Hybrid Neural Network—Finite Element River Flow Model
Publication: Journal of Hydraulic Engineering
Volume 131, Issue 1
Abstract
Results obtained from a hybrid neural network—finite element model are reported in this paper. The hybrid model incorporates artificial neural network (ANN) nodes into a numerical scheme, which solves the two-dimensional shallow water equations using finite elements (FE). First, numerical computations are carried out on the entire numerical model, using a larger mesh. The results from this computation are then used to train several preselected ANN nodes. The ANN nodes model the response for a part of the entire numerical model by transferring the system reaction to the location where both models are connected in real time. This allows a smaller mesh to be used in the hybrid ANN-FE model, resulting in savings in computation time. The hybrid model was developed for a river application, using the computational nodes located at the open boundaries to be the ANN nodes for the ANN-FE hybrid model. Real-time coupling between the ANN and FE models was achieved, and a reduction is CPU time of more than 25% was obtained.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This study was undertaken while the first writer was working on the Deutsches Forschungsnetz Naturkatastrophen (DFNK) project at the Institut für Bauinformatik, BTU Cottbus, Germany. The funding provided by the Bundesministerium für Bildung und Forschung (BMBF) is gratefully acknowledged.
References
Ambrosi, D., Corti, S., Pennati, V., and Saleri, F. (1996). “Numerical simulation of unsteady flow at Po River Delta.” J. Hydraul. Eng., 122(12), 735–743.
Benning, R. M., Becker, T. M., and Delgado, A. (2001). “Initial studies of predicting flow fields with an ANN hybrid.” Adv. Eng. Software, 32, 895–901.
Benque, J. P., Cunge, J. A., Feuillet, J., Hauguel, A., and Holly, F. M., Jr. (1982). “New method for tidal current computation.” J. Waterw., Port, Coastal, Ocean Div., Am. Soc. Civ. Eng., 108(3), 396–417.
Dibike, Y. B., and Abbott, M. B. (1999). “Application of artificial neural networks to the simulation of a two-dimensional flow.” J. Hydraul. Res., 37(4), 435—446.
Funke, E. R., and Crookshank, N. L. (1978). “A hybrid model of the St. Lawrence River Estuary.” Proc., 17th Coastal Engineering Conf., ASCE, Hamburg, 2855–2869.
Haykin, S. (1998). Neural networks—A comprehensive foundation. Prentice-Hall, Englewood Cliffs, N.J.
Holz, K.-P. (1976). “Analysis of time conditions for hybrid tidal models.” Proc., 15th Coastal Engineering Conf., ASCE, Honolulu, 3460–3470.
Holz, K.-P. (1978). “Simulation of tidal river dynamics.” Lecture notes on coastal and estuarine studies, mathematical modeling of estuarine physics, J. Sündermann and K.-P. Holz, eds., Springer, Berlin 145–156.
Karunanithi, N., Grenney, W. J., Whitley, D., and Bovee, K. (1994). “Neural networks for river flow prediction.” J. Comput. Civ. Eng., 8(2), 201–220.
Liong, S.-Y, Lim, W.-H., and Paudyal, G. N. (2000). “River stage forecasting in Bangladesh: Neural network approach.” J. Comput. Civ. Eng., 14(1), 1–8.
Reed, R. D., and Marks, R. J. (1999). Neural smithing: Supervised learning in feedforward artificial neural networks, MIT Press, Cambridge, Mass.
Swevolver for Windows reference manual, release 3.2 (2001). Center for Processes’ Analysis and Research Ltd., (PAIC), Riga, Latvia.
Zealand, C. M., Burn, D. H., and Simonovic, S. P. (1999). “Short term streamflow forecasting using artificial neural networks.” J. Hydrol., 214, 32–48.
Information & Authors
Information
Published In
Copyright
© 2004 ASCE.
History
Received: Oct 7, 2003
Accepted: Jul 21, 2004
Published online: Jan 1, 2005
Published in print: Jan 2005
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.