Abstract
The article reveals the issue of the neural networks’ applicability, considering the possibility of “mixing” the data set of cyclonic activity indicators in the North Atlantic as parallel inputs for constructing a long-term forecast of the air temperature anomaly in the Arctic region. The importance of considering this factor in the implementation of neural forecasting is determined by the fact that the North Atlantic cyclones provide the supply of heat and moisture to the polar regions and can also modify the ice cover of the Arctic Ocean. A nonlinear autoregression model with external inputs was used as a primary neural network. The training was carried out on data changes in temperature anomalies with a monthly resolution with different observation durations. The training sample is composed of three 20 year vectors, randomly selected from the available set. The software environment STATISTICA Automated Neural Networks was used as a tool in work, which allows researching data preparation to testing a trained neural network. Among all the considered variants of the network parameters, the best results of training the neural network were obtained with 15 hidden layers and a signal delay of 2 samples (simulation clock). Testing the predictive properties of the obtained neural network, carried out on a selection of unused data in training, and showed quite good results. In all cases, the correlation coefficient between the input data and the forecast was more than 0.85. The root-mean-square deviation (model error) did not exceed 0.5 °C. Despite the obtained high forecasting accuracy, it should be assumed that in further studies of building a temperature forecasting system, it is necessary to provide a procedure for periodic retraining of the network to consider the variability of parameters with “mixing” and other parallel inputs characterising the modern climatic dynamics of the Arctic region. Such a retraining scheme can be easily implemented using the methodology for constructing a neural model proposed in work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dobrolyubov, S.A.: Global circulation of ocean waters. Bull. Russian Acad. Sci. Geo. Series. 1, 33–41 (2005)
Kattsov, V.M., Porfiriev, B.N.: Climatic changes in the Arctic: consequences for the environment and the economy. Arctic Ecol. Econ. 6(2), 66–79 (2012)
Razorenova, O.A., Shabanov, P.A.: Climatology and interannual movements of upper-level frontal zones in the middle troposphere of the northern hemisphere. Doklady Earth Sci. 2(487), 995–1001 (2019)
Soloviev, D.A.: Modern climate changes in the Arctic: causes and environmental consequences. In: All-Russian conference with international participation II Yudakhin readings “Problems of ensuring environmental safety and sustainable development of the Arctic territories”, pp. 152–156 (2019)
Gulev, S.K., Kattsov, V.M., Solomina, O.N.: Global warming continues. Bull. Russian Acad. Sci. 1(78), 20–27 (2008)
Nefedova, L.V., Solovyev, D.A.: Assessment of the global climate change impact on fuel and energy complex infrastructure and adaptation opportunities in the Russian Arctic. In: IOP Conference Series, vol. 606. pp. 1040 (2020). https://doi.org/10.1088/1755-1315/606/1/012040
Rohde, R., Muller, R., Jacobsen, R., Perlmutter, S., Rosenfeld, A., Wurtele, J., Curry, J., Wickham, C., Mosher, S.: Berkeley Earth temperature averaging process. GeoinforGeostat: An Overview 2(1) (2013). https://doi.org/10.4172/gigs.1000103
Song, J.-N., Fu, G., Xu, Y., Han, Z.-Y., Sun, Q.-Z., Wang, H.: Assessment of the capability of CMIP6 global climate models to simulate Arctic cyclones. Adv. Clim. Change Res. 5(12), 660–676 (2021). https://doi.org/10.1016/j.accre.2021.07.007
Akperov, M.G., Dembitskaya, M.A., Mokhov, I.I.: Cyclonic activity in the Arctic region according to model calculations and reanalysis data. Izvestia Russian Acad. Sci. Geogr. Series. 6, 39–46 (2017)
Sherstyukov, B.G.: Climatic conditions of the Arctic and new approaches to forecasting climate change. Arctic North 24, 39–67 (2016). https://doi.org/10.17238/issn2221-2698.2016.24.39
Vakulenko, N.V., Nigmatulin, R.I., Sonechkin, D.M.: On the issue of global climate change. Meteorol. Hydrol. 9, 89–97 (2015)
Yamanouchi, T., Takata, K.: Rapid change of the Arctic climate system and its global influences—overview of GRENE Arctic climate change research project (2011–2016). Polar Sci. 100548 (2020). https://doi.org/10.1016/j.polar.2020.100548
Tilinina, N.D.: A new look at cyclonic activity in the Arctic. In: Changing Climate and Socio-Economic Potential of the Russian Arctic, pp. 46–55 (2016)
Akperov, M., Rinke, A., Mokhov, I.I., Semenov, V.A., Parfenova, M.R., Matthes, H., Adakudlu, M., Boberg, F., Christensen, J.H., Dembitskaya, M.A., Dethloff, K., Fettweis, X., Gutjahr, O., Heinemann, G., Koenigk, T., Koldunov, N.V., Laprise, R., Mottram, R., Nikiéma, O., Sein, D., Sobolowski, S., Winger, K., Zhang, W.: Future projections of cyclone activity in the Arctic for the 21st century from regional climate models (Arctic-CORDEX). Glob. Planetary Change 182, 103005 (2019). https://doi.org/10.1016/j.gloplacha.2019.103005
Tilinina, N.D., Gulev, S.K.: Dynamics of cyclonic activity in the Northern Hemisphere over the past three decades according to data from seven re-analyses. In: Solar Activity and the Nature of Global and Regional Climatic Changes, pp. 14–15 (2012)
Razorenova, O.A.: Winter climatology of upper-level frontal zones in the Northern Hemisphere. Russian Meteorol. Hydrol. 1(41), 1–9 (2016)
Tilinina, N., Gavrikov, A., Gulev, S.K.: Association of the North Atlantic surface turbulent heat fluxes with midlatitude cyclones. Month. Weather Rev. 11(146), 3691–3715 (2018)
Kuznetsov, B.F.: Short-term forecasting of temperature based on neural networks. Actual Prob. Agric. Sci. 30, 59–65 (2019)
Krinitskiy, M., Verezemskaya, P., Grashchenkov, K., Tilinina, N., Gulev, S., Lazzara, M.: Deep convolutional neural networks capabilities for binary classification of polar mesocyclones in satellite mosaics. Atmosphere 11(9), 426 (2018)
Haykin, S.: Neural Networks: a Complete Course, 2nd edn. Williams Publishing House (2008)
Acknowledgements
The work was performed with the Ministry of Science and Higher Education of the Russian Federation (agreement No. 075-15-2021-979, internal No. 13.2251.21.0071; the unique identifier of the RF project 225121x0071).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Solovyev, D.A., Razorenova, O.A., Nefedova, L.V. (2023). Neural Forecasting of the Average Air Temperature Anomaly in the Arctic Region Considering the Cyclonic Activity. In: Chaplina, T. (eds) Processes in GeoMedia—Volume VI. Springer Geology. Springer, Cham. https://doi.org/10.1007/978-3-031-16575-7_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-16575-7_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16574-0
Online ISBN: 978-3-031-16575-7
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)