The article presents an algorithm for detecting breaks and crevices in the Arctic sea ice cover using radar data from the Sentinel-1 satellite. The algorithm uses polarimetric characteristics of the signal of the sea surface. A method for classifying images to identify cracks and crevices in sea ice using the difference in polarizations and using the convolutional neural network U-Net is proposed. Examples of the algorithm’s testing in the Arctic seas of the Russian Federation are presented. As a result of testing the neural network, the obtained accuracy reached more than 80 % in the absence of clouds and initial types of ice in the stream.

Evgeny P. Istomin
Doctor of Technical Sciences, Professor
Director of the Institute of Information Systems and Geotechnologies
Russian State Hydrometeorological University
79, Voronezhskaya Str., St. Petersburg, 192007, Russia
e-mail: biom220@bk.ru
ORCID ID: 0000-0001-6247-4373
Scopus ID: 56951051300
SPIN-code: 6404-9070
AuthorID: 333123

Yaroslav A. Petrov
Candidate of Technical Sciences, Associate Professor
Associate Professor of the Department of Applied Informatics
Russian State Hydrometeorological University
79, Voronezhskaya Str., Saint-Petersburg, 192007, Russia
е-mail: yaroslav.petrov025@gmail.com
ORCID ID: 0000-0002-9185-441X
SPIN-code: 4170-3003
AuthorID: 899415

Irma A. Martin
Candidate of Technical Sciences
Associate Professor of the Department of Applied Informatics
Russian State Hydrometeorological University
79, Voronezhskaya Str., St. Petersburg, 192007, Russia
е-mail: irma_martyn@mail.ru
ORCID ID: 0000-0002-4332-7308
Scopus Author ID: 57217862251
SPIN-код: 9386-0716
AuthorID: 1004119

Artem Yu. Sidorenko
Associate Professor of the Department of Applied Informatics
Russian State Hydrometeorological University
79, Voronezhskaya Str., St. Petersburg, 192007, Russia
е-mail: sidorenko.ref@gmail.com
ORCID ID: 0000-0003-4520-5846
SPIN-код: 8137-5756
AuthorID: 1041997

1. Kasatkin A.V. Development of the Northern Sea Route: correlation of environmental and economic interests of the state. Bulletin of the Udmurt University. Series Economics and Law. 2025;35(1):131–139.
2. Sazonov K.E., Luk’yanov S.V., Vladimirova O.M. Osnovy fiziki morskogo l’da [Fundamentals of sea ice physics]. Saint Petersburg : RGGMU, 2023. 148 p.
3. Andreev O.M., Ivanov B.V. Parametrizatsiya radiatsionnykh protsessov v modeli ledyanogo pokrova [Parameterization of radiation processes in the ice cover model]. Meteorologiya i Gidrologiya. 2001;(2):81–88.
4. Istomin E., Petrov Ya., Martyn I., Istomin I. Technique for determining bathymetry from Landsat image data. Determining the depth of the penetration zone. Information and Space. 2024;(2):173–179.
5. Bloshchinskiy V.D., Andreev A.I., Kramareva L.S., Davidenko A.N. Satellite data processing for hydrometeorological research with the use of neural network technologies: the approaches used at Planeta State Research Center on Space Hydrometeorology. Russian Meteorology and Hydrology. 2024;49(4):304–312. DOI: 10.3103/s1068373924040034.
6. Martyn Ch.A., Martyn I.A. Segmentation of satellite images of vegetation based on pattern recognition theory. In: Tsifrovye sistemy i modeli: teoriya i praktika proektirovaniya, razrabotki i primeneniya: materialy natsional’noi (s mezhdunarodnym uchastiem) nauchno-prakticheskoi konferentsii (Kazan’, 10–11 April 2024). Kazan’ : KGEhU, 2024. pp. 926–928.