HESS Hydrology and Earth System Sciences HESS Hydrol. Earth Syst. Sci. 1607-7938 Copernicus Publications Göttingen, Germany 10.5194/hess-10-603-2006 Optimising training data for ANNs with Genetic Algorithms Kamp R. G. 1 2 Savenije H. H. G. 1 Section of Water Resources, Delft University of Technology, Delft, The Netherlands MX.Systems B.V., Rijswijk, The Netherlands 07 09 2006 10 4 603 608 Copyright: © 2006 R. G. Kamp 2006 This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Generic License. To view a copy of this licence, visit https://creativecommons.org/licenses/by-nc-sa/2.5/ This article is available from https://hess.copernicus.org/articles/10/603/2006/hess-10-603-2006.html The full text article is available as a PDF file from https://hess.copernicus.org/articles/10/603/2006/hess-10-603-2006.pdf

Artificial Neural Networks (ANNs) have proved to be good modelling tools in hydrology for rainfall-runoff modelling and hydraulic flow modelling. Representative datasets are necessary for the training phase in which the ANN learns the model's input-output relations. Good and representative training data is not always available. In this publication Genetic Algorithms (GA) are used to optimise training datasets. The approach is tested with an existing hydraulic model in The Netherlands. An initial trainnig dataset is used for training the ANN. After optimisation with a GA of the training dataset the ANN produced more accurate model results.

 References Anctil, F. and Lauzon, N.: Generalisation for neural networks through data sampling and training procedures with applications to streamflow predictions, Hydrol. Earth Syst. Sci., 8, 940–958, 2004. Babovic, V. and Keijzer, M.: Genetic programming as a model induction engine, J. Hydroinformatics, 2(1), 35–60, 2000. Babovic, V. and Abbott, M. B.: The evolution of equations from hydraulic data: Part I – Theory, J. Hydraulic Res., 35, 3, 1–14, 1997. Bowden, G. J., Holger, R. M., and Dandy, G. C.: Optimal division of data for neural network models in water resources applications, Water Resour. Res., 38(2), 1–11, 2002. Dibike, Y. B.: Model Induction from Data: Towards the next generation of computational engines in hydraulics and hydrology, IHE Delft, Delft, 2002. Doan, C. D., Liong, S. Y., and Karunasinghe, D. S. K.: Derivation of effective and efficient dataset with subtractive clustering method and genetic algorithm, J. Hydroinformatics, 7, 219–233, 2005. Feyen, L., Vázquez, R., Christiaens, K., Sels, O., and Feyen, J.: Application of a distributed physically-based hydrological model to a medium size catchment, Hydrol. Earth Syst. Sci., 4, 47–63, 2000. Goldberg, D. E.: Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley Pub. Co., 1989. Hagan, T., Demuth, H. B., and Beale, M. H.: Neural Network Design, PWS Pub. Co., Boston, 1996. Haykin, S.: Neural Networks, a comprehensive foundation, Prentice Hall, New Jersey, 1999. Houck, C., Joines, J., and Kay, M.: A genetic algorithm for function optimization: a MATLAB implementation, NCSU-IE TR, 1995. Jolankai, G.: The Tisza River Project, Real-life scale integrated catchment models for supporting water- and environmental management decisions, Section 6 Report, Hungary, 2004. Minns, A. W. and Hall, M. J.: Artificial neural networks as rainfall-runoff models, Hydrol. Sci. J., 41(3), 399–417, 1996. Minns, A. W.: Subsymbolic methods for data mining in hydraulic engineering, J. Hydroinformatics, 2, 3–13, 2000. Price, R. K., Samedov, J. N., and Solomatine, D. P.: An artificial neural network model of a generalised channel network, Proc. 3rd Int. conf. Hydroinformatics, Copenhagen, 1998. Shannon, C., Moore, D., Keys, K., Fomenkov, M., Huffaker, B., and Claffy, K.: The internet measurement data catalog, Computer communication review, 35, 97–100, 2005. Shrestha, R. G., Theobald, S., and Nestmann, F.: Simulation of flood flow in a river system using artificial neural networks, Hydrol. Earth Syst. Sci., 9, 313–321, Solomatine, D. P. and Dulal, K. N.: Model trees as an alternative to neural networks in trainfall-runoff modelling, Hydrol. Sci. J., 48, 3, 399–411, 2003. de Vos, N. J. and Rientjes, T. H. M.: Constraints of artificial neural networks for rainfall-runoff modelling: trade-offs in hydrological state representation and model evaluation, Hydrol. Earth Syst. Sci., 9, 111–126, 2005. Whigham, P. A. and Crapper, P. F.: Modelling rainfall-runoff using genetic programming, Mathematical and Computer Modelling, 33(6–7), 707–721, 2001. Zijderveld, A.: Neural network design strategies and modelling in hydroinformatics, Ph.D. thesis, Delft University of Technology, Delft, 2003.