Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network

Тучинская Валерия Игоревна; Башмачников Игорь Львович; Захваткина Наталья Юрьевна; Козлов Игорь Евгеньевич; Яковлева Диана Андреевна

doi:10.2205/2026es001084

ВАК 1.6.17 УДК 551.465.153 ГРНТИ 37.25 ОКСО 05.03.04 ББК 26 ТБК 6345 BISAC SCI052000 ВАК 1.6 УДК 55 УДК 550.34 УДК 550.383 ГРНТИ 37.01 ГРНТИ 37.15 ГРНТИ 37.31 ГРНТИ 38.01 ГРНТИ 36.00 ГРНТИ 37.00 ГРНТИ 38.00 ГРНТИ 39.00 ГРНТИ 52.00 ОКСО 05.00.00 ТБК 63 BISAC SCI

Ещё 23 Свернуть

AUTOMATIC IDENTIFICATION OF OCEAN EDDIES IN SAR USING U-NET CONVOLUTIONAL NEURAL NETWORK Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network

АА Аа

Опубликовано в Russian Journal of Earth Sciences · Том 26, Номер 1 · Номер статьи: ES1006 · Рубрика: ОРИГИНАЛЬНЫЕ СТАТЬИ

DOI: https://doi.org/10.2205/2026es001084 · EDN: ZFIMQY

Получено: 27.05.2025 Одобрено: 10.11.2025 Опубликовано: 10.03.2026 Язык публикаций: ENG

Авторы

ТУ

Тучинская Валерия Игоревна

БА

Башмачников Игорь Львович

ORCID Scopus ResearcherID SPIN

ЗА

Захваткина Наталья Юрьевна

КО

Козлов Игорь Евгеньевич

ORCID

и др.

ЯК

Яковлева Диана Андреевна

ORCID

ТУ

Тучинская Валерия Игоревна

Ученая степень: адъюнкт географических наук

Санкт-Петербургский государственный университет Санкт-Петербург

БА

Башмачников Игорь Львович

Ученая степень: доктор географических наук

Санкт-Петербургский государственный университет Санкт-Петербург

Нансен-центр Россия

Морской гидрофизический институт Российской академии наук Севастополь

ORCID Scopus ResearcherID SPIN

ЗА

Захваткина Наталья Юрьевна

Ученая степень: кандидат физико-математических наук

Нансен-центр Россия

Арктический и антарктический научно-исследовательский институт Россия

КО

Козлов Игорь Евгеньевич

Морской гидрофизический институт Российской академии наук Севастополь

ORCID

ЯК

Яковлева Диана Андреевна

Ученая степень: кандидат географических наук

Нансен-центр Россия

ORCID

АННОТАЦИЯ

The effect of mesoscale and submesoscale eddies on regional heat and freshwater transport, sea-ice dynamics, and bioproductivity in polar and subpolar regions is largely unknown. The promising massive investigation of relatively small polar and subpolar eddies with Synthetic Aperture Radar (SAR) images requires robust automatic algorithms for their identification. Following recent advances in such algorithms for Sentinel-1 data, in this study describes an algorithm for identifying mesoscale and submesoscale eddies in earlier Envisat Wide-Swath SAR images using convolutional neural network based on U-Net architecture. The model was trained on 520 fragments of SAR images 512 × 512 pixels each, collected in the Greenland, Irminger and Labrador Seas. The resulting accuracy of eddy detection was 0.89. An improvement in the segmentation accuracy compared to previous studies was a result of the applied annotation methods, based on the analysis of typical texture patterns and morphological characteristics of ocean eddies in SAR. The developed algorithm showed its potential in identification of eddies not only in the Marginal Ice Zone, but also in the open water.

КЛЮЧЕВЫЕ СЛОВА

automatic eddy detection, Envisat SAR images, U-Net convolutional neural network

Финансирование

Development of AI-based automated eddy detection algorithm was supported by Russian Science Foundation grant 25-17-00309, https://rscf.ru/project/25-1 7-00309/. Analysis and manual identification of eddies in historical SAR data was done within state task FNNN-2024-0017

Текст

Текст (PDF)

Читать Скачать

1. Aguedjou H. M. A., Chaigneau A., Dadou I., et al. Imprint of mesoscale eddies on air-sea interaction in the tropical Atlantic Ocean // Remote Sensing. — 2023. — Vol. 15, no. 12. — P. 3087. — https://doi.org/10.3390/rs15123087.

2. Atadzhanova O. A., Zimin A. V., Romanenkov D. A., et al. Satellite radar observations of small eddies in the White, Barents and Kara Seas // Physical Oceanography. — 2017. — No. 2. — P. 75–83. — https://doi.org/10.22449/1573-160x-2017-2-75-83.

3. Barbero L., González-Dávila M., Santana-Casiano J. M., et al. Variability of the water mass transports and fluxes in the eastern North Atlantic during 2001 // Journal of Geophysical Research: Oceans. — 2010. — Vol. 115, no. C3. — https://doi.org/10.1029/2008jc005212.

4. Bashmachnikov I., Neves F., Calheiros T., et al. Properties and pathways of Mediterranean water eddies in the Atlantic // Progress in Oceanography. — 2015. — Vol. 137. — P. 149–172. — https://doi.org/10.1016/j.pocean.2015.06.001.

5. Bashmachnikov I. L., Kozlov I. E., Petrenko L. A., et al. Eddies in the North Greenland Sea and Fram Strait from satellite altimetry, SAR and high-resolution model data // Journal of Geophysical Research: Oceans. — 2020. — Vol. 125, no. 7. — e2019JC015832. — https://doi.org/10.1029/2019jc015832.

6. Bashmachnikov I. L., Raj R. P., Golubkin P., et al. Heat transport by mesoscale eddies in the Norwegian and Greenland seas // Journal of Geophysical Research: Oceans. — 2023. — Vol. 128, no. 2. — e2022JC018987. — https://doi.org/10.1029/2022jc018987.

7. Bower A. S., Le Cann B., Rossby T., et al. Directly measured mid-depth circulation in the northeastern North Atlantic Ocean // Nature. — 2002. — Vol. 419, no. 6907. — P. 603–607. — https://doi.org/10.1038/nature01078.

8. Cassianides A., Lique C. and Korosov A. Ocean eddy signature on SAR-derived sea ice drift and vorticity // Geophysical Research Letters. — 2021. — Vol. 48, no. 6. — e2020GL092066. — https://doi.org/10.1029/2020gl092066.

9. Chelton D. B., Schlax M. G. and Samelson R. M. Global observations of nonlinear mesoscale eddies // Progress in Oceanography. — 2011. — Vol. 91, no. 2. — P. 167–216. — https://doi.org/10.1016/j.pocean.2011.01.002.

10. Gaube P., Chelton D. B., Strutton P. G., et al. Satellite observations of chlorophyll, phytoplankton biomass, and Ekman pumping in nonlinear mesoscale eddies // Journal of Geophysical Research: Oceans. — 2013. — Vol. 118, no. 12. — P. 6349–6370. — https://doi.org/10.1002/2013jc009027.

11. Ginzburg A. I., Krek E. V., Kostianoy A. G., et al. Evolution of mesoscale anticyclonic vortex and vortex dipoles/multipoles on its base in the south-eastern Baltic (satellite information: May-July 2015) // Journal of Oceanological Research. — 2017. — Vol. 45, no. 1. — P. 10–22. — https://doi.org/10.29006/1564-2291.jor-2017.45(1).3. — (In Russian).

12. Golivets S. V. and Koshlyakov M. N. Cyclonic eddies at the Subantarctic front and formation of the Antarctic intermediate water // Oceanology. — 2003. — Vol. 43, no. 3. — P. 305–317. — EDN: https://elibrary.ru/LHULBT.

13. Hirschi J. J.-M., Barnier B., Böning C., et al. The Atlantic meridional overturning circulation in high-resolution models // Journal of Geophysical Research: Oceans. — 2020. — Vol. 125, no. 4. — e2019JC015522. — https://doi.org/10.1029/2019jc015522.

14. Johannessen J. A., Kudryavtsev V., Akimov D., et al. On radar imaging of current features: 2. Mesoscale eddy and current front detection // Journal of Geophysical Research: Oceans. — 2005. — Vol. 110, no. C7. — https://doi.org/10.1029/2004jc002802.

15. Kalinin N. A. and Tolmacheva N. I. Space research methods in meteorology. — Perm : Perm State University, 2005. — 348 p. — EDN: https://elibrary.ru/QKFKIZ ; (in Russian).

16. Karimova S. S. Spiral eddies in the Baltic, Black and Caspian seas as seen by satellite radar data // Advances in Space Research. — 2012. — Vol. 50, no. 8. — P. 1107–1124. — https://doi.org/10.1016/j.asr.2011.10.027.

17. Khachatrian E., Sandalyuk N. and Lozou P. Eddy detection in the marginal ice zone with Sentinel-1 data using YOLOv5 // Remote Sensing. — 2023. — Vol. 15, no. 9. — P. 2244. — https://doi.org/10.3390/rs15092244.

18. Kozlov I. E., Artamonova A. V., Manucharyan G. E., et al. Eddies in the Western Arctic Ocean from spaceborne SAR observations over open ocean and marginal ice zones // Journal of Geophysical Research: Oceans. — 2019. — Vol. 124, no. 9. — P. 6601–6616. — https://doi.org/10.1029/2019jc015113.

19. Kozlov I. E., Plotnikov E. V. and Manucharyan G. E. Brief Communication: Mesoscale and submesoscale dynamics of marginal ice zone from sequential SAR observations // The Cryosphere Discussions. — 2020. — P. 1–11. — https://doi.org/10.5194/tc-2020-126.

20. Kudryavtsev V., Akimov D., Johannessen J., et al. On radar imaging of current features: 1. Model and comparison with observations // Journal of Geophysical Research: Oceans. — 2005. — Vol. 110, no. C7. — https://doi.org/10.1029/2004jc002505.

21. Lavrova O. Yu., Kostianoy A. G., Lebedev S. A., et al. Complex satellite monitoring of the Russian seas. — Moscow : Space Research Institute of RAS, 2011. — 470 p. — (In Russian).

22. Luo D. and Lu Y. The influence of negative viscosity on wind-driven, barotropic ocean circulation in a subtropical basin // Journal of Physical Oceanography. — 2000. — Vol. 30, no. 5. — P. 916–932. — https://doi.org/10.1175/1520-0485(2000)030<0916:tionvo>2.0.co;2.

23. Meneghello G., Marshall J., Cole S. T., et al. Observational inferences of lateral eddy diffusivity in the halocline of the Beaufort Gyre // Geophysical Research Letters. — 2017. — Vol. 44, no. 24. — P. 12331–12338. — https://doi.org/10.1002/2017gl075126.

24. Morozov E. A. and Kozlov I. E. Eddies in the Arctic Ocean revealed from MODIS optical imagery // Remote Sensing. — 2023. — Vol. 15, no. 6. — P. 1608. — https://doi.org/10.3390/rs15061608.

25. Nurser A. J. and Bacon S. The Rossby radius in the Arctic Ocean // Ocean Science. — 2014. — Vol. 10, no. 6. — P. 967– 975. — https://doi.org/10.5194/os-10-967-2014.

26. Raj R. P. and Halo I. Monitoring the mesoscale eddies of the Lofoten Basin: importance, progress, and challenges // International Journal of Remote Sensing. — 2016. — Vol. 37, no. 16. — P. 3712–3728. — https://doi.org/10.1080/01431161.2016.1201234.

27. Ronneberger O., Fischer P. and Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation // Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015. — Springer International Publishing, 2015. — P. 234–241. — https://doi.org/10.1007/978-3-319-24574-4_28.

28. Sea Ice in the Arctic: Past, Present and Future / ed. by O. M. Johannessen, L. P. Bobylev, E. V. Shalina, et al. — Springer International Publishing, 2020. — https://doi.org/10.1007/978-3-030-21301-5.

29. Siegelman L., Klein P., Riviére P., et al. Enhanced upward heat transport at deep submesoscale ocean fronts // Nature Geoscience. — 2020. — Vol. 13, no. 1. — P. 50–55. — https://doi.org/10.1038/s41561-019-0489-1.

30. Spreen G., Kaleschke L. and Heygster G. Sea ice remote sensing using AMSR-E 89-GHz channels // Journal of Geophysical Research: Oceans. — 2008. — Vol. 113, no. C2. — https://doi.org/10.1029/2005jc003384.

31. Suzuki S. and Abe K. Topological structural analysis of digitized binary images by border following // Computer Vision, Graphics, and Image Processing. — 1985. — Vol. 30, no. 1. — P. 32–46. — https://doi.org/10.1016/0734-189x(85)90016-7.

32. Wang Y., Yang M. and Chong J. Simulation and Analysis of SAR Images of Oceanic Shear-Wave-Generated Eddies // Sensors. — 2019. — Vol. 19, no. 7. — P. 1529. — https://doi.org/10.3390/s19071529.

33. Wu J., Zheng Y., Wang T., et al. Oriented ice eddy detection network based on the Sentinel-1 dual-polarization data // Frontiers in Marine Science. — 2025. — Vol. 11. — https://doi.org/10.3389/fmars.2024.1480796.

34. Wunsch C. and Ferrari R. Vertical mixing, energy, and the general circulation of the oceans // Annual Review of Fluid Mechanics. — 2004. — Vol. 36, no. 1. — P. 281–314. — https://doi.org/10.1146/annurev.fluid.36.050802.122121.

35. Xia L., Chen G., Chen X., et al. Submesoscale oceanic eddy detection in SAR images using context and edge association network // Frontiers in Marine Science. — 2022. — Vol. 9. — https://doi.org/10.3389/fmars.2022.1023624.

36. Xu M., Li H., Yun Y., et al. End-to-end pixel-wisely detection of oceanic eddy on SAR images with stacked attention network // IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. — 2023. — Vol. 16. — P. 9711–9724. — https://doi.org/10.1109/jstars.2023.3322404.

37. Zi N., Li X. M., Gade M., et al. Ocean eddy detection based on YOLO deep learning algorithm by synthetic aperture radar data // Remote Sensing of Environment. — 2024. — Vol. 307. — P. 114139. — https://doi.org/10.1016/j.rse.2024.114139.

Контент доступен под лицензией Creative Commons «С указанием авторства версии 4.0 Международная»

PDF Текст JATS XML

Главный редактор

Гвишиани Алексей Джерменович

rjes@wdcb.ru

Заместитель главного редактора

Дзебоев Борис Аркадьевич

rjes@wdcb.ru

Ведущий редактор

Кедров Эрнест Олегович

ernest.kedrov@ya.ru

Ответственный секретарь

Карева Наталья Александровна

rjes@wdcb.ru

915

загрузок

Контент доступен под лицензией Creative Commons «С указанием авторства версии 4.0 Международная» Creative Commons

ГОСТ

Тучинская В. И., Башмачников И. Л., Захваткина Н. Ю., Козлов И. Е., Яковлева Д. А. Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network // Russian Journal of Earth Sciences. 2025. №. 1. ES1006. DOI: https://doi.org/10.2205/2026es001084. EDN: ZFIMQY. (дата обращения: 23.09.2026).

MLA

Тучинская Валерия Игоревна, Башмачников И. Л., Захваткина Н. Ю., Козлов И. Е., Яковлева Д. А.. "Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network." Russian Journal of Earth Sciences 26.1 (2025): ES1006. DOI: https://doi.org/10.2205/2026es001084. EDN: ZFIMQY.

APA

Тучинская В. И., Башмачников И. Л., Захваткина Н. Ю., Козлов И. Е., Яковлева Д. А. (2025). Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network. Russian Journal of Earth Sciences, 26(1), ES1006. https://doi.org/10.2205/2026es001084 EDN: ZFIMQY.

Chicago

Тучинская Валерия Игоревна, Башмачников И. Л., Захваткина Н. Ю., Козлов И. Е., Яковлева Д. А.. "Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network." Russian Journal of Earth Sciences 26, no. 1 (2025): ES1006. https://doi.org/10.2205/2026es001084. EDN: ZFIMQY.

WIKI

{{cite journal | author = Тучинская В. И., Башмачников И. Л., Захваткина Н. Ю., Козлов И. Е., Яковлева Д. А. | title = Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network | journal = Russian Journal of Earth Sciences | year = 2025 | volume = 26 | issue = 1 | pages = ES1006 | doi = 10.2205/2026es001084 }} EDN: ZFIMQY

Скопировать

Экспорт: BibTeX EndNote RefMan RusMARC

AUTOMATIC IDENTIFICATION OF OCEAN EDDIES IN SAR USING U-NET CONVOLUTIONAL NEURAL NETWORK Automatic Identification of Ocean Eddies in SAR Using U-Net Convolutional Neural Network

Подтверждение