Hydrology and Earth System Sciences www.hydrol-earth-syst-sci.net 1027-5606 1607-7938 13 9 2009 10.5194/hess-13-1555-2009 http://www.hydrol-earth-syst-sci.net/13/1555/2009/ http://www.hydrol-earth-syst-sci.net/13/1555/2009/hess-13-1555-2009.html http://www.hydrol-earth-syst-sci.net/13/1555/2009/hess-13-1555-2009.pdf 1555 1566 2009-09-03 Classification of hydro-meteorological conditions and multiple artificial neural networks for streamflow forecasting E. Toth elena.toth@unibo.it University of Bologna, Faculty of Engineering, viale Risorgimento 2, 40136 Bologna, Italy This paper presents the application of a modular approach for real-time streamflow forecasting that uses different system-theoretic rainfall-runoff models according to the situation characterising the forecast instant. For each forecast instant, a specific model is applied, parameterised on the basis of the data of the similar hydrological and meteorological conditions observed in the past. In particular, the hydro-meteorological conditions are here classified with a clustering technique based on Self-Organising Maps (SOM) and, in correspondence of each specific case, different feed-forward artificial neural networks issue the streamflow forecasts one to six hours ahead, for a mid-sized case study watershed. The SOM method allows a consistent identification of the different parts of the hydrograph, representing current and near-future hydrological conditions, on the basis of the most relevant information available in the forecast instant, that is, the last values of streamflow and areal-averaged rainfall. The results show that an adequate distinction of the hydro-meteorological conditions characterising the basin, hence including additional knowledge on the forthcoming dominant hydrological processes, may considerably improve the rainfall-runoff modelling performance. % vor jede Referenz Abrahart, R. J. and See, L.: Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments, Hydrol. Process., 14(11), 2157–2172, 2000. % vor jede Referenz Abrahart, R. J. and See, L.: Multi-model data fusion for river flow forecasting: an evaluation of six alternative methods based on two contrasting catchments, Hydrol. Earth Syst. Sci., 6, 655–670, 2002. % vor jede Referenz Anctil, F., Perrin, Ch., and Andreassian V.: Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting models, Environ. Modell. Softw., 19, 357–368, 2004. % vor jede Referenz ASCE Task Committee on Application of Artificial Neural Networks in Hydrology: Artificial neural networks in hydrology. I: preliminary concepts, J. Hydrol. Eng., 5, 115–123, 2000a. % vor jede Referenz ASCE Task Committee on Application of Artificial Neural Networks in Hydrology: Artificial neural networks in hydrology II: hydrologic applications, J. Hydrol. Eng., 5, 124–137, 2000b. % vor jede Referenz Astel, A., Tsakovski, S., Barbieri, P., and Simeonov, V.: Comparison of self-organizing maps classification approach with cluster and principal components analysis for large environmental data sets, Water Res., 41(19), 4566–4578, 2007. % vor jede Referenz Bowden, G. J., Dandy G. C., and Maier, H. R.: Input determination for neural network models in water resources applications. Part 1 – background and methodology, J. Hydrol., 301, 75–92, 2005 % vor jede Referenz Cameron, D., Kneale, P., and See, L.: An evaluation of a traditional and a neural net modelling approach to flood forecasting for an upland catchment, Hydrol. Process., 16, 1033–1046, 2002. % vor jede Referenz Campolo, M., Andreussi, P., and Soldati, A.: River flood forecasting with neural network model, Water Resour. Res., 35(4), 1191–1197, 1999. % vor jede Referenz Corzo, G. A. and Solomatine, D. P.: Baseflow separation techniques for modular artificial neural networks modelling in flow forecasting, Hydrolog. Sci. J., 52(3), 491–507, 2007. % vor jede Referenz Coulibaly, P., Bobée, B., and Anctil, F.: Improving extreme hydrologic events forecasting using a new criterion for artificial neural network selection, Hydrol. Process., 15, 1533–1536, 2001. % vor jede Referenz Dawson, C. W. and Wilby, R.: An artificial neural network approach to rainfall-runoff modeling, Hydrolog. Sci. J., 43(1), 47–65, 1998. % vor jede Referenz de Vos, N. J. and Rientjes, T. H. M.: Multi-objective performance comparison of an artificial neural network and a conceptual rainfall-runoff model, Hydrolog. Sci. J., 52(3), 397–413, doi:10.1623/hysj.52.3.397, 2007. % vor jede Referenz de Vos, N. J. and Rientjes, T. H. M.: Multiobjective training of artificial neural networks for rainfall-runoff modeling, Water Resour. Res., 44, W08434, doi:10.1029/2007WR006734, 2008. % vor jede Referenz Fernando, T. M. K. G., Maier, H. R., and Dandy, G. C.: Selection of input variables for data driven models: An average shifted histogram partial mutual information estimator approach, J. Hydrol., 367, 165–176, 2009. % vor jede Referenz Foody, G.: Applications of the self-organising feature map neural network in community data analysis, Ecol. Model., 120, 97–107, 1999. % vor jede Referenz Foresee, F. D. and Hagan, M. T.: Gauss-Newton approximation to Bayesian learning, IEEE IJCNN, New York, 3, 1930–1935, 1997. % vor jede Referenz Furundzic, D.: Application example of neural networks for time series analysis: rainfall-runoff modelling, Signal Process., 64, 383–396, 1998. % vor jede Referenz Georgakakos, K. P., Seo, D., Gupta, H., Schaake, J., and Butts, M. B.: Towards the characterization of streamflow simulation uncertainty through multimodel ensembles, J. Hydrol., 298, 222–241, 2004. % vor jede Referenz Gopakumar R., Takara, K., and James E. J.: Hydrologic Data Exploration and River Flow Forecasting of a Humid Tropical River Basin Using Artificial Neural Networks, Water Resour. Manag., 21(11), 1915–1940, 2007. % vor jede Referenz Gupta, H. V., Sorooshian, S., and Yapo, P. O.: Toward improved calibration of hydrologic models: Multiple and noncommensurable measures of information, Water Resour. Res., 34, 751–764, 1998. % vor jede Referenz Hagan, M. T. and Menhaj, M.: Training feedforward networks with the Marquardt algorithm, IEEE T. Neural Networ., 5(6), 989–993, 1994. % vor jede Referenz Hsu, A. L. and Halgamuge, S. K.: An unsupervised hierarchical dynamic selforganizing approach to cancer class discovery and marker gene identification in microarray data (supplementary information on "Dynamic SOM with hexagonal structure for data mining"), Bioinformatics, 19(16), 2131–2140, 2003. % vor jede Referenz Hsu, K., Gupta, H. V., Gao, X., Sorooshian, S., and Imam, B.: Self-organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysis, Water Resour. Res., 38(12), 1302, doi:10.1029/2001WR000795, 2002. % vor jede Referenz Jain, A., Sudheer, K. P., and Srinivasulu, S.: Identification of physical processes inherent in artificial neural network rainfall runoff models, Hydrol. Process., 18, 571–581, 2004. % vor jede Referenz Jain, A. and Srinivasulu, S.: Integrated approach to model decomposed flow hydrograph using artificial neural network and conceptual techniques, J. Hydrol., 317, 291–306, 2006. % vor jede Referenz Kalteh, A. M., Hjorth, P., and Berndtsson, R.: Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application, Environ. Modell. Softw. 23, 835–845, 2008. % vor jede Referenz Khan,~M. S. and Coulibaly,~P.: Bayesian neural network for rainfall-runoff modeling, Water Resour. Res., 42(7), W07409, doi:10.1029/2005WR003971, 2006. % vor jede Referenz Kohonen, T.: Self-organized formation of topologically correct feature maps, Biol. Cybern., 43, 59–69, 1982. % vor jede Referenz Kohonen, T.: Self-Organizing Maps (third edn.), Springer, Berlin, Germany, 2001. % vor jede Referenz Legates, D.R. and McCabe, G.J.: Evaluating the use of `goodness-of-fit' measures in hydrologic and hydroclimatic model validation, Water Resour. Res., 35, 233-241, 1999. % vor jede Referenz Madsen, H.: Automatic calibration of a conceptual rainfall-runoff model using multiple objectives, J. Hydrol., 235, 267–288, 2000. % vor jede Referenz Maier, H. and Dandy, G.: Neural networks for the prediction and forecasting of water resources variables: A review of modeling issues and applications, Environ. Modell. Softw., 15(1), 101–104, 2000. % vor jede Referenz Mangiameli, P., Chen, S. K., and West, D.: A comparison of SOM neural network and hierarchical clustering methods, Eur. J. Oper. Res., 93, 402–417, 1996. % vor jede Referenz Minns, A. W. and Hall, M. J.: Artificial neural networks as rainfall runoff models, Hydrolog. Sci. J., 41, 399–417, 1996. % vor jede Referenz Moradkhani, H., Hsu, K., Gupta, H. V., and Sorooshian, S: Improved streamflow forecasting using self-organizing radial basis function artificial neural networks, J. Hydrol., 295, 246–262, 2004. % vor jede Referenz Parasuraman, K. and Elshorbagy, A.: Cluster-based hydrologic prediction using genetic-algorithm trained neural networks, J. Hydrol. Eng., 12(1), 52–62, 2007. % vor jede Referenz Shamseldin, A. Y., Nasr, A. E., and O'Connor, K. M.: Comparison of different forms of the Multi-layer Feed-Forward Neural Network method used for river flow forecasting, Hydrol. Earth Syst. Sci., 6, 671–684, 2002. % vor jede Referenz Shamseldin, A. Y., O'Connor, K. M., and Liang, G. C.,: Methods for combining the outputs of different rainfall-runoff rodels, J. Hydrol., 197, 203–229, 1997. % vor jede Referenz Shamseldin, A. Y., O'Connor, K. M., and Nasr, A. E.: A comparative study of three neural network forecast combination methods for simulated river flows of different rainfall-runoff models, Hydrolog. Sci. J., 52(5), 896–916, 2007. natural phenomena, Neural Networks, 19, 215–224, 2006. % vor jede Referenz Shirazi, J. and Menhaj, M. B.: A SOM Based 2500-Isolated-Farsi-Word Speech Recognizer, in: ICANN 2005, LNCS 3696, edited by: Duch, W., Kacprzyk, J., Oja, E., and Zadrony, S., Springer-Verlag Berlin Heidelberg, 589–595, 2005. % vor jede Referenz Solomatine, D. P. and Siek, M. B.: Modular learning models in forecasting % vor jede Referenz Solomatine, D. P. and Dulal, K. N.: Model trees as an alternative to neural networks in rainfall-runoff modelling, Hydrolog. Sci. J., 48(3), 399–411, 2003. % vor jede Referenz Srivastav, R. K., Sudheer, K. P., and Chaubey, I.: A simplified approach to quantifying predictive and parametric uncertainty in artificial neural network hydrologic models, Water Resour. Res., 23(10), W10407, doi:10.1029/2006WR005352, 2007. % vor jede Referenz Tang, Y., Reed, P., and Wagener, T.: How effective and efficient are multiobjective evolutionary algorithms at hydrologic model calibration?, Hydrol. Earth Syst. Sci., 10, 289–307, 2006. % vor jede Referenz Toth, E. and Brath, A.: Multistep ahead streamflow forecasting: Role of calibration data in conceptual and neural network modeling, Water Resour. Res., 43, W11405, doi:10.1029/2006WR005383, 2007. % vor jede Referenz Van der Voort, M., Dougherty, M., and Watson, S.: Combining Kohonen maps with ARIMA time series models to forecast traffic flow, Transport. Res., C4(5), 307–318, 1996. % vor jede Referenz Vrugt, J. A., Gupta, H. V., Bastidas, L. A., Bouten, W., and Sorooshian, S.: Effective and efficient algorithm for multiobjective optimization of hydrologic models, Water Resour. Res., 39, 1–19, 2003. % vor jede Referenz Wang, W., Gelder, P., Vrijling, J. K., and Ma, J.: Forecasting daily streamflow using hybrid ANN models, J. Hydrol., 324(1), 383–399, 2006. % vor jede Referenz Wheater, H. S., Jakeman, A. J., and Beven, K. J.: Progress and directions in rainfall-runoff modelling, in: Modelling change in environmental systems, edited by: Jakeman, A. J., Beck, M. B., and McAleer, M. J., Wiley, Chichester, 101–132, 1993. % vor jede Referenz World Meteorological Organization: Simulated real-time intercomparison of hydrological models, WMO Publications, Geneva, Swiss, 1992. % vor jede Referenz Young, P. C.: Advances in real-time flood forecasting, Philos. T. R. Soc. Lond., 360, 1433–1450, 2002. % vor jede Referenz Zhang, B. and Govindaraju, S.: Prediction of Watershed Runoff using Bayesian Concepts and Modular Neural Networks, Water Resour. Res., 36(3), 753–762, 2000.