-citation><mixed-citation xml:lang="en">Huang X., Zhang B., Perrie W., Lu Y., Wang C. A novel deep learning method for marine oil spill detection from satellite synthetic aperture radar imagery. Marine Pollution Bulletin. 2022;179:11366. https://doi.org/10.1016/j.marpolbul.2022.113666</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Rousso R., Katz N., Sharon G., Glizerin Y., Kosman E., Shuster A. Automatic Recognition of Oil Spills Using Neural Networks and Classic Image Processing. Water. 2022;14:1127. https://doi.org/10.3390/w14071127</mixed-citation><mixed-citation xml:lang="en">Rousso R., Katz N., Sharon G., Glizerin Y., Kosman E., Shuster A. Automatic Recognition of Oil Spills Using Neural Networks and Classic Image Processing. Water. 2022;14:1127. https://doi.org/10.3390/w14071127</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Favorskaya M., Nishchhal N. Verification of Marine Oil Spills Using Aerial Images Based on Deep Learning Methods. Informatics and Automation. 2022; 21(5):937‒962. https://doi.org/10.15622/ia.21.5.4</mixed-citation><mixed-citation xml:lang="en">Favorskaya M., Nishchhal N. Verification of Marine Oil Spills Using Aerial Images Based on Deep Learning Methods. Informatics and Automation. 2022; 21(5):937‒962. https://doi.org/10.15622/ia.21.5.4</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Zeng K., Wang Y. A Deep Convolutional Neural Network for Oil Spill Detection from Spaceborne SAR Images. Remote Sens. 2020;12:1015. https://doi.org/10.3390/rs12061015</mixed-citation><mixed-citation xml:lang="en">Zeng K., Wang Y. A Deep Convolutional Neural Network for Oil Spill Detection from Spaceborne SAR Images. Remote Sens. 2020;12:1015. https://doi.org/10.3390/rs12061015</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Yekeen S.T., Balogun A.L. Automated Marine Oil Spill Detection Using Deep Learning Instance Segmentation Model. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 2020;XLIII-B3-2020:1271–1276. https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-1271-2020</mixed-citation><mixed-citation xml:lang="en">Yekeen S.T., Balogun A.L. Automated Marine Oil Spill Detection Using Deep Learning Instance Segmentation Model. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 2020;XLIII-B3-2020:1271–1276. https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-1271-2020</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Сафин М.А., Бикбулатов Р.И., Пирогова А.М. Повышение эффективности автоматической идентификации разливов нефти с помощью беспилотных летальных аппаратов. Инженерный вестник Дона. 2022;12. URL: ivdon.ru/ru/magazine/archive/n12y2022/8046 (дата обращения: 25.11.2024).</mixed-citation><mixed-citation xml:lang="en">Safin M.A., Bikbulatov R.I., Pirogova A.M. Improving the efficiency of automatic identification of oil spills using unmanned aerial vehicles. Engineering Bulletin of the Don. 2022;12. (in Russ.). URL: ivdon.ru/ru/magazine/archive/n12y2022/8046 (accessed: 25.11.2024).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Sukhinov A., Sidoryakina V., Solomakha D. Identification of plankton populations in the surface waters of the Azov Sea based on neural network structures of various architectures. BIO Web of Conferences. 2024;141:03003. https://doi.org/10.1051/bioconf/202414103003</mixed-citation><mixed-citation xml:lang="en">Sukhinov A., Sidoryakina V., Solomakha D. Identification of plankton populations in the surface waters of the Azov Sea based on neural network structures of various architectures. BIO Web of Conferences. 2024;141:03003. https://doi.org/10.1051/bioconf/202414103003</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Sukhinov A.I., Sidoryakina V.V., Solomakha D.A. Identification of plankton populations on the surface of marine systems based on machine learning methods. Priority areas for the development of science and education in the context of the formation of technological sovereignty: materials of the International scientific and practical conference. Rostovon-Don: DSTU-Print; 2024. P. 272‒277. (In Russ.)</mixed-citation><mixed-citation xml:lang="en">Sukhinov A.I., Sidoryakina V.V., Solomakha D.A. Identification of plankton populations on the surface of marine systems based on machine learning methods. Priority areas for the development of science and education in the context of the formation of technological sovereignty: materials of the International scientific and practical conference. Rostovon-Don: DSTU-Print; 2024. P. 272‒277. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Bui N.A., Oh Y.G., Lee I.P. Oil spill detection and classification through deep learning and tailored data augmentation. International Journal of Applied Earth Observation and Geoinformation. 2024;129:103845. https://doi.org/10.1016/j.jag.2024.103845</mixed-citation><mixed-citation xml:lang="en">Bui N.A., Oh Y.G., Lee I.P. Oil spill detection and classification through deep learning and tailored data augmentation. International Journal of Applied Earth Observation and Geoinformation. 2024;129:103845. https://doi.org/10.1016/j.jag.2024.103845</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>
