ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa


Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2022, Vol. 19, No. 6, pp. 18-28

Classification of SAR images of Arctic ice fields based on the use of multifractal features

D.V. Uchaev 1 , Dm.V. Uchaev 1 , V.A. Malinnikov 1 
1 Moscow State University of Geodesy and Cartography, Moscow, Russia
Accepted: 22.11.2022
DOI: 10.21046/2070-7401-2022-19-6-18-28
The article presents a method for multifractal classification of radar images of Arctic ice fields obtained using synthetic aperture radars (SAR). This method is aimed at distinguishing areas of ice fields in SAR images, characterized by different values of sea ice concentration. The method is based on the fact that Arctic ice cover has a complex hierarchical (multifractal) structure, which can vary significantly depending on the regional and seasonal features of the ice regime, as well as the dynamics of atmospheric and oceanic processes. The main steps of the proposed method for classifying SAR images of ice fields are as follows: preliminary processing of SAR images, forming a multiband image of multifractal features, classification of the formed multifractal feature vectors using a classifier based on random multigraphs. Experimental verification of the proposed method for classifying SAR images was carried out on more than 50 regions of SAR images of ice-covered sea areas of the Arctic, obtained from Sentinel-1 in the summer season. The verification results show that the proposed method for multifractal classification of SAR images allows using relatively small training samples and at the same time achieves sufficiently high values of overall and average classification accuracy.
Keywords: Arctic seas, ice cover, sea ice concentration, SAR image, multifractal classification
Full text


  1. Zakhvatkina N. Yu., Bychkova I. A., Bayesian classification of the ice cover of the Arctic seas, Izvestiya, Atmospheric and Oceanic Physics, 2015, Vol. 51, No. 9, pp. 883–888, DOI: 10.1134/S0001433815090212.
  2. Zakhvatkina N. Yu., Alexandrov V. Yu., Korosov A. A., Johannessen O. M., Sea ice classification using ENVISAT ASAR images, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2009, Vol. 1, No. 6, pp. 373–379 (in Russian).
  3. Kobernichenko V. G., Ivanov V. G., Sosnovsky A. V., Obrabotka radiolokatsionnykh dannykh distantsionnogo zondirovaniya Zemli: laboratornyi praktikum (Processing of Earth remote sensing radar data: laboratory workshop), Ekaterinburg: Ural University Press, 2013, 64 p. (in Russian).
  4. Malinnikov V. A., Savinykh V. P., Uchaev Dm. V., Uchaev D. V., Multifractal assessment of the ice situation based on space imagery, Ideas and Innovations, 2018, Vol. 6, No. 3, pp. 69–74 (in Russian).
  5. Mironov E. U., Klyachkin S. V., Smolyanitsky V. M., Yulin A. V., Frolov S. V., Current state and perspectives of ice cover studies in the Russian Arctic seas, Russian Arctic, 2020, No. 10, pp. 13–29 (in Russian), DOI: 10.24411/2658-4255-2020-12102.
  6. Mitnik L. M., Khazanova E. S., Ice cover dynamics in the East Siberian and Laptev Seas at the second half of October 2014 from remote sensing data, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2015, Vol. 12, No. 2, pp. 100–113 (in Russian).
  7. Nikolsky D. B., Comparative study of modern SAR systems, Geomatika, 2008, No. 1, pp. 11–17 (in Russian).
  8. Repina I. A., Ivanov V. V., Remote sensing in ice sea dynamic and modern Arctic, Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2012, Vol. 9, No. 5, pp. 89–103 (in Russian).
  9. Smirnov V. N., The features of dynamics and deformation mechanics of the Arctic basin ice, Arctic and Antarctic Research, 2007, No. 1(75), pp. 73–84 (in Russian).
  10. Congalton R. G., Green K., Assessing the accuracy of remotely sensed data: principles and practices, 2nd ed., Boca Raton: CRC Press, 2008, 210 p.
  11. Dalla Mura M., Benediktsson J. A., Waske B., Bruzzone L., Extended profiles with morphological attribute filters for the analysis of hyperspectral data, Intern. J. Remote Sensing, 2010, Vol. 31, No. 22, pp. 5975–5991, DOI: 10.1080/01431161.2010.512425.
  12. Han Y., Liu Y., Hong Z., Zhang Y., Yang S., Wang J., Sea ice image classification based on heterogeneous data fusion and deep learning, Remote Sensing, 2021, Vol. 13, No. 4, Art. No. 592, DOI: 10.3390/rs13040592.
  13. Jaffard S., Multifractal formalism for functions part I: results valid for all functions, SIAM J. Mathematical Analysis, 1997, Vol. 28, No. 4, pp. 944–998, DOI: 10.1137/S0036141095282991.
  14. Khaleghian S., Ullah H., Kræmer T., Hughes N., Eltoft T., Marinoni A., Sea ice classification of SAR imagery based on convolution neural networks, Remote Sensing, 2021, Vol. 13, No. 9, Art. No. 1734, DOI: 10.3390/rs13091734.
  15. Lee G., Refined filtering of image noise using local statistics, Computer Graph Image Processing, 1981, Vol. 15, No. 4, pp. 380–389, DOI: 10.1016/S0146-664X(81)80018-4.
  16. Lee J. S., Jurkevich L., Dewaele P., Wambacq P., Oosterlinck A., Speckle filtering of synthetic aperture radar images: a review, Remote Sensing Reviews, 1994, Vol. 8, No. 4, pp. 313–340, DOI: 10.1080/02757259409532206.
  17. Li W., Chen C., Su H., Du Q., Local binary patterns and extreme learning machine for hyperspectral imagery classification, IEEE Trans. Geoscience and Remote Sensing, 2015, Vol. 53, No. 7, pp. 3681–3693, DOI: 10.1109/TGRS.2014.2381602.
  18. Mironov Ye. U., Frolov I. Ye., Spichkin V. A., Karklin V. P., Karelin I. D., Gorbunov Y. A., Losev S. M., Sea ice conditions observed from satellite remote-sensing data, In: Remote Sensing of Sea Ice in the Northern Sea Route: Studies and Applications, Berlin; Heidelberg: Springer-Verlag, 2007, pp. 253–322, DOI: 10.1007/978-3-540-48840-8_5.
  19. Mirzapour F., Ghassemian H., Moment-based feature extraction from high spatial resolution hyperspectral images, Intern. J. Remote Sensing, 2016, Vol. 37, No. 6, pp. 1349–1361, DOI: 10.1080/2150704X.2016.1151568.
  20. Park J.-W., Korosov A. A., Babiker M., Won J.-S., Hansen M. W., Kim H.-C., Classification of sea ice types in Sentinel-1 synthetic aperture radar images, The Cryosphere, 2020, Vol. 14, No. 8, pp. 2629–2645, DOI: 10.5194/tc-14-2629-2020.
  21. Uchaev Dm. V., Uchaev D. V., Malinnikov V. A. (2020a), Chebyshev multifractal signatures and their use in multifractal interpretation of SAR images of ice-covered sea areas, Proc. SPIE, 2020, Vol. 11433, Art. No. 1143307, DOI: 10.1117/12.2559391.
  22. Uchaev Dm. V., Uchaev D. V., Malinnikov V. A. (2020b), Spectral-spatial classification of hyperspectral images based on multifractal features, Proc. SPIE, 2020, Vol. 11533, Art. No. 115330T, DOI: 10.1117/12.2573715.
  23. Uchaev D. V., Uchaev Dm. V., Feature profiles for semisupervised hyperspectral image classification with limited labeled training samples, Proc. SPIE, 2021, Vol. 11862, pp. 235–243, DOI: 10.1117/12.2599182.
  24. Uchaev Dm. V., Uchaev D. V., Malinnikov V. A. (2021a), Hyperspectral image classification by Chebyshev moment multifractal profiles, In: Recent Progress in Moments and Moment Invariants, Papakostas G. A. (ed.), Thrace: Science Gate Publ. P. C., 2021, Vol. 7, pp. 75–99, DOI: 10.15579/gcsr.vol7.ch4.
  25. Uchaev Dm. V., Uchaev D. V., Malinnikov V. A., Savinykh V. P. (2021b), Multifractal classification of Sentinel-1 SAR images of ice-covered sea areas, Proc. SPIE, 2021, Vol. 11862, Art. No. 118620S, DOI: 10.1117/12.2599886.
  26. Vihma T., Effects of Arctic sea ice decline on weather and climate: a review, Surveys in Geophysics, 2014, Vol. 35, No. 5, pp. 1175–1214, DOI: 10.1007/s10712-014-9284-0.
  27. WMO sea-ice nomenclature, WMO-No. 259, 2014, Vol. I, II and III.
  28. Zakhvatkina N., Smirnov V., Bychkova I., Satellite SAR data-based sea ice classification: an overview, Geosciences, 2019, Vol. 9, No. 4, Art. No. 152, DOI: 10.3390/geosciences9040152.