Abstract
A supervised deep learning approach has been developed to automate recognition of the large-scale atmospheric circulation patterns. The approach is based on an application of the convolution neural network. The reanalysis meteorological fields were used as an input dataset. The dataset was labeled according to the circulation calendar constructed using the subjective Dzerdzeewski classification. One of the key issues for the success of the modeling was found to be a proper data preprocessing. The developed approach has demonstrated an accuracy compared with the more detailed regional classification methods that currently are being widely used for automated synoptic analysis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Available via atmospheric-circulation.ru.
References
Ashkezari M, Hill C, Follett C, Forget G, Follows M (2016) Oceanic eddy detection and lifetime forecast using machine learning methods. Geophys Res Lett 43:12234–12241. https://doi.org/10.1002/2016GL071269
Barnston AG, Livezey RE (1987) Classifications, seasonality, and persistence of low-frequency atmospheric circulation patterns. Mon Weather Rev 115:1083–1126. https://doi.org/10.1175/1520-0493(1987)115<1083:CSAPOL>2.0.CO;2
Bartoszek K (2017) The main characteristics of atmospheric circulation over East-Central Europe from 1871 to 2010. Meteorol Atmos Phys 129:113–129. https://doi.org/10.1007/s00703-016-0455-z
Bednorz E, Czernecki B, Tomczyk A, Polrolniczak M (2018) If not NAO then what?—regional circulation patterns governing summer air temperatures in Poland. Theoret Appl Climatol 1–13 (in press). https://doi.org/10.1007/s00704-018-2562-x
Cahynova M, Huth R (2016) Atmospheric circulation influence on climatic trends in Europe: an analysis of circulation type classifications from the COST733 catalogue. Int J Climatol 36:2743–2760. https://doi.org/10.1002/joc.4003
Cannon A (2012) Regression-guided clustering: a semisupervised method for circulation-to-environment synoptic classification. J Appl Meteorol Climatol 51:185–190. https://doi.org/10.1175/JAMC-D-11-0155.1
Chollet F et al (2015) Keras. https://keras.io
Compo G, Whitaker J, Sardeshmukh P, Matsui N, Allan R, Yin X, Gleason B, Vose R, Rutledge G, Bessemoulin P, BroNnimann S, Brunet M, Crouthamel R, Grant A, Groisman P, Jones P, Kruk M, Kruger A, Marshall G, Maugeri M, Mok H, Nordli O, Ross T, Trigo R, Wang X, Woodruff S, Worley S (2011) The twentieth century reanalysis project. Q J Roy Meteorol Soc 137:1–28. https://doi.org/10.1002/qj.776
Fleig A, Tallaksen L, James P, Hisdal H, Stahl K (2015) Attribution of European precipitation and temperature trends to changes in synoptic circulation. Hydrol Earth Syst Sci 19:3093–3107. https://doi.org/10.5194/hess-19-3093-2015
Gerlitz L, Steirou E, Schneider C, Moron V, Vorogushyn S, Merz B (2018) Variability of the cold season climate in Central Asia. Part I: weather types and their tropical and extratropical drivers. J Clim 31:7185–7207. https://doi.org/10.1175/JCLI-D-17-0715.1
Hannachi A, Straus D, Franzke C, Corti S, Woollings T (2017) Low-frequency nonlinearity and regime behavior in the Northern Hemisphere extratropical atmosphere, 55:199–234. https://doi.org/10.1002/2015RG000509
Kadavi P, Lee C, Lee S (2018) Application of ensemble-based machine learning models to landslide susceptibility mapping. Remote Sens 10:1252–1269. https://doi.org/10.3390/rs10081252
Kononova N (2018) Type of global atmospheric circulation: results of monitoring and observations for 1899–2017 yy. Fundam Pract Climatol 3:108–123. https://doi.org/10.21513/2410-8758-2018-3-108-123 (in Russian)
Korycki L, Krawczyk B (2018) Combining active learning and self-labeling for data stream mining. In: Kurzynski M, Wozniak M, Burduk R (eds) Proceedings of the 10th International Conference on Computer Recognition Systems, CORES 2017. Advances in Intelligent Systems and Computing, vol 578. Springer, Cham. https://doi.org/10.1007/978-3-319-59162-9_50
Kucerova M, Beck C, Philipp A, Huth R (2017) Trends in frequency and persistence of atmospheric circulation types over Europe derived from a multitude of classifications. Int J Climatol 37:2502–2521. https://doi.org/10.1002/joc.4861
Mammadov A, Rajabov R, Hasanova N (2018) Causes of periodical rainfall distribution and long-term forecast of precipitation for Lankaran, Azerbaijan. Meteorol Hydrol Water Manag 6(2):1–5. https://doi.org/10.26491/mhwm/89763
Nojarov P (2017) Genetic climatic regionalization of the Balkan Peninsula using cluster analysis. J Geogr Sci 27(1):43–61. https://doi.org/10.1007/s11442-017-1363-y
Park K, Kim D (2018) Accelerating image classification using feature map similarity in convolutional neural networks. Appl Sci 9(1):108. https://doi.org/10.3390/app9010108
Pringle J, Stretch D, Bardossy A (2014) Automated classification of the atmospheric circulation patterns that drive regional wave climates. Nat Hazards Earth Syst Sci 14:2145–2155. https://doi.org/10.5194/nhess-14-2145-2014
Rodrigues E, Gomes A, Gaspar A, Henggeler Antunes C (2018) Estimation of renewable energy and built environment-related variables using neural networks - a review. Renew Sustain Energy Rev 94:959–988. https://doi.org/10.1016/j.rser.2018.05.060
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, CoRR. arXiv:1409.1556
Stryhal J, Huth R (2018) Classifications of winter atmospheric circulation patterns: validation of CMIP5 GCMs over Europe and the North Atlantic. Clim Dyn 7:1–24. https://doi.org/10.1007/s00382-018-4344-7
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA, USA. https://doi.org/10.1109/CVPR.2015.7298594
Cohen TS, Welling M (2016) Group equivariant convolutional networks. arXiv: 1602.07576
Tarabukina L, Kononova N, Kozlov V, Innokentiev D, Shafer Y (2018) Analysis of atmospheric circulation condition during severe thunderstorms in Yakutia in 2009–2016. In: Miloch WJ, Vodinchar GM, Shevtsov BM (eds) 62 Proceedings of the 10th 9th International Conference Solar-Terrestrial Relations and Physics of Earthquake Precursors, STRPEP 2018. EDP Science. https://doi.org/10.1051/e3sconf/20186201001
Wan J, Ren G, Liu J, Hu Q, Yu D (2016) Ultra-short-term wind speed prediction based on multi-scale predictability analysis. Cluster Comput 19:741–755. https://doi.org/10.1007/s10586-016-0554-0
Woyciechowska J, Ustrnul Z (2011) Fuzzy logic circulation types based on the Osuchowska-Klein classification system created for Poland. Theoret Appl Climatol. https://doi.org/10.1007/s00704-010-0366-8
Zhang J, Liu P, Zhang F, Song Q (2018) CloudNet: ground-based cloud classification with deep convolutional neural network. Geophys Res Lett 45:1–8. https://doi.org/10.1029/2018GL077787
Acknowledgments
Authors highly appreciate discussions of the meteorologic processes with Prof. N.K. Kononova that have been highly encouraging for a presented work.
The work was supported by the Russian Science Foundation (project no. 18-79-10255).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Luferov, V., Fedotova, E. (2020). A Deep Learning Approach to Recognition of the Atmospheric Circulation Regimes. In: Burduk, R., Kurzynski, M., Wozniak, M. (eds) Progress in Computer Recognition Systems. CORES 2019. Advances in Intelligent Systems and Computing, vol 977. Springer, Cham. https://doi.org/10.1007/978-3-030-19738-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-19738-4_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19737-7
Online ISBN: 978-3-030-19738-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)