Neural Networks as Routine for Error Updating of Numerical Models
Publication: Journal of Hydraulic Engineering
Volume 127, Issue 3
Abstract
This paper describes a somewhat alternative approach to combining observations and numerical model results in order to produce a more accurate forecast routine. The approach utilizes artificial neural networks to analyze and forecast the errors created by numerical models. The resulting hybrid model provides very good forecast skills that can be extended over a forecasting horizon of considerable length. The method has been developed for the purpose of operational forecasting of current speeds in the Danish ∅resund Strait. The forecast system was used as a planning tool during the construction of the 16 km-long fixed link across the ∅resund Strait, linking the countries of Denmark and Sweden.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Babovic, V. ( 1996). Emergence, evolution, intelligence; Hydroinformatics, Balkema, Rotterdam, The Netherlands.
2.
Babovic, V., and Keijzer, M. ( 1999). “Coping with floods.” Forecasting of river discharges in the presence of chaos and noise, J. Marsalek, ed., Kluwer, Dordrecht, The Netherlands.
3.
Cañizares, R. T. ( 1999). “On the application of data assimilation in regional coastal models.” PhD thesis, IHE, Delft, The Netherlands.
4.
DHI/LIC. ( 1997). “The ∅resund Link: Transport and installation weather windows.”
5.
Friedman, J. H. ( 1997). “On bias, variance 0/1-loss, and the curse of dimensionality.” Data Mining and Knowledge Discovery, 1(1), 55–78.
6.
Gelb, A. ( 1974). Applied optimal estimation, MIT Press, Cambridge, Mass.
7.
German, S., Bienenstock, E., and Doursat, R. ( 1992). “Neural networks and the bias/variance dilemma.” Neural Computation, 5, 1–58.
8.
Haykin, S. ( 1994). Neural networks: A comprehensive foundation, Macmillan, New York.
9.
Hebb, D. O. ( 1949). Organization of behavior, Wiley, New York.
10.
Hoppcroft, J. E., and Ullman, J. D. ( 1979). Introduction to automata theory, languages, and computation, Addison-Wesley, Reading, Mass.
11.
Hornik, K., Stinchcombe, M., and White, H. ( 1989). “Multilayer neural networks are universal approximators.” Neural Networks, 2, 356–366.
12.
Lang, K., and Hinton, G. ( 1988). “A time delay neural network for speech recognition.” Tech. Rep. CMU-CS-88-152, Carnegie Mellon University, Pittsburgh, Pa.
13.
McCulloch, W. S., and Pitts, W. ( 1943). “A logical calculus of the ideas imminent in nervous activity.” Bull. Math. Biophysics, 5, 115–133.
14.
Minns, A. W. ( 1998). Artificial neural networks as subsymbolic model descriptors, Balkema, Rotterdam, The Netherlands.
15.
Refsgåard, J. C. ( 1997). “Validation and intercomparison of different updating procedures for real-time forecasting.” Nordic Hydro., 28, 65–84.
16.
Van den Boogaard, H. P. C., and Kruisbrinck, A. C. H. ( 1996). “Hybrid modeling by integrating neural networks and numerical models.” Proc., Hydroinformatics '96 Conf., A. Muller, ed.
17.
Wan, E. A. ( 1993). “Time-series prediction: Forecasting the future and understanding the past.” Time-series prediction by using a connectionist network with internal delay units, A. Weigend and N. Gershenfeld, eds., Addison-Wesley, Reading, Mass.
18.
World Meteorological Organization (WMO). ( 1992). “Simulated real-time intercomparison of hydrological models.” Operational Hydro. Rep. No. 38, Geneva.
Information & Authors
Information
Published In
History
Received: Jan 11, 2000
Published online: Mar 1, 2001
Published in print: Mar 2001
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.