PREDICTION OF ICE CONDITIONS TO SUPPORT ECONOMIC ACTIVITY IN THE RUSSIAN ARCTIC SEAS USING DEEP LEARNING METHODS

The paper presents a technology for predicting ice conditions in the Russian Arctic seas to solve forecasting problems in a grid setting for a given local water area. The technology is based on the application of in-depth training models in the form of convolutional neural networks. It allows solving problems of long-term predicting ice conditions (concentration and thickness) with a given temporal and spatial resolution. Experimental studies to assess the quality of ice concentration forecasting have confirmed the effectiveness of ensemble modelling in comparison with single models, as well as with existing forecasts (SEAS5). The proposed approach surpasses the global forecasting system based on in-depth training IceNet, while having a lower computational complexity.

1. Mironov E. U. et al. The current state and prospects of research on the ice cover of the seas of the Russian Arctic. The Russian Arctic, 2020, no. 3, pp. 13—29. (In Russian).

2. Overview ice maps of the Arctic Ocean. Available at: https://www.aari.ru/data/realtime/ledovye-karty-2. (In Russian)

3. SIGRID-3: A vector archive format for sea ice charts: developed by the International Ice Charting Working Group’s Ad Hoc Format Team for the WMO Global Digital Sea Ice Data Bank Project. Available at: https://repository.oceanbestpractices.org/handle/11329/97.

4. Malyshev N. A., Verzhbitskii V. E., Kolyubakin A. A., Komissarov D. K., Borodulin A. A., Obmetko V. V., Popova A. B., Danilkin S. M., Vasil’eva I. S., Timoshenko T. A., Aleksandrova G. N., Gatovskii Yu. A., Suslova A. A., Nikishin A. M. Technological aspects and experience of stratigraphic drilling in the seas of the Russian Arctic. Geologiya nefti i gaza, 2024, no. 3, pp. 19—30. DOI: 10.47148/0016-7894-2024-3-19-30. (In Russian).

5. Petrov O. V., Ponimaskin A. I., Tokarev M. Yu., Leont’ev D. I., Tolmacheva T. Yu., Razumkova E. S., Shurekova O. V., Stavitskaya V. N., Komissarov D. K., Kolyubakin A. A., Verzhbitskii V. E. et al. First results of stratigraphic drilling in the East Siberian Sea focused on the geological studies of the suture zone of the continental shelf’s marginal structures and deep-water areas of the Arctic Ocean. Doklady Earth Sciences, 2023, vol. 512, no. 2, pp. 261—271. DOI: 10.31857/S268673972360100X. (In Russian).

6. Guemas V. et al. A review on Arctic sea‐ice predictability and prediction on seasonal to decadal time-scales. Quarterly J. of the Royal Meteorological Society, 2016, vol. 142, no. 695, pp. 546—561.

7. Wang M., Overland J. E. A sea ice free summer Arctic within 30 years: An update from CMIP5 models. Geophysical Research Letters, 2012, vol. 39, no. 18.

8. Zhang J., Rothrock D. A. Modeling global sea ice with a thickness and enthalpy distribution model in generalized curvilinear coordinates. Monthly Weather Rev., 2003, vol. 131, no. 5, pp. 845—861.

9. Wang W., Chen M., Kumar A. Seasonal prediction of Arctic sea ice extent from a coupled dynamical forecast system. Monthly Weather Rev., 2013, vol. 141, no. 4, pp. 1375—1394.

10. Madec G. et al. NEMO ocean engine. [S. l.], 2017.

11. Hvatov A. et al. Adaptation of NEMO-LIM3 model for multigrid high resolution Arctic simulation. Ocean Modelling, 2019, vol. 141, p. 101427.

12. Pemberton P. et al. Sea-ice evaluation of NEMO-Nordic 1.0: a NEMO–LIM3. 6-based ocean–sea-ice model setup for the North Sea and Baltic Sea. Geoscientific Model Development, 2017, vol. 10, no. 8, pp. 3105—3123.

13. Dominicus S., Mishra A. K. Sea ice concentration estimation techniques using machine learning: An end-to-end workflow for estimating concentration maps from sar images. arXiv preprint arXiv:2205.01403, 2022.

14. Johnson S. J. et al. SEAS5: the new ECMWF seasonal forecast system. Geoscientific Model Development, 2019, vol. 12, no. 3, pp. 1087—1117.

15. Petty A. A. et al. Skillful spring forecasts of September Arctic sea ice extent using passive microwave sea ice observations. Earth’s Future, 2017, vol. 5, no. 2, pp. 254—263.

16. Kapsch M. L. et al. The importance of spring atmospheric conditions for predictions of the Arctic summer sea ice extent. Geophysical Research Letters, 2014, vol. 41, no. 14, pp. 5288—5296.

17. Wang L. et al. Predicting summer Arctic sea ice concentration intraseasonal variability using a vector autoregressive model. J. of Climate, 2016, vol. 29, no. 4, pp. 1529—1543.

18. Kim J. et al. Satellite-based prediction of Arctic sea ice concentration using a deep neural network with multi-model ensemble. Remote Sensing, 2018, vol. 11, no. 1, p. 19.

19. Sochnev О. Ya., Kornishin K. А., Yefimov Ya. О., Mironov Ye. U., Porubayev V. S. Interannual variability of the ice-free period duration in the southwestern Kara Sea. Problemy Arktiki i Antarktiki [Arctic and Antarctic Research], 2019, vol. 65, no. 3, pp. 239—254. (In Russian).

20. Kim Y. J. et al. Prediction of monthly Arctic sea ice concentrations using satellite and reanalysis data based on convolutional neural networks. The Cryosphere, 2020, vol. 14, no. 3, pp. 1083—1104.

21. Dumanskaya I. O. Ice conditions of the seas of the European part of Russia. Moscow; Obninsk, IG-SOCIN, 2014, 605 p. (In Russian).

22. Dumanskaya I. O. Ice conditions of the seas of the Asian part of Russia. Moscow; Obninsk, IG-SOCIN, 2017, 640 p. (In Russian).

23. Dumanskaya I. O., Kotilevskaya A. M. Assessment of the possibility of using predictive methods of the twentieth century in the modern practice of ice navigation services in the non-Arctic seas of Russia. Tr. GMTS RF, 2009, iss. 343, pp. 67—88. (In Russian).

24. Timofeeva A. B., Yulin A. V., Ivanov V. V., Sharatunova M. V., Pavlova E. A. Ice cover of the Russian Arctic seas along the Northern sea route in the current climatic period. Arctic: Ecology and Economy, 2024, vol. 14, no. 1, рр. 135—146. DOI: 10.25283/2223-4594-2024-1-135-146. (In Russian).

25. Shishkin A. N., Kornishin K. A., Deinego I. D., Tarasov P. A. Northern sea route: present climate and future projections. Oil industry, 2024, no. 6, pp. 40—44. (In Russian).

26. Lemieux J. F. et al. The Regional Ice Prediction System (RIPS): verification of forecast sea ice concentration. Quarterly J. of the Royal Meteorological Society, 2016, vol. 142, no. 695, pp. 632—643.

27. Topaj A. G., Tarovik O. V., Bakharev A. A. Automatic routing of vessels in ice: problem statement and solution tools. Arctic: Ecology and Economy, 2022, vol. 12, no. 1, рр. 123—139. DOI: 10.25283/2223-4594-2022-1-123-139. (In Russian).

28. Tonboe R. et al. Product user manual for osi saf global sea ice concentration. Danish Meteorological Institute. Copenhagen, Denmark, 2016.

29. US National Ice Center and National Snow and Ice Data Center. Multisensor Analyzed Sea Ice Extent—Northern Hemisphere (MASIE-NH), Version 1. 2010.

30. Cartographic foundations of Natural Earth Data. Available at: https://www.naturalearthdata.com/.

31. The topographic basis of GEBCO. Available at: https://www.gebco.net/.

32. Sazonov K. E., Dobrodeev A. A. Ice handling of large-tonnage vessels. St. Petersburg, FSUE Krylov State Scientific Center, 2017.

33. Tarovik O. V. Models to predict the parameters of ship voyages in the Arctic: existing approaches and possible ways of development. Arctic: Ecology and Economy, 2021, vol. 11, no. 3, pp. 422—435. DOI: 10.25283/2223-4594-2021-3-422-435. (In Russian).

34. Buzin I. V., Klyachkin S. V., Frolov S. V., Smirnov K. G., Mikhaltseva S. V., Sokolova Yu. V., Gudoshnikov Yu. P., Voinov G. N., Grigoryev M. N. Compression of the ice cover in the Pechora Sea: a natural phenomenon and its impact on marine operations. Arctic: Ecology and Economy, 2022, vol. 12, no. 4, pp. 500—512. DOI: 10.25283/2223-4594-2022-4-500-512. (In Russian).

35. Buzin I. V., Klyachkin S. V., Frolov S. V., Smirnov K. G., Mikhaltceva S. V., Sokolova Yu. V., Gudoshnikov Yu  P., Voinov G. N., Grigoryev M. N. Some estimates of the severe ice conditions in the Pechora Sea based on observational and modeling data (simulation and analysis). Arctic: Ecology and Economy, 2024, vol. 14, no. 1, рр. 24—35. DOI: 10.25283/2223-4594-2024-1-24-35. (In Russian).

36. Andersson T. R. et al. Seasonal Arctic sea ice forecasting with probabilistic deep learning. Nature communications, 2021, vol. 12, no. 1, p. 5124.