Evaluation of empirical orthogonal functions to the fuzzy inference system and artificial neural network to predict the flow

Document Type : Original Article

Authors

1 Graduate master of irrigation and drainage, Department of water engineering, Razi university,

2 -Assistant professor, Department of water engineering, Faculty of agriculture, Razi university, Iran

3 Assistant professor, Department of water engineering, Faculty of agriculture, Razi university, Iran

4 ssistant professor, Department of civil engineering, Faculty of engineer, azad university, Iran

Abstract

To predict the value of the streamflow, usually two methods of the Process-driven methods and Data – driven methods is used. Including Data – driven methods in river flow forecasting is artificial neural network, regression, time series and fuzzy logic. In this study, performance of another method empirical orthogonal functions than artificial neural network and fuzzy inference system to predict monthly inflow Latyan Dam reservoir was evaluated. Five models of ANN and ANFIS are similar and depends on  rainfall, temperature and streamflow. Whereas five models of EOF depends on only streamflow in Latian station and Adjacent stations. Initial for all models the best combination identified, then statistical parameters of CE, MAPE, RMSE, CORR in the best combinations of all models  were compared. The results showed that the fuzzy inference system, a better performance than the other way round

Keywords

References

عرب، ر. 1385.  بررسی آماری ارتباط بارش و جریان رودخانه های حوضه جراحی با پدیده های اقلیمی ENSO, NAO. هفتمین سمینار بین المللی مهندسی رودخانه. اهواز.
2- محمدی، م.، م. محمودشوشتری. 1385. برآورد دبی هفتگی متوسط رودخانه کر بوسیله شبکه عصبی مصنوعی و مدل hec-hms. هفتمین سمینار بین المللی مهندسی رودخانه. اهواز.
3- نوری قیداری، م. 1384.  کلاسه بندی منطقه ای مقادیر حدی جریان رودخانه با نگرش آماری. پایان نامه کارشناسی ارشد گروه مهندسی آب. دانشگاه تهران.
4. Braud, I. 1992. EOF analysis: analytical aspects of a geostatistical like method adapted to the simulation of non-stationary fields. Statistics for Spatial Data. Wiley, New York,USA.
5. Hisdal, H. ؛Tveito, O.E. 1993. Extension of runoff series using empirical orthogonal functions. Hydrological Sciences Journal 38 (1/2) 33–49.
6. Kang, K.W. ؛Kim J.H. ؛Park C.Y. ؛and Ham K.J. 1993. Evaluation of hydrological forecasting system based on neural network model. In: Proc. 25 th Congress of Int. Assoc. for Hydr. Res. IAHR. Delft. The Netherlands. 257-264.
7. Kisi, O. 2004. River Flow Modelling using artificial neural networks. J. Hydrol. Eng. 9(1).60-63.
8. Mahabir, C.; Hicks, F.E.; and Robinson, Fayek A. 2003. Application of fuzzy logic to forecast seasonal runoff. Hydrol. Process. 17. 3749–3762.
9.Mizumura, K. 1995. Application of fuzzy theory to snowmelt-runoff. In: Kundzewicz, Z.W. Ed. New uncertainty concep ts in hydrology and water resources, Cambridge University Press, New York.
10. Obled, C.; Creutin, J.D. 1986. Some development in the use of empirical orthogonal functions for mapping meteorological fields.
11. Sajikumar, N.; Thandaveswara, B.S. 1999. A nonlinear rainfall runoff model using an artificial neural network. J. hydrol. 216. 32-55.
12. Tawfik, Maha. 2003. Linearity Versus non-linearity in forecasting Nile River flows. Advances in Enginearing Software. 34.515-524.
13. Wang,  W.; Vrijling,  J K.; Van, Gelder.; 2006. Stochastisity, Nonlinearity and Forecasting of Streamflow Processes. Publisher and Distributer: IOS Press, 1013 B G Amsterdam, Netherland.
14. Zealand, C.M.; Burn, D.H.; and Simonovic, S.P. 1999. Short term streamflow forecasting using artificial neural networks. J. hydrol. 214. 32-48.

Files

Share

How to cite

Statistics