Skip to main content
Log in

Improvement of the AI-Based Estimation of Significant Wave Height Based on Preliminary Training on Synthetic X-Band Radar Sea Clutter Images

  • Published:
Moscow University Physics Bulletin Aims and scope


Marine X-band radar is an important navigational tool that records signals reflected from the sea surface. Theoretical studies show that the initial unfiltered signal contains information about the sea surface state, including wind wave parameters. Physical laws describing the intensity of the signal reflected from the rough surface are the basis of the classical approaches for significant wave height (SWH) estimation. Nevertheless, the latest research claims the possibility of SWH approximation using machine learning models. Both classical and AI-based approaches require in situ data collected during expensive sea expeditions or with wave monitoring systems. An alternative to real data is generation of synthetic radar images with certain wind wave parameters. This Fourier-based approach is capable of modelling the sea clutter images for wind waves of any given height. Assuming a fully-developed sea, we generate synthetic images from the Pierson–Moskowitz wave spectrum. After that, we apply an unsupervised learning using synthetic radar images to train the convolutional part of the neural network as the encoding part of the autoencoder. In this study, we demonstrate how the accuracy of SWH estimation based on radar images changes when the neural network is pretrained on synthetic data.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13


  1. K. Höhlein, M. Kern, T. Hewson, and R. Westermann, Meteorol. Appl. 27, e1961 (2020).

  2. S. Gulev, V. Grigorieva, and A. Sterl, Global Atlas of Ocean Waves at the Sea Atmosphere Interaction And Climate Laboratory (2014).

  3. K. Hessner, J. Borge, and K. Reichert, in Proc. 28th Int. Conf. Offshore Mechanics and Arctic Engineering (ASME, 1999), p. 17.

  4. N. Tilinina, D. Ivonin, A. Gavrikov, et al., Preprint ESSD-2021-431 (2021).

  5. N. Tilinina, D. Ivonin, A. Gavrikov, et al., Earth Syst. Sci. Data 14, 3615 (2022).

    Article  ADS  Google Scholar 

  6. R. Vicen-Bueno, C. Lido-Muela, J. Nieto-Borge, EURASIP J. Adv. Signal. Process. 84 (2012).

  7. G. Ludeno and F. Serafino, J. Mar. Sci. Eng. 7, 432 (2019).

    Article  Google Scholar 

  8. G. Mastin, P. Watterberg, and J. Mareda, IEEE Comput. Graphics Appl. 7(3), 16 (1987).

    Article  Google Scholar 

  9. W. Pierson and L. Moskowitz, J. Geophys. Res. 69, 5181 (1964).

    Article  ADS  Google Scholar 

  10. D. Lyzenga and D. Walker, IEEE Geosci. Remote Sens. Lett. 12(12), 2389 (2015).

    Article  ADS  Google Scholar 

  11. D. Hasselmann, M. Dunckel, and J. Ewing, J. Phys. Oceanogr. 10, 1264 (1980).

    Article  ADS  Google Scholar 

  12. J. Nieto Borge, G. Rodriguez, K. Hessner, and P. Gonzales, J. Atmos. Ocean. Technol. 21, 1291 (2004).;2

    Article  ADS  Google Scholar 

  13. V. Rezvov, M. Krinitskiy, and S. Gulev, in The 6th Int. Workshop on Deep Learning in Computational Physics (2022), p. 429.

  14. K. He, X. Zhang, Sh. Ren, and J. Sun, in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, 2016 (IEEE, 2016), pp. 770–778.

  15. D. Misra, ‘‘Mish: A self regularized non-monotonic activation function,’’ arXiv Preprint (2019).

  16. E. Matsuyama, J. Biomed. Sci. Eng. 13, 140 (2020).

    Article  Google Scholar 

  17. M. A. Kramer, AIChE J. 37, 233 (1991).

    Article  ADS  Google Scholar 

  18. T. A. Tani, M. M. A. Shibly, Md. Sh. Hasan, et al., in Deep Learning Applications in Image Analysis, Ed. by S. Roy, C.-H. Hsu, and V. Kagita, Studies in Big Data, Vol. 129 (Springer, Singapore, 2023), pp. 1–26.

  19. W. Shi, J. Caballero, F. Huszár, et al., ‘‘Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network,’’ arXiv Preprint (2016).

  20. Y. Sugawara, S. Shiota, and H. Kiya, APSIPA Trans. Signal Inf. Process. 8, e9 (2019).

  21. P. Bergmann, S. Löwe, M. Fauser, et al., ‘‘Improving unsupervised defect segmentation by applying structural similarity to autoencoders,’’ arXiv Preprint (2018).

  22. D. P. Kingma and J. Ba, ‘‘Adam: A method for stochastic optimization,’’ arXiv Preprint (2015).

Download references


A method for synthesizing sea clutter images has been developed with support from the program FMWE-2022-0002. The development and assessment of the artificial neural network was supported by the Kazan Federal University Strategic Academic Leadership Program (PRIORITY-2030).

Author information

Authors and Affiliations


Corresponding author

Correspondence to V. Yu. Rezvov.

Ethics declarations

The authors of this work declare that they have no conflicts of interest.

Additional information

Publisher’s Note.

Allerton Press remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rezvov, V.Y., Krinitskiy, M.A., Golikov, V.A. et al. Improvement of the AI-Based Estimation of Significant Wave Height Based on Preliminary Training on Synthetic X-Band Radar Sea Clutter Images. Moscow Univ. Phys. 78 (Suppl 1), S188–S201 (2023).

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: