Abstract
One of the major constraints on the use of backpropagation neural networks as a practical forecasting tool, is the number of training patterns needed. We propose a methodology that reduces the data requirements. The general idea is to use the Box-Jenkins models in an exploratory phase to identify the “lag components” of the series, to determine a compact network structure with one input unit for each lag, and then apply the validation procedure. This process minimizes the size of the network and consequently the data required to train the network. The results obtained in four studies show the potential of the new methodology as an alternative to the traditional time series models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Akaike, H. (1974) A new look at the statistical model identification, IEEE Transactions on Automatic Control, AC-19, 6, 716–723.
Box, G. E. P., Jenkins, G. M. (1976) Time series analysis: forecasting and control, Holden-Day, Inc. Oakland, California.
Chakraborty, K., Mehrotra, K., Mohan, C. K., Ranka, S. (1992) Forecasting the behavior of multivariate time series using neural networks, Neural Networks, 5, 961–970.
Coakley, J. R., McFarlane, D. D., Perley, W. G. (1992) Alternative criteria for evaluating artificial neural network performance,presented at TIMS/ORSA Joint National Meeting, April.
El-Sharkawi, M. A., Oh, S., Marks, R. J., Damborg, M. J., Brace, C. M. (1991) Short term electric load forecasting using an adaptative trained layered perceptron, in Proceedings of the First Forum on Application of Neural Networks to Power Systems, 3–6, Seattle, Washington.
Gorr, W., Nagin, D., Szcypula, J. (1992) The relevance of artificial neural networks to managerial forecasting; an analysis and empirical study, Technical Report 93–1, Heinz School of Public Policy and Management, Carnegie Mellon University, Pittsburgh, PA, USA.
Hertz, John, Krogh, Anders, Palmer, Richard G. (1991) Introduction to the Theory of Neural Computation,Addison-Wesley Publishing Co., Don Mills, Ontario, 1–8 and 89–156.
Hipel, K.W., McLeod, A.I. (1993) Time series modelling of water resources and environmental systems, to be published by Elsevier, Amsterdam, The Netherlands.
Lachtermacher, G. (1991) A fast heuristic for backpropagation in neural networks, Master’s Thesis, Department of Management Sciences, University of Waterloo, Waterloo, Ontario, Canada.
Lachtermacher, G. (1993) Backpropagation in Time Series Analysis, Ph.D Thesis, Department of Management Sciences, University of Waterloo, Waterloo, Ontario, Canada.
Lapedes, A., Farber, R. (1987) Nonlinear signal processing using neural networks: prediction and system modelling,Technical Report LA-UR2662, Los Alamos National Laboratory.
Lapedes, A., Farber, R. (1988) How neural nets works, in Neural Information Processing Systems, ed. Dana Z. Anderson, 442–456, American Institute of Physics, New York.
Nowlan, S. J., Hinton, G. E. (1992) Simplifying neural networks by soft weight-sharing, Neural Computation, 4, 473–493.
Rumelhart, David E., McClelland James L. and The PDP Research Group (1986) Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1: Foundations, MIT Press, Cambridge, Massachusetts, USA.
Srinivasan, D., Liew, A.C., Chen, J. S. P. (1991) Short term forecasting using neural network approach, in Proceedings of the First Forum on Application of Neural Networks to Power Systems, 12–16, Seattle, Washington.
Tang, Z., Almeida, C., Fishwick, P.A. (1991) Times series forecasting using neural networks vs. Box Jenkins methodology, in Simulations, 303–310, Simulations Councils, Inc., November.
Tong, H., Lim, K. S. (1980) Threshold autoregressive, limit cycles and cyclical data Journal of the Royal Stat. Society, series B, 42, 3, 245–292.
Tong, H. (1983) Threshold Models in non-linear time series analysis, in Lecture Notes in Statistics, ed. D.Brillinger, S. Flenberg, J.Ganid, J.Hartigan and K. Krickeberg, Springer-Verlag, New York, N.Y., USA.
Tukey, J. W. (1977) Exploratory data Analysis, Addison-Wesley, Reading, Massachusetts, USA.
Weigend, A. S. (1991) Connectionist architectures for time series prediction of dynamical systems, PhD Thesis, Department of Physics, Stanford University, University Microfilms International, Ann Arbor, Michigan.
Weigend, A. S., Rumelhart, D. E., Huberman, B.A. (1990) Predicting the future: a connectionist approach, International Journal of Neural Systems, 1, 3, 193–209.
Weigend, A. S., Rumelhart, D. E., Huberman, B.A. (1991) Back propagation, weight-elimination and time series prediction, in Connectionist Models - Proceedings of the 1990 Summer School, Edited by D.S.Touretzky, J.L.Elman, T.J.Sejnowski, G.E.Hinton, Morgan Kaufmann Publishers, Inc.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Lachtermacher, G., Fuller, J.D. (1994). Backpropagation in Hydrological Time Series Forecasting. In: Hipel, K.W., McLeod, A.I., Panu, U.S., Singh, V.P. (eds) Stochastic and Statistical Methods in Hydrology and Environmental Engineering. Water Science and Technology Library, vol 10/3. Springer, Dordrecht. https://doi.org/10.1007/978-94-017-3083-9_18
Download citation
DOI: https://doi.org/10.1007/978-94-017-3083-9_18
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-4379-5
Online ISBN: 978-94-017-3083-9
eBook Packages: Springer Book Archive