HESS Hydrology and Earth System Sciences HESS Hydrol. Earth Syst. Sci. 1607-7938 Copernicus Publications Göttingen, Germany 10.5194/hess-10-485-2006 Clustering of heterogeneous precipitation fields for the assessment and possible improvement of lumped neural network models for streamflow forecasts Lauzon N. 1 Anctil F. 2 Baxter C. W. 3 Golder Associates, Burnaby, BC, Canada Département de génie civil, Pavillon Pouliot, Université Laval, Québec, G1K 7P4, Canada HYDRANNT Consulting Inc., Port Coquitlam, Canada 07 07 2006 10 4 485 494 Copyright: © 2006 N. Lauzon et al. 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/10/485/2006/hess-10-485-2006.html The full text article is available as a PDF file from https://hess.copernicus.org/articles/10/485/2006/hess-10-485-2006.pdf

This work addresses the issue of better considering the heterogeneity of precipitation fields within lumped rainfall-runoff models where only areal mean precipitation is usually used as an input. A method using a Kohonen neural network is proposed for the clustering of precipitation fields. The evaluation and improvement of the performance of a lumped rainfall-runoff model for one-day ahead predictions is then established based on this clustering. Multilayer perceptron neural networks are employed as lumped rainfall-runoff models. The Bas-en-Basset watershed in France, which is equipped with 23 rain gauges with data for a 21-year period, is employed as the application case. The results demonstrate the relevance of the proposed clustering method, which produces groups of precipitation fields that are in agreement with the global climatological features affecting the region, as well as with the topographic constraints of the watershed (i.e., orography). The strengths and weaknesses of the rainfall-runoff models are highlighted by the analysis of their performance vis-à-vis the clustering of precipitation fields. The results also show the capability of multilayer perceptron neural networks to account for the heterogeneity of precipitation, even when built as lumped rainfall-runoff models.

 References Anctil, F., Perrin, C., and Andréassian, V.: ANN output updating of lumped conceptual rainfall-runoff forecasting models, J. Am. Water Resour. Assoc., 39(5), 1269–1279, 2003. Anctil, F., Perrin, P., and Andréassian, V.: Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting models, Environ. Modelling and Software, 19, 357–368, 2004a. Anctil, F., Michel, C., Perrin, C., and Andréassian, V.: A soil moisture index as an auxiliary ANN input for stream flow prediction, J. Hydrol., 286, 155–167, 2004b. ASCE: Artificial neural networks in hydrology – I: Preliminary concepts, ASCE J. Hydrol. Eng., 5(2), 115–123, 2000a. ASCE: Artificial neural networks in hydrology – II: Hydrologic applications, ASCE J. Hydrol. Eng., 5(2), 124–137, 2000b. Bardossy, A. and Plate, E. J.: Space-time model for daily rainfall using atmospheric circulation patterns, Water Resour. Res., 28(5), 1247–1259, 1992. Bardossy, A., Muster, H. Duckstein, L., and Bogardi, I.: Knowledge-based classification of circulation patterns for stochastic precipitation modelling, Proc. Stochastic and Statist. Methods in Hydrol. Environ. Eng., Waterloo, Ontario, Canada, 21–23 June 1993, 1994. Bechtold, P. and Bazile, E.: The 12–13 November 1999 flash flood in southern France, Atmos. Res., 56, 171–189, 2001. Benzie, R., Deidda, R., and Marrocu, M.: Characterization of temperature and precipitation fields over Sardinia with principal component analysis and singular spectrum analysis, Int. J. Climatol., 17(11), 1231–1262, 1997. Bowden, G. J., Maier, H. R., and Dandy, G. C.: Optimal division of data for neural network models in water resources applications, Water Resour. Res., 38(2), 2.1–2.11, 2002. Brath, A., Montanari, A., and Toth, E.: Neural networks and non-parametric methods for improving realtime flood forecasting through conceptual hydrological models, Hydrol. Earth Syst. Sci., 6(4), 627–640, 2002. Breiman, L.: Bagging predictors, Machine Learning, 24(2), 123–140, 1996. Breiman, L.: Using iterated bagging to debias regressions, Machine Learning, 45, 262–277, 2001. Cannon, A. J. and Whitfield, P. H.: Downscaling recent streamflow conditions in British Columbia, Canada using ensemble neural network models, J. Hydrol., 259, 136–151, 2002. Coulibaly, P., Anctil, F., and Bobée, B.: Prévision hydrologique par réseaux de neurones artificiels: état de l'art, Can. J. Civil Eng., 26, 293–304, 1999. Cybenko, G.: Approximation by superposition of a sigmoidal function, Mathematics of Control, Signals and Systems, 2, 303–314, 1989. Dawdy, D. R. and Bergman, J. M.: Effect of rainfall variability on streamflow simulation, Water Resour. Res., 5(3), 958–966, 1969. Dillon, W. R. and Goldstein, M.: Multivariate analysis: Methods and applications, John Wiley & Sons, New York, NY, USA, 1984. Doswell III, C. A., Ramis, C., Romero, R., and Alonso, S.: A diagnostic study of three heavy precipitation episodes in the western Mediterranean, Weather Forecast, 13, 102–124, 1998. Faures, J. M., Goodrich, D. C., Woolhiser, D. A., and Sorooshian, S.: Impact of small-scale rainfall variability on runoff simulation, J. Hydrol., 173, 309–326, 1995. Foresee, F. D. and Hagan, M. T.: Gauss-Newton approximation to Bayesian learning, Proceedings, 1997 IEEE Int. Conf. Neural Networks, Houston, TX, 3, 1930–1935, 1997. Gotz, R., Steiner, B., Sievers, S., Friesel, P., Roch, K., Schworer, R., and Haag, F.: Dioxin, dioxin-like PCBS and organotin compounds in the River Elbe and the Hamburg Harbour: Identification of sources, Water Sci. Technol., 37(6–7), 207–215, 1998. Hagan, M. T. and Menhaj, M.: Training feedforward networks with the Marquardt algorithm, IEEE Trans. Neural Networks, 5, 989–993, 1994. Hall, M. J. and Minns, A. W.: The classification of hydrologically homogeneous regions, Hydrol. Sci. J., 44(5), 693–704, 1999. Hornik, K., Stinchcombe, M., and White, H.: Multilayer feedforward networks are universal approximators, Neural Networks, 2, 359–366, 1989. Hughes, J. P., Lettenmaier, D. P., and Guttorp, P.: A stochastic approach for assessing the effects of changes in synoptic circulation patterns on gauge precipitation, Water Resour. Res., 29(10), 3303–3315, 1993. Kitadinis, P. K. and Bras, R. L.: Real-time forecasting with a conceptual hydrologic model: 2. Applications and results, Water Resour. Res., 16(6), 1034–1044, 1980. Kohonen, T.: The self-organizing map, Proc. IEEE, 79(9), 1464–1480, 1990. Lauzon, N.: Water Resources Data Quality Assessment and Description of Natural Processes Using Artificial Intelligence Techniques, Ph.D. Thesis, The University of British Columbia, Department of Civil Engineering, Vancouver, BC, Canada, 2003. Liong, S. Y., Lim, W. H., Kojiri, T., and Hori, T.: Advance flood forecasting for flood stricken Bangladesh with a fuzzy reasoning method, Hydrol. Processes, 14(3), 431–448, 2000. MacKay, D. J. C.: Bayesian interpolation, Neural Computation, 4(3), 415–447, 1992. Maier, H. R. and Dandy, G. C.: Neural networks for prediction and forecasting of water resources variables: Review of modelling issues and applications, Environ. Modelling and Software, 15, 101–124, 2000. Naden, P. S.: Spatial variability in flood estimation for large catchments: The exploitation of channel network structure, Hydrol. Sci. J., 37(1), 53–71, 1992. Ozelkan, E. C., Ni, F., and Duckstein, L.: Relationship between Monthly Atmospheric Circulation Patterns and Precipitation: Fuzzy Logic and Regression Approaches, Water Resour. Res., 32(7), 2097–2103, 1996. Schnur, R. and Lettenmaier, D. P.: A case study of statistical downscaling in Australia using weather classification by recursive partitioning, J. Hydrol., 212–213(1–4), 362–379, 1998. Schoof, J. T. and Pryor, S. C.: Downscaling temperature and precipitation: A comparison of regression-based methods and artificial neural networks, Int. J. Climatol., 21(7), 773–790, 2001. Sénési, S., Bourgeault, P., Chèze, J.-L., Cosentino, P., and Thepenier, R.-M.: The Vaison-La-Romaine flash flood: Mesoscale analysis and predictability issues, Weather Forecast, 11(4), 417–442, 1996. Siew-Yan-Yu, T. O., Rousselle, J., Jacques, G., and Nguyen, V. T. V.: Régionalisation du régime des précipitations dans la région des Bois-francs et de l'Estrie par l'analyse en composantes principales, Can. J. Civil Eng., 25(6), 1050–1058, 1998. Singh, V. P. and Woolhiser, D. A.: Mathematical modelling of watershed hydrology, ASCE J. Hydrol. Eng., 7(4), 270–292, 2002. Tan, Y. and Van Cauwenberghe, A.: Neural-network-based d-step-ahead predictors for nonlinear systems with time delay, Eng. Applications of Artificial Intelligence, 12, 21–35, 1999. Toth, E., Brath, A. and Montanari, A.: A comparison of short-term rainfall prediction models for real-time flood forecasting, J. Hydrol., 239, 132–147, 2000. Wilson, C. B., Valdes, J. B., and Rodriguez-Iturbe, I.: On the influence of spatial distribution of rainfall on storm runoff, Water Resour. Res., 15(1), 321–328, 1979. Zorita, E. and Storch, H. V.: The analog method as a simple statistical downscaling technique: Comparison with more complicated methods, J. Climate, 12(8), 2474–2489, 1999. Zorita, E., Hughes, J. P., Lettenmaier, D. P., and Storch, H. V.: Stochastic characterization or regional circulation patterns for climate models diagnosis and estimation of local precipitation, J. Climate, 8(5), 1023–1042, 1995.