Hydrology and Earth System Sciences www.hydrol-earth-syst-sci.net 1027-5606 1607-7938 13 9 2009 10.5194/hess-13-1619-2009 http://www.hydrol-earth-syst-sci.net/13/1619/2009/ http://www.hydrol-earth-syst-sci.net/13/1619/2009/hess-13-1619-2009.html http://www.hydrol-earth-syst-sci.net/13/1619/2009/hess-13-1619-2009.pdf 1619 1634 2009-09-11 Combining semi-distributed process-based and data-driven models in flow simulation: a case study of the Meuse river basin G. A. Corzo corzogac@yahoo.es D. P. Solomatine Hidayat M. de Wit M. Werner S. Uhlenbrook R. K. Price Department of Water Engineering and Hydroinformatics, UNESCO-IHE, Westvest 7, 2611 AX Delft, The Netherlands Deltares (Delft|Hydraulics), Rotterdamseweg 185, Delft, The Netherlands Water Resources Section, Delft University of Technology, Delft, The Netherlands Vrije Universiteit Amsterdam, Faculteit der Aardwetenschappen, Amsterdam, The Netherlands Centre for Limnology, Indonesian Institute of Sciences, Cibinong, Indonesia One of the challenges in river flow simulation modelling is increasing the accuracy of forecasts. This paper explores the complementary use of data-driven models, e.g. artificial neural networks (ANN) to improve the flow simulation accuracy of a semi-distributed process-based model. The IHMS-HBV model of the Meuse river basin is used in this research. Two schemes are tested. The first one explores the replacement of sub-basin models by data-driven models. The second scheme is based on the replacement of the Muskingum-Cunge routing model, which integrates the multiple sub-basin models, by an ANN. The results show that: (1) after a step-wise spatial replacement of sub-basin conceptual models by ANNs it is possible to increase the accuracy of the overall basin model; (2) there are time periods when low and high flow conditions are better represented by ANNs; and (3) the improvement in terms of RMSE obtained by using ANN for routing is greater than that when using sub-basin replacements. It can be concluded that the presented two schemes can improve the performance of process-based models in the context of flow forecasting. 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. Anctil, F. and Tapé, D G.: An exploration of artificial neural network rainfall-runoff forecasting combined with wavelet decomposition, J. Environ. Eng. Sci, 3(1), S121–S128, 2004. ASCE: Task Committee on Application of Artificial Neural Networks in Hydrology, Artificial Neural Networks in Hydrology. II: Hydrologic Application, J. Hydrol. Eng., 5, 124–136, 2000. Ashagrie, A. G., de Laat, P. J., de Wit, M. J., Tu, M., and Uhlenbrook, S.: Detecting the influence of land use changes on discharges and floods in the Meuse River Basin - the predictive power of a ninety-year rainfall-runoff relation?, Hydrol. Earth Syst. Sci., 10, 691–701, 2006. Berger, H. E J.: Flow Forecasting for the River Meuse, Technische Universiteit Delft, 1992. Bergström, S. and Forsman, A.: Development of a conceptual deterministic rainfall-runoff model, Nord. Hydrol., 4, 147–170, 1973. Booij, M J.: Modelling the effects of spatial and temporal resolution of rainfall and basin model on extreme river discharge, Hydrolog. Sci. J., 47, 307–320, 2002. Booij, M J.: Impact of climate change on river flooding assessed with different spatial model resolutions, J. Hydrol., 303, 176–198, 2005. 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. Brath, A., Montanari, A., and Toth, E.: Neural networks and non-parametric methods for improving real-time flood forecasting through conceptual hydrological models, Hydrol. Earth Syst. Sci., 6, 627–639, 2002. Chen, J. and Adams, B J.: Integration of artificial neural networks with conceptual models in rainfall-runoff modeling, J. Hydrol., 318, 232–249, 2006. Corzo, G. and Solomatine, D.: Knowledge-based modularization and global optimization of artificial neural network models in hydrological forecasting, Neural Networks, 20, 528–536, 2007a. Corzo, G A. and Solomatine, D P.: Baseflow separation techniques for modular artificial neural networks modelling in flow forecasting, Hydrolog. Sci. J., 52, 491–507, 2007b. Dawson, C W., See, L M., Abrahart, R J., Wilby, R L., Shamseldin, A Y., Anctil, F., Belbachir, A N., Bowden, G., Dandy, G., and Lauzon, N.: A comparative study of artificial neural network techniques for river stage forecasting, in: Proceedings of IEEE International Joint Conference on Neural Networks, Montreal, Que., 4, 2666–2670, 2005. de Wit, M. J. M., Peeters, H. A., Gastaud, P. H., Dewil, P., Maeghe, K., and Baumgart, J.: Floods in the Meuse basin: event descriptions and an international view on ongoing measures, International Journal of River Basin Management, 5, 279-292, 2007a. de~Wit, M. J M., van~den Hurk, B., Warmerdam, P. M M., Torfs, P., Roulin, E., and van Deursen, W. P A.: Impact of climate change on low-flows in the river Meuse, 2007b. Dibike, Y., Velickov, S., Solomatine, D., and Abbott, M.: Model Induction with Support Vector Machines: Introduction and Applications, J. Comput. Civil Eng., 15, 208–216, 2001. Dibike, Y B. and Abbott, M B.: Application of artificial neural networks to the simulation of a two dimensional flow, J. Hydraul. Res., 37, 435–446, 1999. Diermansen, F.: Physically based modelling of rainfall-runoff processes, Ph.D. Thesis – TuDelft, 123–150, 2001. Fenicia, F., Solomatine, D. P., Savenije, H. H. G., and Matgen, P.: Soft combination of local models in a multi-objective framework, Hydrol. Earth Syst. Sci., 11, 1797–1809, 2007. Fogelberg, S., Arheimer, B., Venohr, M., and Behrendt, H.: HBV modeling in several European countries, Proceedings of Nordic Hydrologic conference, 2004. Haykin, S.: Neural networks: a comprehensive foundation, Prentice Hall, second edn., 1999. Kachroo, R.: River Flow Forecasting. Part 2. Applications of a conceptual model, J. Hydrol., 7(133), 141–178, 1992. Kachroo, R. and Liang, G.: River Flow Forecasting. Part 2. Algebraic Development of Linear Modelling Techniques, J. Hydrol., 133, 17–40, 1992. Leander, R. and Buishand, T A.: Resampling of regional climate model output for the simulation of extreme river flows, 2007. Levenberg, K.: A method for the solution of certain problems in least squares, Quart. Appl. Math, 2, 164–168, 1944. Linde, A T., Hurkans, R., Aerts, J., and Dolman, H.: Comparing model performance of the HBV and VIC models in the Rhine basin, in: Symposium HS2004 at IUGG2007, IAHS, Perugia, 278–285, 2007. Lindström, G., Johansson, B., Persson, M., Gardelin, M., and Bergtröm, S.: Development and test of the distributed HBV-96 hydrological model, J. Hydrol., 201, 272–228, 1997. Marquardt, D.: An algorithm for least-squares estimation of nonlinear parameters, SIAM J. Appl. Math., 11, 431–441, 1963. Moore, R.: Flood forecasting techniques, Tech. rep., I. WMO/UNDP Regional Training seminar on flood forecasting, Bangkok, Thailand, 1983. NERC: Flood Studies Report, Vol. 5: Flood Routing Studies., Tech. rep., Natural Environment Research Council, London, 1975. Nilsson, P., Uvo, C B., and Berndtsson, R.: Monthly runoff simulation: Comparing and combining conceptual and neural networks models, J. Hydrol., 321, 344–363, 2006. Ponce, V M., Lohani, A K., and Scheyhing, C.: Analytical verification of Muskingum-Cunge routing, J. Hydrol., 174, 235–241, \doi10.1016/0022-1694(95)02765-3, http://www.sciencedirect.com/science/article/B6V6C-3VW173F-3/2/842b6f3ce5b836f6b48ebf8347774b88, 1996. Schreider, S., Jakeman, A., Dyer, B., and Francis, R.: A combined deterministic and self-adaptive stochastic algorithm for streamflow forecasting with application to catchments of the Upper Murray Basin, Australia, Environ. Modell. Softw., 12, 93–104, 1997. Seibert, J.: Estimation of parameter uncertainty in the HBV model, Nord. Hydrol., 28, 247–262, 1997. Solomatine, D P. and Dulal, K N.: Model tree as an alternative to neural network in rainfall-runoff modelling, Hydrolog. Sci. J., 48, 399–411, 2003. Solomatine, D P. and Price, R K.: Innovative approaches to flood forecasting using data driven and hybrid modelling, in: 6th International Conference on Hydroinformatics, edited by: Liong, Phoon, and Babovic, 1639–1646, World Scientific Publishing Company, Singapore, 1639–1647, 2004. Stein, M.: Interpolation of Spatial Data: Some Theory for Kriging, Springer, 1999. Toth, E.: Classification of hydro-meteorological conditions and multiple artificial neural networks for streamflow forecasting, Hydrol. Earth Syst. Sci. Discuss., 6, 897–919, 2009. 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. Tu, M., Hall, M., and Laat, P D.: Detection of long-term changes in precipitation and discharge in the Meuse, GIS and remote sensing in Hydrology, Water resources and enviromental – Proceedings of the international conference of the ICGRHWE held at the Three Gorges Dam, China, Septembre 2003, IAHS Publ. 289, 2004. van Deursen, W.: Calibration HBV model Meuse, Tech. rep., Carthago Consultancy, 2004. Witten, I H. and Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, Morgan Kaufmann, 2000.