Combination of Artificial Neural Networks and Hydrodynamic Models for More Precise Prediction of River Flow

Document Type : Research Paper

Authors

1 Assistant Professor of the Faculty of Natural Resources Engineering, the University of Yazd, Iran

2 Professor of the School of Civil Engineering, the University of Nottingham, UK

Abstract

 









آب و فاضلاب                                                                                                                                                                                                               شماره 49- سال 1383
 





 












* استادیار دانشکده منابع طبیعی دانشگاه یزد
** استاد گروه عمران دانشگاه تاتینگهام انگلستان





 



In this study, an artificial neural networks (ANN) model was used to optimize the results obtained from a hydrodynamic model of river flow was evaluated. The study area is Reynolds Creek experimental watershed in southwest Idaho, USA. A hydrodynamic model was constructed to predict flow at the outlet using time series data from upstream gauging sites as boundary conditions. In the second stage, the model was replaced with an ANN model bout with the same inputs. Finally a hybrid model was employed in which the error of the hydrodynamic model is predicted using an ANN model to optimize the outputs. Simulation were carried out for two different conditions (with and without data from a recently suspended gauging site) to evaluate the effect of this suspension in hydrodynamic, ANN and the combined model. Using ANN in this way the error produced by the hydrodynamic model is predicted and thereby, the results of the model are improved.

References

1- DHI (Danish Hydraulic Institute), (2000). "MIKE11 User Manual".
2- Hanson, C.L., Marks, D. and Van Vactor, S.S., (2006). "Climate Monitoring at the Reynolds Creek Experimental Watershed", ARS Technical Bulletin, NWRC. Idaho, USA.
3- Hanson C.L., (2004). "Precipitation Monitoring at the Reynolds Creek Experimental Watershed", Technical Bulletin, NWRC. Idaho, USA.
4- Marks, D., Cooley, K.R., Robertson, D.C. and Winstral, A., (2005). "Snow Monitoring at the Reynolds Creek Experimental Watershed", ARS Technical Bulletion NWRC. Idaho, USA.
5- Neuro Dimensions, NeuroSolutions, 2001.www.nd.com.
6- Pierson, F.B., Slaughter, C.W. and Cram, Z.K., (2008). "Monitoring Discharge and Suspended Sediment", Reynolds Creek Experimental Watershed, ARS Technical Bulletin NWRC. Idaho, USA.
7- Seyfried, M.S., Harris, R.C., Marks, D. and Jacob, B., (2003). "A Geographic Database fro Watershed Research, Reynolds Creek Experimental Watershed", Idaho, USA, ARS Technical Bulletin NWRC.
8- Slaughter C.W., Marks, D., Flerchinger, G.N., Van Vactor, S.S. and Burgess M., (2007). "Research Data Collection at the Reynolds Creek Experimental Watershed", Idaho, USA, ARS Technical Bulletin NWRC.
9- USDA-ARS Northwest Watershed Research Center, Anonymous, ftp site: ftp.nwrc.ars.usda.gov.
10- Wright, N.G., Dastorani, M.T., Goodwin, P. and Slaughter, C.W., (2002). "Using Artificial Neural Networks for Optimisation of hydraulic river flow modeling results", Proceedings of the International Conference of River Flow 2002, Louvain-al-Neuve, Belgium, September, 2002.
Journal of Water and Wastewater; Ab va Fazilab ( in persian )
Volume 15, Issue 1 - Serial Number 1
Serial number: 49
May and June 2004
Pages 10-20

Files

Share

How to cite

Statistics