Selection of Parameters and Architecture of Multilayer Perceptrons for Predicting Ice Coverage of Lakes

Nikolaevich Vyacheslav Baklagin 1
  • 1 Northern Water Problems Institute, Karelian Research Centre, Russian Academy of Sciences, , 185030, Petrozavodsk, Russian Federation


The ice cover on lakes is one of the most influential factors in the lakes’ winter aquatic ecosystem. The paper presents a method for predicting ice coverage of lakes by means of multilayer perceptrons. This approach is based on historical data on the ice coverage of lakes taking Lake Onega as an example. The daily time series of ice coverage of Lake Onega for 2004–2017 was collected by means of satellite data analysis of snow and ice cover of the Northern Hemisphere. Input signals parameters for the multilayer perceptrons aimed at predicting ice coverage of lakes are based on the correlation analysis of this time series. The results of training of multilayer perceptrons showed that perceptrons with architectures of 3-2-1 within the Freeze-up phase (arithmetic mean of the mean square errors for training epoch MSE¯=0.0155 ) and 3-6-1 within the Break-up phase ( MSE¯=0.0105 ) have the least mean-squared error for the last training epoch. Tests within the holdout samples prove that multilayer perceptrons give more adequate and reliable prediction of the ice coverage of Lake Onega (mean-squared prediction error MSPE = 0.0076) comparing with statistical methods such as linear regression, moving average and autoregressive analyses of the first and second order.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Atapaththu, K.S.S., Asaeda, T., Yamamuro, M. & Kamiya H. (2017). Effects of water turbulence on plant, sediment and water quality in reed (Phragmites australis) community. Ekológia (Bratislava), 36(1), 1–10. DOI: 10.1515/eko-2017-0001.

  • Blumberg, A.F. & Mellor G.L. (1986). A description of a three-dimensional coastal ocean circulation model. In N.S. Heaps (Ed.), Three-dimensional coastal ocean models (pp. 1–16). Washington, DC: American Geophysical Union.

  • Box, G.E.P., Jenkins, G.M., Reinsel, G.C. & Ljung G.M. (2015). Time series analysis: Forecasting and control. Hoboken, New Jersey: John Wiley & Sons, Inc.

  • Dallimore, C., Hodges, B.R. & Imberger J. (2003). Coupling an underflow model to a three-dimensional hydrodynamic model. Journal of Hydraulic Engineering, 129, 748–757. DOI: 10.1061/(ASCE)0733-9429(2003)129:10(748).

  • Hagan, M.T., Demuth, H.B., Beale, M.H. & De Jesus O. (2014). Neural network design. New Castle, DE: International Edition.

  • Haykin, S.(1999). Neural network: A comprehensive foundation. Hamilton, Ontario: Pearson Education, Inc.

  • Karetnikov, S.G. & Naumenko A.M. (2008). Recent trends in Lake Ladoga ice cover. Hydrobiologia, 599, 41–48. DOI: 10.1007/s10750-007-9211-1.

  • Madec, G. & NEMO team (2015). NEMO ocean engine. Paris: Insitute Pierre Simon Laplace.

  • Menshytkin, V.V., Rukhovets, L.A. & Filatov N.N. (2013). Ecosystem modeling of freshwater lakes (Review): 1. Hydrodynamics of lakes. Water Resources, 40, 606–620. DOI: 10.1134/S0097807813060080.

  • Sharif, A.J., Elias, Z.R. & Omar M.F. (2013). Water flow model for the Harrier basin, Kurdistan of Iraq. Ekológia (Bratislava), 32(2), 242–247. DOI: 10.2478/eko-2013-0020.

  • Quamrul Ahsan, A.K.M. & Blumberg A.F. (1999). Three-dimensional hydrothermal model of Onondaga Lake. Journal of Hydraulic Engineering, 125, 912–923. DOI: 10.1061/(ASCE)0733-9429(1999)125:9(912).


Journal + Issues