Hydrology and Earth System Sciences www.hydrol-earth-syst-sci.net 1027-5606 1607-7938 13 7 2009 10.5194/hess-13-1235-2009 http://www.hydrol-earth-syst-sci.net/13/1235/2009/ http://www.hydrol-earth-syst-sci.net/13/1235/2009/hess-13-1235-2009.html http://www.hydrol-earth-syst-sci.net/13/1235/2009/hess-13-1235-2009.pdf 1235 1248 2009-07-21 A novel approach to parameter uncertainty analysis of hydrological models using neural networks D. L. Shrestha d.shrestha@unesco-ihe.org N. Kayastha D. P. Solomatine UNESCO-IHE Institute for Water Education, Delft, The Netherlands MULTI Disciplinary Consultants Ltd, Kathmandu, Nepal Water Resources Section, Delft University of Technology, The Netherlands In this study, a methodology has been developed to emulate a time consuming Monte Carlo (MC) simulation by using an Artificial Neural Network (ANN) for the assessment of model parametric uncertainty. First, MC simulation of a given process model is run. Then an ANN is trained to approximate the functional relationships between the input variables of the process model and the synthetic uncertainty descriptors estimated from the MC realizations. The trained ANN model encapsulates the underlying characteristics of the parameter uncertainty and can be used to predict uncertainty descriptors for the new data vectors. This approach was validated by comparing the uncertainty descriptors in the verification data set with those obtained by the MC simulation. The method is applied to estimate the parameter uncertainty of a lumped conceptual hydrological model, HBV, for the Brue catchment in the United Kingdom. The results are quite promising as the prediction intervals estimated by the ANN are reasonably accurate. The proposed techniques could be useful in real time applications when it is not practicable to run a large number of simulations for complex hydrological models and when the forecast lead time is very short. Abebe, A. J. and Price, R. K.: Managing uncertainty in hydrological models using complementary models, Hydrol. Sci. J., 48, 679–692, 2003. Abebe, A. J. and Price, R. K.: Forecasting surge prediction accuracy on the Dutch coast using neural networks, in: Proceedings of the 6th International Conference on Hydroinformatics: Singapore, 21–24 June 2004, World Scientific, 2004. 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. Proc., 14, 2157-2172, 2000. Ajami, N. K., Duan, Q., and Sorooshian, S.: An integrated hydrologic Bayesian multimodel combination framework: Confronting input, parameter, and model structural uncertainty in hydrologic prediction, Water Resour. Res., 43, W01403, doi:10.1029/2005WR004745, 2007. Allen, R. G., Pereisa, L. S., Raes, D., and Smith, M.: Crop evapotranspiration, guideline for computing crop water requirements, FAO, Irrigation and drainage paper, 56, 300~pp., 1998. Ballio, F. and Guadagnini, A.: Convergence assessment of numerical Monte Carlo simulations in groundwater hydrology, Water Resour. Res., 40, W04603, doi:10.1029/2003WR002876, 2004. Beven, K. and Binley, A.: The future of distributed models: Model calibration and uncertainty prediction, Hydrol. Proc., 6, 279–298, doi:10.1002/hyp.3360060305, 1992. Beven, K. and Freer, J.: Equifinality, data assimilation, and uncertainty estimation in mechanistic modelling of complex environmental systems using the GLUE methodology, J. Hydrol., 249, 11–29, 2001. Bishop, C. M.: Neural networks for pattern recognition, Clarendon-Press, Oxford, 504~pp., 1995. Blasone, R. S., Vrugt, J. A., Madsen, H., Rosbjerg, D., Robinson, B. A., and Zyvoloski, G. A.: Generalized likelihood uncertainty estimation (GLUE) using adaptive Markov chain Monte Carlo sampling, Adv. Water Resour., 31, 630–648, doi:10.1016/j.advwatres.2007.12.003, 2008. 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, 93-107, doi:10.1016/j.jhydrol.2004.06.020, 2005. Braun, L. N. and Renner, C. B.: Application of a conceptual runoff model in different physiographic regions of Switzerland, Hydrol. Sci. J., 37, 217–232, 1992. Dawson, C. W. and Wilby, R. L.: Hydrological modelling using artificial neural networks, Prog. Phys. Geogr., 25, 80–108, doi:10.1177/030913330102500104, 2001. Dibike, Y. B., Velickov, S., Solomatine, D. P., and Abbott, M. B.: Model induction with support vector machines: Introduction and applications, J. Comput. Civil Eng., 15, 208–216, 2001. Fraser, A. M. and Swinney, H. L.: Independent coordinates for strange attractors from mutual information, Phys. Rev. A, 33(2), 1134–1140, 1986. Freer, J., Beven, K., and Ambroise, B.: Bayesian estimation of uncertainty in runoff prediction and the value of data: An application of the GLUE approach, Water Resour. Res., 32, 2161–2173, 1996. Georgakakos, K., Seo, D.-J., Gupta, H. V, Schaake, J., and Butts, M. M.: Towards the characterization of streamflow simulation uncertainty through multimodel ensembles, J. Hydrol., 298, 222–241, doi:10.1016/j.jhydrol.2004.03.037, 2004. Govindaraju, R. S. and Rao, A. R.: Artificial neural networks in hydrology, Kluwer Academic Publishers, Amsterdam, 348~pp., 2000. Guyon, I. and Elisseeff, A.: An introduction to variable and feature selection, J. Mach. Learn. Res., 3, 1157–1182, 2003. Haario, H., Laine, M., Mira, A., and Saksman, E.: DRAM: efficient adaptive MCMC, Stat. Comput., 16, 339–354, doi:10.1007/s11222-006-9438-0, 2006. Harr, M.: Probabilistic estimates for multivariate analyses, Appl. Math. Model., 13, 313–318, doi:10.1016/0307-904X(89)90075-9, 1989. Haykin, S.: Neural networks: A comprehensive foundation. Prentice-Hall, Upper Saddle River, NJ, USA, 1999. Jacquin, A. P. and Shamseldin, A. Y.: Development of rainfall-runoff models using Takagi-Sugeno fuzzy inference systems, J. Hydrol., 329(1–2), 154–173, 2006. Kavetski, D., Kuczera, G., and Franks, S. W.: Bayesian analysis of input uncertainty in hydrological modeling: 1. Theory, Water Resour. Res., 42, W03407, doi:10.1029/2005WR004368, 2006. Klir, G. J. and Yuan, B.: Fuzzy sets, fuzzy logic, and fuzzy systems: selected papers by: Zadeh, L. A., World Scientific Publishing Co. Inc., River Edge, NJ, USA, 840~pp., 1996. \bibitem[Khan and Coulibaly (2006)] khan2006bnn Khan, M. S. and Coulibaly, P.: Bayesian neural network for rainfall-runoff modeling, Water Resour. Res., 42, W07409, doi:10.1029/2005WR003971, 2006. Khu, S.-T. and Werner, M. G. F.: Reduction of Monte-Carlo simulation runs for uncertainty estimation in hydrological modelling, Hydrol. Earth Syst. Sci., 7, 680–692, 2003. Kuczera, G. and Parent, E.: Monte Carlo assessment of parameter uncertainty in conceptual catchment models: the Metropolis algorithm, J. Hydrol., 211, 69–85, 1998. Kuczera, G., Kavetski, D., Franks, S. W., and Thyer, M.: Towards a Bayesian total error analysis of conceptual rainfall-runoff models: Characterising model error using storm-dependent parameters, J. Hydrol., 331, 161–177, doi:10.1016/j.jhydrol.2006.05.010, 2006. Kunstmann, H., Kinzelbach, W., and Siegfried, T.: Conditional first-order second-moment method and its application to the quantification of uncertainty in groundwater modeling, Water Resour. Res., 38, 1035, doi:10.1029/2000WR000022, 2002. Li, G., Azarm, S., Farhang-Mehr, A., and Diaz, A.: Approximation of multiresponse deterministic engineering simulations: a dependent metamodeling approach, Struct. Multidiscip. O., 31, 260–269, doi:10.1007/s00158-005-0574-5, 2006. Lindström, G., Johansson, B., Persson, M., Gardelin, M., and Bergström, S.: Development and test of the distributed HBV-96 hydrological model, J. Hydrol., 201, 272–288, 1997. Maier, H. R. and Dandy, G. C.: Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications, Environ. Modell. Softw., 15, 101–124, 2000. Mantovan, P. and Todini, E.: Hydrological forecasting uncertainty assessment: Incoherence of the GLUE methodology, J. Hydrol., 330, 368–381, doi:10.1016/j.jhydrol.2006.04.046, 2006. Maskey, S., Guinot, V., and Price, R. K.: Treatment of precipitation uncertainty in rainfall-runoff modelling: a fuzzy set approach, Adv. Water Resour., 27, 889–898, 2004. McKay, M. D., Conover, W. J., and Beckman, R. J.: A comparison of three methods for selecting values of input variables in the analysis of output from a computer code, Technometrics, 21, 239–245, 1979. Melching, C. S.: An improved-first-order reliability approach for assessing uncertainties in hydrologic modeling, J. Hydrol., 132, 157–177, 1992. Melching, C. S.: Reliability estimation in computer models of watershed hydrology, Water Res. Publ., 69–118, 1995. Minns, A. W. and Hall, M. J.: Artificial neural networks as rainfall-runoff models, Hydrol. Sci. J., 41, 399–417, 1996. Montanari, A. and Brath, A.: A stochastic approach for assessing the uncertainty of rainfall-runoff simulations, Water Resour. Res., 40, W01106, doi:10.1029/2003WR002540, 2004. Montanari, A.: Large sample behaviors of the generalized likelihood uncertainty estimation (GLUE) in assessing the uncertainty of rainfall-runoff simulations, Water Resour. Res., 41, W08406, doi:10.1029/2004WR003826, 2005. Moradkhani, H., Hsu, K.-L., Gupta, H. V., and Sorooshian, S.: Uncertainty assessment of hydrologic model states and parameters: Sequential data assimilation using the particle filter, Water Resour. Res., 41, W05012, doi:10.1029/2004WR003604, 2005. Nash, J. and Sutcliffe, J.: River flow forecasting through conceptual models – Part I – A discussion of principles, J. Hydrol., 10, 282–290, 1970. O'Hagan, A.: Bayesian analysis of computer code outputs: A tutorial, Reliab. Eng. Syst. Safe., 91, 1290–1300, doi:10.1016/j.ress.2005.11.025, 2006. Protopapas, A. and Bras, R.: Uncertainty propagation with numerical models for flow and transport in the unsaturated zone, Water Resour. Res., 26, 2463–2474, 1990. Rosenblueth, E.: Two-point estimates in probability, Appl. Math. Model., 5, 329–335, doi:10.1016/S0307-904X(81)80054-6, 1981. Shrestha, D. L. and Solomatine, D. P.: Machine learning approaches for estimation of prediction interval for the model output, Neural Networks, 19, 225–235, doi:10.1016/j.neunet.2006.01.012, 2006. Shrestha, D. L. and Solomatine, D. P.: Data-driven approaches for estimating uncertainty in rainfall-runoff modelling, Int. J. River Basin Management, 6, 109–122, 2008. Solomatine, D. P., Dibike, Y. B., and Kukuric, N.: Automatic calibration of groundwater models using global optimization techniques, Hydrol. Sci. J., 44, 879–894, 1999. Solomatine, D. P. and Dulal, K. N.: Model trees as an alternative to neural networks in rainfall–runoff modelling, Hydrol. Sci. J., 48, 399–411, 2003. Solomatine, D. P. and Shrestha, D. L.: A novel method to estimate model uncertainty using machine learning techniques, Water Resour. Res., 45, W00B11, doi:10.1029/2008WR006839, 2009. Thiemann, M., Trosset, M., Gupta, H. V., and Sorooshian, S.: Bayesian recursive parameter estimation for hydrologic models, Water Resour. Res., 37, 2521–2535, 2001. Tung, Y.-K.: Uncertainty and reliability analysis, in: Water Resources Handbook, edited by: Mays, L. W., McGraw-Hill Book Company, 7.1–7.64, 1996. Vernieuwe, H., Georgieva, O., De Baets, B., Pauwels, V. R. N., Verhoest, N. E. C., and De Troch, F. P.: Comparison of data-driven Takagi-Sugeno models of rainfall–discharge dynamics, J. Hydrol., 302(1–4), 173–186, 2005. Vrugt, J. A., Diks, C., Gupta, H. V., Bouten, W., and Verstraten, J. M.: Improved treatment of uncertainty in hydrologic modeling: Combining the strengths of global optimization and data assimilation, Water Resour. Res., 41, W01017, doi:10.1029/2004WR003059, 2005. Vrugt, J. A., Gupta, H. V., Bouten, W., and Sorooshian, S.: A Shuffled complex evolution Metropolis algorithm for optimization and uncertainty assessment of hydrologic model parameters, Water Resour. Res., 39, 1201, doi:10.1029/2002WR001642, 2003. Vrugt, J. A. and Robinson, B. A.: Treatment of uncertainty using ensemble methods: Comparison of sequential data assimilation and Bayesian model averaging, Water Resour. Res., 43, W01411, doi:10.1029/2005WR004838, 2007. Vrugt, J. A., ter Braak, C. J. F., Clark, M. P., Hyman, J. M, and Robinson, B. A.: Treatment of input uncertainty in hydrologic modeling: doing hydrology backwards with Markov chain Monte Carlo simulation, Water Resour. Res., 44, W00B09, doi:10.1029/2007WR006720, 2008. Xiong, L. and O'Connor, K.: An empirical method to improve the prediction limits of the GLUE methodology in rainfall-runoff modeling, J. Hydrol., 349, 115–124, doi:10.1016/j.jhydrol.2007.10.029, 2008. Young, P. C.: Data-based mechanistic modelling of environmental, ecological, economic and engineering systems, Environ. Modell. Softw., 13, 105–122, doi:10.1016/S1364-8152(98)00011-5, 1998. Young, P. C. and Ratto, M.: A unified approach to environmental systems modeling, Stoch. Env. Res. Risk A., 10, 008–0271, doi:10.1007/s00477-008-0271-1, 2008.