ASSESSMENT OF ATMOSPHERIC DYNAMICS BASED ON NEURAL NETWORK DOWNSCALING OF NEAR-SURFACE WIND OVER THE BARENTS AND KARA SEAS

  • V. Yu. Rezvov Moscow Institute of Physics and Technology; Shirshov Institute of Oceanology, Russian Academy of Sciences
  • M. A. Krinitskiy Moscow Institute of Physics and Technology; Shirshov Institute of Oceanology, Russian Academy of Sciences
  • A. V. Gavrikov Shirshov Institute of Oceanology, Russian Academy of Sciences
DOI: 10.29006/1564-2291.JOR-2025.53(2).8
Keywords: downscaling, near-surface wind, polar mesocyclones, Novaya Zemlya bora, artificial neural networks, machine learning, deep learning, wind-induced waves

Abstract

This study explores the use of deep learning for downscaling of near-surface wind over the Barents and Kara Seas, utilizing deep artificial neural networks with skip connections to increase spatial resolution while reducing computational costs compared to non-hydrostatic modeling. The low-resolution input data is sourced from the global atmospheric reanalysis ERA5, while high-resolution data is obtained using the Weather Research and Forecasting (WRF) model. The results of neural network downscaling are compared with the baseline from bilinear interpolation. The neural network model improves the distribution of mesocyclone life cycle parameters, aligning them closer to the high-resolution modeling data, and outperforms bilinear interpolation by 50 times in terms of speed. The height of wind-induced waves, obtained using boundary conditions from the neural network model instead of non-hydrostatic modeling, shows similar values to those obtained with non-hydrostatic modeling. The developed neural network model shows a deviation of less than 3 % from high-resolution dynamic modeling in terms of the number of mesoscale structures.

References


  1. Davis, C., B. Brown, and R. Bullock, 2006: Object-based verification of precipitation forecasts. Part I: Methodology and application to mesoscale rain areas. Monthly Weather Review, 134 (7), 1772–1784, https://doi.org/10.1175/MWR3145.1.

  2. Dong, H., S. Cao, T. Takemi, and Y. Ge, 2018: WRF simulation of surface wind in high latitudes. Journal of Wind Engineering and Industrial Aerodynamics, 179, 287–296, https://doi.org/10.1016/j.jweia.2018.06.009.

  3. Efimov, V. V. and O. I. Komarovskaya, 2018: Novozemelskaya bora: analiz i chislennoye modelirovaniye (Novaya Zemlya Bora: Analysis and Numerical Modeling). Izvestiya Rossiiskoi akademii nauk. Fizika atmosfery i okeana, 54 (1), 83–96, https://doi.org/10.7868/S0003351518010099.

  4. Gavrikov, A., 2017: Estimating the reproduction quality of precipitation over the North Atlantic and influence of the hydrostatic approximation in the WRF–ARW atmospheric model. Oceanology, 57 (2), 232–238, https://doi.org/10.1134/S0001437017020047.

  5. Gavrikov, A. V. and S. K. Gulev, 2020: The North Atlantic High-Resolution Regional Climate Model Experiment for Oceanic and Atmospheric Applications. Oceanology, 60, 725–727, https://doi.org/10.1134/S0001437020060041.

  6. Hersbach, H., B. Bell, P. Berrisford, S. Hirahara, A. Horányi, J. Muñoz-Sabater, J. Nicolas, C. Peubey, R. Radu, D. Schepers, A. Simmons, C. Soci, S. Abdalla, X. Abellan, G. Balsamo, P. Bechtold, G. Biavati, J. Bidlot, M. Bonavita, G. De Chiara, P. Dahlgren, D. Dee, M. Diamantakis, R. Dragani, J. Flemming, R. Forbes, M. Fuentes, A. Geer, L. Haimberger, S. Healy, R. J. Hogan, E. Hólm, M. Janisková, S. Keeley, P. Laloyaux, P. Lopez, C. Lupu, G. Radnoti, P. de Rosnay, I. Rozum, F. Vamborg, S. Villaume, and J.-N. Thépaut, 2020: The ERA5 global reanalysis. Quarterly Journal of the Royal Meteorological Society, 146 (730), 1999–2049, https://doi.org/10.1002/qj.3803.

  7. Höhlein, K., M. Kern, T. Hewson, and R. Westermann, 2020: A comparative study of convolutional neural network models for wind field downscaling. Meteorological Applications, 27, Article e1961, https://doi.org/10.1002/met.1961.

  8. Hong, S. Y. and J. O. J. Lim, 2006: The WRF single-moment 6-class microphysics scheme (WSM6). Asia-Pacific Journal of Atmospheric Sciences, 42 (2), 129–151.

  9. Hydrometeorologiya i gidrokhimiya morey SSSR. Barentsevo more, Vyp. 1. Gidrometeorologicheskie usloviya (Hydrometeorology and Hydrochemistry of the Seas of the USSR. Vol. 1. Barents Sea. Issue 1. Hydrometeorological Conditions), Leningrad, Gidrometeoizdat, 1990, 280 p.

  10. Iacono, M. J., J. S. Delamere, E. J. Mlawer, M. W. Shephard, S. A. Clough, and W. D. Collins, 2008: Radiative forcing by long-lived greenhouse gases: Calculations with the AER radiative transfer models. Journal of Geophysical Research, 113, D13103, https://doi.org/10.1029/2008JD009944.

  11. Jagannathan, K., A. D. Jones, and I. Ray, 2020: The making of a metric: Coproducing decision-relevant climate science. Bulletin of the American Meteorological Society, 102 (8), 1–33, https://doi.org/10.1175/BAMS-D-19-0296.1.

  12. Janjić, Z. I., 1994: The Step-Mountain Eta Coordinate Model: Further Developments of the Convection, Viscous Sublayer, and Turbulence Closure Schemes. Monthly Weather Review, 122, 927–945, https://doi.org/10.1175/1520-0493(1994)122<0927:TSMECM>2.0.CO;2.

  13. Kain, J. S., 2004: The Kain–Fritsch Convective Parameterization: An Update. Journal of Applied Meteorology and Climatology, 43, 170–181, https://doi.org/10.1175/1520-0450(2004)043<0170:TKCPAU>2.0.CO;2.

  14. Kingma, D. P. and J. Ba, 2014: Adam: A method for stochastic optimization. Preprint arXiv:1412.6980.

  15. Kolář, V., P. Moses, and J. Šístek, 2010: Local corotation of line segments and vortex identification. In: Proceedings of the Seventeenth Australasian Fluid Mechanics Conference, 251–254.

  16. Koshkina, V. S., A. V. Gavrikov, and S. K. Gulev, 2023: Methods of identifying atmospheric mesoscale coherent structures over the North Atlantic. Oceanology, 63 (Suppl. 1), S101–S110, https://doi.org/10.1134/S000143702307007X.

  17. Koshkina, V. S. and A. V. Gavrikov, 2024: Issledovanie primenimosti metodov identifikatsii kogerentnykh vikhrvykh struktur v modelnykh eksperimentakh (Study of the Applicability of Methods for Identifying Coherent Vortex Structures in Model Experiments). Journal of Oceanological Research, 52 (4), 90–107.

  18. Koshkina, V. S., A. V. Gavrikov, and N. D. Tilinina, 2024: Avtomaticheskaya identifikatsiya novozemelskoy bory (Automatic Identification of the Novaya Zemlya Bora). Journal of Oceanological Research, 52 (4), 74–89, https://doi.org/10.29006/1564-2291.JOR-2024.52(4).5.

  19. Krinitskiy, M., K. Grashchenkov, N. Tilinina, and S. Gulev, 2021: Tracking of atmospheric phenomena with artificial neural networks: a supervised approach. Procedia Computer Science, 186, 403–410, https://doi.org/10.1016/j.procs.2021.04.209.

  20. Krinitskiy, M. A., N. D. Tilinina, V. Y. Rezvov, A. I. Suslov, V. A. Golikov, E. A. Yezhova, P. S. Verezemskaya, and A. V. Gavrikov, 2024: Metody mashinnogo obucheniya v issledovaniyakh okeana i atmosfery (Methods of Machine Learning in Ocean and Atmospheric Research). Moscow, Sam Poligrafist, 170 p.

  21. Liu, C., Y. Wang, and Y. Yang et al., 2016: New omega vortex identification method. Science China Physics, Mechanics & Astronomy, 59, 684711, https://doi.org/10.1007/s11433-016-0022-6.

  22. Liu, C., Y. Gao, S. Tian, and X. Dong, 2018: Rortex – A new vortex vector definition and vorticity tensor and vector decompositions. Physics of Fluids, 30 (3), 035103, https://doi.org/10.1063/1.5023001.

  23. Monin, A. S., 1965: Statisticheskaya gidromekhanika. Mekhanika turbulentnosti. Ch. 1. (Statistical Hydromechanics. Mechanics of Turbulence. Part 1). 639 p.

  24. Moreno-Chamarro, E., T. Arsouze, M. Acosta, P.-A. Bretonnière, M. Castrillo, E. Ferrer, A. Frigola, D. Kuznetsova, E. Martin-Martinez, P. Ortega, and S. Palomas, 2025: The very-high-resolution configuration of the EC-Earth global model for HighResMIP. Geoscientific Model Development, 18, 461–482, https://doi.org/10.5194/gmd-18-461-2025.

  25. Nakanishi, M., and H. Niino, 2009: Development of an improved turbulence closure model for the atmospheric boundary layer. Journal of the Meteorological Society of Japan. Series II, 87 (5), 895–912, https://doi.org/10.2151/jmsj.87.895.

  26. Neu, U., M. G. Akperov, N. Bellenbaum, R. Benestad, R. Blender, R. Caballero, A. Cocozza, H. F. Dacre, Y. Feng, K. Fraedrich, J. Grieger, S. Gulev, J. Hanley, T. Hewson, M. Inatsu, K. Keay, S. F. Kew, I. Kindem, G. C. Leckebusch, M. L. R. Liberato, P. Lionello, I. I. Mokhov, J. G. Pinto, C. C. Raible, M. Reale, I. Rudeva, M. Schuster, I. Simmonds, M. Sinclair, M. Sprenger, N. D. Tilinina, I. F. Trigo, S. Ulbrich, U. Ulbrich, X. L. Wang, and H. Wernli, 2013: IMILAST: A Community Effort to Intercompare Extratropical Cyclone Detection and Tracking Algorithms. Bulletin of the American Meteorological Society, 94 (4), 529–547, https://doi.org/10.1175/BAMS-D-11-00154.1.

  27. Nikitin, M. A., G. S. Rivin, I. A. Rozinkina, and M. M. Chumakov, 2016: Ispol’zovanie prognosticheskoy sistemy COSMO-Ru dlya issledovaniya svoistv polyarnykh tsiklonov: epizod 25–27 marta 2014 goda (Using the COSMO-Ru Forecast System to Study the Properties of Polar Cyclones: Episode of March 25–27, 2014). Trudy Gidromettsentra Rossii, 361, 128–145.

  28. Oberto, E., M. Milelli, F. Pasi, and B. Gozzini, 2012: Intercomparison of two meteorological limited area models for quantitative precipitation forecast verification. Natural Hazards and Earth System Sciences, 12, 591–606, https://doi.org/10.5194/nhess-12-591-2012.

  29. Petrichenko, S. A., O. V. Kalmykova, S. V. Kozlov, and L. K. Kulizhnikova, 2023: Ispolzovanie kompozitsii indeksov konvektivnoy neustoychivosti dlya prognoza zarozhdeniya polyarnykh mezotsiklonov v Arkticheskom regione Rossii (Use of Composite Indices of Convective Instability for Predicting the Formation of Polar Mesocyclones in the Russian Arctic Region). Rossiyskaya Arktika, 5 (2), 54–64.

  30. Reed, K. A., N. Goldenson, R. Grotjahn, W. J. Gutowski, K. Jagannathan, A. D. Jones, L. R. Leung, S. A. McGinnis, S. C. Pryor, A. K. Srivastava, P. A. Ullrich, and C. M. Zarzycki, 2022: Metrics as tools for bridging climate science and applications. Wiley Interdisciplinary Reviews: Climate Change, 13 (6), e799, https://doi.org/10.1002/wcc.799.

  31. Rezvov, V. Yu., M. A. Krinitskiy, and N. D. Tilinina, 2024: Potocechnye i kompleksnye mery kachestva v issledovaniyakh atmosfery i okeana: obzor metodov i podkhodov (Point and Comprehensive Quality Measures in Atmosphere and Ocean Studies: Review of Methods and Approaches). Journal of Oceanological Research, 52 (4), 193–223, https://doi.org/10.29006/1564-2291.JOR-2024.52(4).10.

  32. Robinson, S., et al., 1991: Coherent motions in the turbulent boundary layer. Annual Review of Fluid Mechanics, 23 (1), 601–639.

  33. Ronneberger, O., P. Fischer, and T. Brox, 2015: U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Eds. N. Navab, J. Hornegger, W. Wells, and A. Frangi, Springer, Cham, Lecture Notes in Computer Science, 9351, https://doi.org/10.1007/978-3-319-24574-4_28.

  34. Schubert, E., J. Sander, M. Ester, H. P. Kriegel, and X. Xu, 2017: DBSCAN Revisited, Revisited: Why and How You Should (Still) Use DBSCAN. ACM Transactions on Database Systems, 42 (3), Article 19, https://doi.org/10.1145/3068335.

  35. Shestakova, A. A., 2016: Novozemel’skaya bora: podvetrennye kharakteristiki i struktura natekayushchego potoka (Novaya Zemlya Bora: Leeward Characteristics and Structure of the Incoming Flow). Arktika i Antarktika, 2, 86–98, https://doi.org/10.7256/2453-8922.2016.2.21479.

  36. Skamarock, W., J. Klemp, J. Dudhia, D. O. Gill, Z. Liu, J. Berner, W. Wang, J. G. Powers, M. G. Duda, D. Barker, and X.-Y. Huang, 2019: A Description of the Advanced Research WRF Model Version 4.1, https://doi.org/10.5065/1dfh-6p97.

  37. Stoll, P. J., T. M. Valkonen, R. G. Graversen, and G. Noer, 2020: A well-observed polar low analysed with a regional and a global weather-prediction model. Quarterly Journal of the Royal Meteorological Society, 146, 1740–1767, https://doi.org/10.1002/qj.3764.

  38. Surkova, G. V., and A. A. Krylov, 2018: Izmeneniya srednikh i ekstremal’nykh skorostei vetra v Arktike v kontse XXI veka (Changes in Average and Extreme Wind Speeds in the Arctic by the End of the 21st Century). Arktika i Antarktika, 3, 26–36, https://doi.org/10.7256/2453-8922.2018.3.27395.

  39. Turner, J., 2003: Polar Lows: Mesoscale Weather Systems in the Polar Regions. Cambridge University Press, Cambridge, 612 p.

  40. Verezemskaya, P., N. Tilinina, S. Gulev, I. A. Renfrew, and M. Lazzara, 2017: Southern Ocean mesocyclones and polar lows from manually tracked satellite mosaics. Geophysical Research Letters, 44, 7985–7993, https://doi.org/10.1002/2017GL074053.

  41. The WAVEWATCH III Development Group (WW3DG). User manual and system documentation of WAVEWATCH III version 6.07.1. https://raw.githubusercontent.com/wiki/NOAA-EMC/WW3/files/manual.pdf,.(last accessed in 10.06.2024).

  42. Zhou, J., R. J. Adrian, S. Balachandar, and T. Kendall, 1999: Mechanisms for generating coherent packets of hairpin vortices in channel flow. Journal of Fluid Mechanics, 387, 353–396.

  43. Zolotokrylin, A. N., T. B. Titkova, and A. Yu. Mikhailov, 2014: Klimaticheskie variatsii arkticheskogo fronta i ledovitosti Barentseva morya zimoi (Climatic Variations of the Arctic Front and Ice Cover in the Barents Sea in Winter). Led i Sneg, 54 (1), 85–90, https://doi.org/10.15356/2076-6734-2014-1-85-90.

Published
2025-06-30
Issue
Vol 53 No 2 (2025): Journal of Oceanological Research
Section
Ocean physics and atmosphere

Transfer of copyrights occurs on the basis of a license agreement between the Author and Shirshov Institute of Oceanology, RAS