ACS  Vol.3 No.4 , October 2013
On the Downscaling of Meteorological Fields Using Recurrent Networks for Modelling the Water Balance in a Meso-Scale Catchment Area of Saxony, Germany
ABSTRACT

In this study, recurrent networks to downscale meteorological fields of the ERA-40 re-analysis dataset with focus on the meso-scale water balance were investigated. Therefore two types of recurrent neural networks were used. The first approach is a coupling between a recurrent neural network and a distributed watershed model and the second a nonlinear autoregressive with exogenous inputs (NARX) network, which directly predicted the component of the water balance. The approaches were deployed for a meso-scale catchment area in the Free State of Saxony, Germany. The results show that the coupled approach did not perform as well as the NARX network. But the meteorological output of the coupled approach already reaches an adequate quality. However the coupled model generates as input for the watershed model insufficient daily precipitation sums and not enough wet days were predicted. Hence the long-term annual cycle of the water balance could not be preserved with acceptable quality in contrary to the NARX approach. The residual storage change term indicates physical restrictions of the plausibility of the neural networks, whereas the physically based correlations among the components of the water balance were preserved more accurately by the coupled approach.


Cite this paper
R. Kronenberg, K. Barfus, J. Franke and C. Bernhofer, "On the Downscaling of Meteorological Fields Using Recurrent Networks for Modelling the Water Balance in a Meso-Scale Catchment Area of Saxony, Germany," Atmospheric and Climate Sciences, Vol. 3 No. 4, 2013, pp. 552-561. doi: 10.4236/acs.2013.34058.
References
[1]   H. von Storch, S. Güss and M. Heimann, “Das Klimasystem und seine Modellierung—Eine Einführung,” Springer-Verlag, Berlin, Heidelberg, 1999. http://dx.doi.org/10.1007/978-3-642-58528-9

[2]   D. Jacob, “A Note to the Simulation of the Annual and Inter-Annual Variability of the Water Budget over the Baltic Sea Drainage Basin,” Meteorological Atmospheric Physics, Vol. 77, 2001, pp. 61-73.
http://dx.doi.org/10.1007/978-3-642-58528-9

[3]   D. Jacob, H. Gottel, S. Kotlarski, P. Lorenz and K. Sieck, “Klimaauswirkungen und Anpassung in Deutschland— Phase 1: Erstellung Regionaler Klimaszenarien für Deutschland,” 2008.

[4]   H. D. Hollweg, U. Bohm, I. Fast, B. Hennemuth, K. Keuler, E. Keupthiel, M. Lautenschlager, S. Legutke, K. Radtke, B. Rockel, M. Schubert, A. Will, M. Woldt and C. Wunram, “Ensemble Simulations over Europe with the Regional Climate Model CLM Forced with IPCC AR4 Global Scenarios,” M & D Technical Report 3, 2008.

[5]   W. C. Skamarock, J. B. Klemp, J. Dudhia, D. O. Gill, D. M. Barker, M. G. Duda, X. Huang, W. Wang and J. G. Powers, “A Description of the Advanced Research WRF Version 3,” NCAR Technical Note June 2008, 2008.

[6]   R. L. Wilby and T. M. L. Wigley, “Downscaling General Circulation Model Output: A Review of Methods and Limitations,” Progress in Physical Geography, Vol. 21, No. 4, 1997, pp. 530-548.
http://dx.doi.org/10.1177/030913339702100403

[7]   Y. B. Dibike and P. Coulibaly, “Temporal Neural Networks for Downscaling Climate Variability and Extremes,” Neural Networks, Vol. 19, No. 2, 2006, pp. 135-144. http://dx.doi.org/10.1016/j.neunet. 2006.01.003

[8]   B. Tomassetti, M. Verdecchia and F. Giorgi, “NN5: A Neural Network Based Approach for the Downscaling of Precipitation Fields—Model description and preliminary results,” Journal of hydrology, Vol. 367, No. 1-2, 2009, pp. 14-26. http://dx.doi.org/10.1016/j.jhydrol.2008.12.017

[9]   T. Sauter and V. Venema, “Natural Three-Dimensional Predictor Domains for Statistical Precipitation Downscaling,” Journal of Climate, Vol. 24, No. 23, 2011, pp. 6132-6145.
http://dx.doi.org/10.1175/2011JCLI4155.1

[10]   C. Bernhofer, V. Goldberg, J. Franke, J. Hantschel, S. Harmansa, T. Pluntke, T. Geidel, M. Surke, H. Prasse, E. Freydank, S. Hasel, U. Mellentin and W. Küchler, “Sachsen im Klimawandel—Eine Analyse,” Sachsisches Staatsministerium für Umwelt und Landwirtschaft, Dresden, 2008, p. 211.

[11]   K. Mannsfeld, O. Bastian, A. Kaminski, W. Katzschner, M. Roder, R.-U. Syrbe and B. Winkeler, “Landschaftsgliederungen in Sachsen,” Mitteilungen des Landesvereins S?chsischer Heimatschutz e.V., Sonderheft, Dresden, 2005, p. 68.

[12]   C. Bernhofer and V. Goldberg, “CLISAX—Statistische Untersuchungen Regionaler Klimatrends in Sachsen,” TU Dresden, Institut für Hydrologie und Meteorologie, 2001.

[13]   J. Franke, V. Goldberg, U. Eichelmann, E. Freydank and C. Bernhofer, “Statistical Analysis of Regional Climate Trends in Saxony, Germany,” Climate Research, Vol. 27, No. 2, 2004, pp. 145-150.
http://dx.doi.org/10.3354/cr027145

[14]   J. Schulla and K. Jasper, “Model Description WaSiMETH,” Internal Report, Institute for Atmospheric and Climate Science, ETH Zürich, 2007, p. 181.

[15]   S. M. Uppala, P. W. Kallberg, A. J. Simmons, U. Andrae, V. da Costa Bechtold, M. Fiorino, J. K. Gibson, J. Haseler, A. Hernandez, G. A. Kelly, X. Li, K. Onogi, S. Saarinen, N. Sokka, R. P. Allan, E. Andersson, K. Arpe, M. A. Balmaseda, A. C. M. Beljaars, L. van de Berg, J. Bidlot, N. Bormann, S. Caires, F. Chevallier, A. Dethof, M. Dragosavac, M. Fisher, M. Fuentes, S. Hagemann, E. Hólm, B. J. Hoskins, L. Isaksen, P. A. E. M Janssen, R. Jenne, A. P. McNally, J.-F. Mahfouf, J.-J. Morcrette, N. A. Rayner, R. W. Saunders, P. Simon, A. Sterl, K. E. Trenberth, A. Untch, D. Vasiljevic, P. Viterbo and J. Woollen, “The ERA-40 Re-Analysis,” Quarterly Journal of the Royal Meteorological Society, Vol. 131, No. 612, 2005, pp. 2961-3012. http://dx.doi.org/10.1256/qj.04.176?

[16]   J. Schulla and K. Jasper, “Modellbeschreibung WaSiMETH,” Technischer Bericht, Institut für Atmosphare und Klima, ETH Zürich, 1998, p. 152

[17]   J. Scherzer, G. Wriedt, D. Sames, M. Müller, F. Hesser, K. Jasper and H. Pohler, “KLiWEP—Abschatzung der Auswirkungen der für Sachsen Prognostizierten Klimaveranderungen auf den Wasserund Stoffhaushalt im Einzugsgebiet der Parthe—Teil 3: Vorstudie zur Simulation der Stoffflüsse von Stickstoff und Kohlenstoff im Parthe-Einzugsgebiet,” 2006.

[18]   H. Pohler, F. Chmielewski, K. Jasper, Y. Hennings and J. Scherzer, “KliWEP -Abschatzung der Auswirkungen der für Sachsen Prognostizierten Klimaveranderungen auf den Wasserund Stoffhaushalt im Einzugsgebiet der Parthe—Weiterentwicklung von WaSiM-ETH: Implikation Dynamischer Vegetationszeiten und Durchführung von Testsimulationen für Sachsische Klimaregionen,” Sachsisches Landesamt für Umwelt und Geologie, Abschlussbericht des Forschungsund Entwicklungsvorhabens Nr. 13, 2007.

[19]   J. Doherty, “Model-Independent Parameter Estimation User Manual: 5th Edition,” Watermark Numerical Computing, 2004, p. 336.

[20]   D. N. Moriasi, J. G. Arnold, M. W. Van Liew, R. L. Bingner, R. D. Harmel and T. L. Veith, “Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations,” Transactions of the ASABE, Vol. 50, 2007, pp. 885-900.

[21]   J. Singh, H. V. Knapp, J. G. Arnold and M. Demissie, “Hydrologic Modeling of the Iroquois River Watershed Using HSPF and SWAT,” Journal of the American Water Resources Association, Vol. 41, No. 2, 2005, pp. 343-360. http://dx.doi.org/10.1111/j.1752-1688.2005.tb03740.x

[22]   T. Jayalakshmi and A. Santhakumaran, “Statistical Normalization and Back Propagation for Classification,” International Journal of Computer Theory and Engineering, Vol. 3, No. 1, 2011, pp. 89-93. http://dx.doi.org/10.7763/IJCTE. 2011.V3.288

[23]   C. Jiang and F. Song, “Sunspot Forecasting by Using Chaotic Time Timeseries Analysis and NARX Network,” Journal of Computers, Vol. 6, No. 7, 2011, pp. 1424-1429. http://dx.doi.org/10.4304/ jcp.6.7.1424-1429

[24]   C. M. Bishop, “Neural Networks for Pattern Recognition,” Oxford University Press, 1996, p. 482.

[25]   J. M. P. Menezes Jr. and G. A. Barreto, “Long-Term Time Series Prediction with the NARX Network: An Empirical Evaluation,” Neurocomputing, Vol. 71, No. 16-18, 2008, pp. 3335-3343.
http://dx.doi.org/10.1016/j.neucom.2008.01.030

[26]   H.-Y. Shen and L.-C. Chang, “Online Multistep-Ahead Inundation Depth Forecasts by Recurrent NARX Networks,” Hydrology and Earth System Sciences, Vol. 17, 2013, pp. 935-945.
http://dx.doi.org/10.5194/hess-17-935-2013

[27]   S. Haykin, “Neural Networks and Learning Machines,” 3rd Edition, Pearson Prentice Hall, Upper Saddle River, 2009.

[28]   H. von Storch and F. W. Zwiers, “Statistical Analysis in Climate Reasearch,” Cambridge University Press, 2010.

[29]   D. S. Wilks, “Statistical Methods in the Atmospheric Sciences: An Introduction,” International Geophysics Series, Vol. 59, Academic Press, 1995, p. 464.

[30]   C.-D. Schonwiese, “Praktische Statistik für Meteorologen und Geowissenschaftler,” 4 Auflage, Verlag Gebrüder Borntraeger, Stuttgart, 2006, p. 302.

[31]   C. Bernhofer, J. Matschullat and A. Bobeth (Hrsg.), “Das Klima in der Modellregion Dresden,” Rhombos-Verlag, Berlin, 2009, p. 117.

[32]   D. S. Wilks and R. L. Wilby, “The Weather Generation Game: A Review of Stochastic Weather Models,” Progress in Physical Geography, Vol. 23, No. 3, 1999, pp. 329-357.
http://dx.doi.org/10.1177/030913339902300302

[33]   R. Kronenberg, J. Franke and C. Bernhofer, “Comparison of Different Approaches to Fit Log-Normal Mixtures on Radar-Derived Precipitation Data,” Meteorological Applications, 2013, I press.
http://dx.doi.org/10.1002/met.1408

[34]   M. Mudelsee, M. Borngen, G. Tetzlaff and U. Grünwald, “Extreme Floods in Central Europe over the Past 500 Years: Role of Cyclones Pathway, ‘Zugstrasse Vb’,” Journal of Geophysical Research, Vol. 109, No. D23, 2004, pp. 1-21. http://dx.doi.org/10.1029/2004JD005034

 
 
Top