Artificial neural networks as an alternative to the Volterra series in rainfall-runoff modelling

• Autorzy: Napiórkowski J.J. , Piotrowski A.
• Języki publikacji: EN

Abstrakty

EN

Methods of description of the non-linear effects in dynamic rainfall-runoff systems have been surveyed. Particular reference is given to such non-linear methods which do not require detailed topographical survey and determination of rough-ness parameters. To describe rainfall-runoff relation, alternative approaches to non-linear partial differential equations of mass and energy transfer have been discussed, namely conceptual and black-box models. In more details, application of Volterra net, Multi-Layer Perceptron Artificial Neural Network and Radial Basis Function Network is tackled. Illustrative numerical examples of rainfall-runoff simulation and river flow forecast are presented.

Słowa kluczowe

EN

Volterra series; artificial neural network; rainfall-runoff model

• Wydawca: Instytut Geofizyki PAN
• Czasopismo: Acta Geophysica Polonica
• Rocznik: 2005
• Tom: Vol. 53, nr 4
• Strony: 459--472
• Opis fizyczny: Bibliogr. 21 poz.

Twórcy

autor

Napiórkowski J.J.

• Institute of Geophysics, Polish Academy of Sciences, Księcia Janusza 64, 01-452 Warszawa, Poland

autor

Piotrowski A.

• Institute of Geophysics, Polish Academy of Sciences, Księcia Janusza 64, 01-452 Warszawa, Poland

Bibliografia

• Amorocho, J., 1973: "Nonlinear hydrologie analysis", Adv. Hydrosci. 9, pp. 203-251.
• ASCE, 2000, Task Committee on Application of Artificial Neural Networks in Hydrology, Rao S. Govindaraju, 2000: "Artificial Neural Networks in Hydrology. I: Preliminary Con¬cepts", J. Hydr. Eng. 5 (2), pp. 115-123.
• Brath, A., A. Montanari and E. Toth, 2002: "Neural networks and non-parametric methods for improving real-time flood forecasting through conceptual hydrological models", Hydrol. Earth Syst. Sci. 6 (4), pp. 627-640.
• Dawson, C.W., C. Harpham, R.L. Wilby and Y. Chen, 2002: "Evaluation of artificial neural network techniques for flow forecasting in the River Yangtze, China", Hydrol. Earth Syst. Sci. 6 (4), pp. 619-626.
• Diskin, M.H., and A. Boneh, 1972: "Properties of kernels for time invariant initially relaxed, second order surface runoff systems", J. Hydrol. 17, pp. 115-141.
• Diskin, M.H., and A. Boneh, 1973: "Determination of the optimal krenels for second order stationary surface runoff systems". Water Resour. Res. 9 (2), pp. 311-325.
• Dooge, J.C.I., and J.P. O'Kane, 2003: "Deterministic methods in system hydrology", IHE Delft Lecture Note Series, Swets & Zeitlinger B.V., Lisse.
• Haykin, S., 1994: Neural Networks, a Comprehensive Foundation, Macmillan College Publish. Соmр., New York.
• Jayawardena, A.W., and D.A.K. Fernando, 1998: "Use of radial basis function type artificial neural networks for runoff simulation", Computer-Aided Civil and Infrastructure Eng. 13, pp. 91-99.
• Lighthill, M.H., and G.B. Witham, 1955: "On kinematic waves. I. Flood movement in long rivers". Proc. Roy. Soc, ser. A 299, pp. 281-316.
• Moradkhani, H., K.L. Hsu, H.V. Gupta and S. Sorooshian, 2004: "Improved streamflow fore, casting using self-organizing radial basis function artificial neural networks", J. Hydrol. 245, pp. 246-262.
• Napiórkowski, J.J., 1978: "Identification of the conceptual reservoir model described by Volterra series", D.Sc. Thesis, Institute of Geophysics, Polish Academy of Sciences Warsaw (in Polish).
• Napiórkowski, J.J., 1983: "The optimization of a third-order surface runoff model". Scientific Procedures Applied to Planning, Design and Management of Water Resources Systems (Proc. Hamburg Symposium, August), IAHS Publ. no. 147, pp. 161-172.
• Napiórkowski, J.J., and P. O'Kane, 1984: "A new nonlinear conceptual model of flood waves", J. Hydrol. 69, pp. 43-58.
• Napiórkowski, J.J., and W.G. Strupczewski, 1979: "The analytical determination of the kernels of the Volterra series describing the cascade of nonlinear reservoirs", J. Hydrol. Sci. 6 (3-4), pp. 121-142.
• Napiórkowski, J.J., and W.G. Strupczewski, 1981: "The properties of the kernels of the Volterra series describing flow deviation from a steady state in an open channel", J. Hydrol. 52, pp. 185-198.
• Napiórkowski, J.J., and W.G. Strupczewski, 1984: "Problems involved in identification of the kernels of Volterra series". Acta Geophys. Pol. 32 (4), pp. 375-391.
• Press, W.H., B.P. Flannery, S.A. Teukolsky and W.T. Vetterling, 1989: Numerical recipes in C. The Art of Scientific Computing, Cambridge University Press, Cambridge, UK.
• Silipo, R., 2003: "Neural networks". In: M. Berthold and D.J. Hand (eds.), Intelligent Data Analysis, pp. 270-320.
• Tikhonov, A.N., 1963: "On the solution of ill-posed problems and the regularization method", Doklady Akad. Nauk SSR 151.
• Volterra, v., 1930: Theory of Functionals and of Integral and Integro-Differential Equations, Blackie and Sons, London.