Predicrion Daily Flow of Vanyar Station Using ANN and Wavelet Hybrid Procedure

Document Type : Original Article

Authors

1 .MSc in water resource engineering,Tabriz University,Tabriz,Iran

2 Professor ,department of water engineering, Tabriz University,Tabriz,Iran

3 Assistant Professor, department on water engineering, Tabriz University,Tabriz,Iran

4 .Associate Professor, department on water engineering, Tabriz University, Tabriz,Iran

Abstract

According to the importance of river flow forecasting in water resources management, various methods are considered to model the flow in rivers. For the propose of minimizing the flood or drought hazard from the view point of management. Having nonlinear features and multiple time scales, the time series of daily flow were considered to be analised using artificial neural network (ANN) and wavelet hybrid procedures. For this purpose the original time series for 35 years was decomposed to 11 multi-frequency subseries by wavelet transform and then in order to predict the flow of future 1, 2, 3, and 4 days, this sub series was entered as input data to ANN model. The results of the Application modeling of wavelet- ANN with the results of modeling of ANN is compared, and it was observed that method of wavelet-neural networks has a higher forecast accuracy than method of ANN and also forecast accuracy in both models with increasing number of  delays in the output neurons is reduced, and it was observed that in predicte by wavelet-neural networks were used from Haar wavelet and Meyer wavelet that results the simulation of  Meyer wavelet  were more accurate than Haar wavelet.

Keywords

References

  1.  

    ۱.ابراهیمی، ل. و غ. بارانی. ۱۳۸۴. معرفی مدل تلفیقی تبدیل موجکی و شبکه های عصبی برای پیش بینی خشکسالی حوزه های آبخیز سدها. مجموعه مقالات دومین کنفرانس سراسری آبخیزداری و مدیریت منابع آب و خاک، ۳ و ۴ اسفند ۱۳۸۴ ، دانشگاه کرمان، ص۲۳۵۴-۲۳۵۹

    ۲.سلطانی، س. ۱۳۸۱. مقایسه مدل های تفهیمی در مقایسه با شبکه های عصبی مصنوعی در شبیه سازی بارش- رواناب. پایان نامه کارشناسی ارشد، دانشگاه تربیت مدرس، ص 98.

    ۳.طوفانی، پ.، ا. مساعدی، و ا. فاخری فرد.۱۳۹۰.پیش بینی بارندگی با استفاده مستقیم از نظریه موجک. نشریه آب و خاک. 25، ص1217-1226.

    ۴.قبائی سوق، م.، ا. مساعدی  و ح. موسی هزار جریبی .۱۳۸۹.  ارزیابی تأثیر  پیش پردازش پارامترهای ورودی به شبکه عصبی مصنوعی با استفاده از روشهای رگرسیون گام به گام و گاما تست به منظور تخمین سریعتر تبخیر و تعرق روزانه. نشریه آب و خاک،دانشگاه فردوسی مشهد. جلد ۲۴ شماره۳ ، ص610-624.

    ۵. منهاج، م .۱۳۸۱. مبانی شبکه های عصبی(هوش محاسباتی). جلد اول، مرکز نشر دانشگاهی صنعتی امیرکبیر، صفحه 715.

    ۶.نوری، م.، ه. عبقری.۱۳۸۶. شبیه سازی بارش- رواناب با شبکه های عصبی تابع بنیادی شعاعی(RBF) مبتنی بر طبقه بندی شبکه عصبی احتمالاتی.(PNN) لوح فشرده مجموعه مقالات سومین کنفرانس آبخیزداری و مدیریت منابع آب و خاک، ۲۰ و ۲۱ آذر ۱۳۸۶ ، دانشگاه کرمان.

    7. Abrahart, RJ.; L. See .2000. comparing neural network (NN) and Auto Regressive Moving Average (ARMA) techniques for the provision of continuous river flow forecasts in two contrasting catchment.Hydrol Process,14:2157-2172.

    8. Adamowski, Jan.; Karen. Sun. 2010. Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. Journal of Hydrology vol, 390:85–91.

    9. Bowden, G.J.; G.C. Dandy; H.R. Maier. 2005. Input determination for neural network models in water resources applications. Part1.background and methodology.” J. of Hydrologic.. 301:75-92.

    10. Broadhurst, D.; R. Goodacre; A. Jones; J.J. Rowland and D.B. Kell .1997. Genetic algorithms as a method for variable selection in multiple linear regression and partial least squares regression, with applications to pyrolysis mass spectrometry. Anal. Chim. Acta. 348 (1-3): 71-86.

    11. Cannas, B.; A. Fanni; L. See and G. Sias.2006. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Phys Chem Earth.31(18):1164–1171.

    12. de Vos, N.J. 2003. Rainfall-Runoff Modelling Using Artificial Neural Networks. M. Sc. Thesis Report., Civil Engineering Informatics Group and Section of Hydrology & Ecology.

    13. Govindaraju, Rao S. 2000. Artificial neural networks in hydrology II: hydrologic applications. Journal of Hydrologic Engineering. 5(2):124-137, ASCE.

    14. Haykin, S. 1994. Neural Networks:a comprehensive foundation. Mac Millan College. Publishing Company New York.

    15. Haykin, S.1999. Neural networks: a comprehensive foundation, 2nd Ed., Prentice Hall., New Jersey, USA.

    16. Kisi, O .2008. Stream flow forecasting using neuro-wavelet technique.Hydrol. Process. Vol, 22:4142–4152.

    17. Mallat, S. 1989. Throries for multiresolution signal decomposition: the wavelet representation ,IEEE Pattern Anal. and Machine Intell.11(7): 93-674.

    18. Merry, R.J.E. 2005. Wavelet Theory and Applications. A literature study. Eindhoven University of Technology Department of Mechanical Engineering Control Systems Technology Group.

    19. Misiti, M.; Y. Misiti; G. Oppenheim and J.M. Poggi. 1996. “Wavelet Toolbox”..

    20. Nourani ,V.; M. Komasi and A. Mano .2009.A Multivariate ANN-Wavelet Approachfor Rainfall–Runoff Modeling. Water Resour Manage 23: 2877–2894.

    1. 21.  Partal, T.; O. Kisi. 2007. Wavelet and neruro-fuzzy conjunction model for precipitation forecasting. Journal of Hydrology 342: 199-212.

    22. Polikar, R. 1996. Fundamental Concept  and  An Oveview Of The Wavelet Theory  Wavelet Tutorial. sECOND edition. rowan university. coollege of engineering web servers. glassboro .nj.08028.

    1. 23.  Rioul, O.; M. Vetterli. 1991. Wavelets and signal processing. IEEE SP Magazine. p-p, 14–38.

    24. Sifuzzaman, M.; M.R. Islam; M.Z.  Ali  .2009. Application of Wavelet Transform and its Advantages Compared to Fourier Transform. Journal of Physical Sciences, 13:121-134.

    25. Silverman, D.; J. A. Dracup.2000. Artificial neural network and long range precipitation prediction in California. Journal of Applied Meteorology 39(1):57-66.

    26. Thuillard, M .2000. A review of wavelet networks ,wavelets, fuzzy wavelets and their application. ESIT.in:Presented in Conference 14-15 September.

    27. Zhang, BL .; ZY. Dong .2001. An adaptive neural wavelet model for short term load forecasting. Electr Power Syst Res. 59:121–129.

    28. Zhang, Y.X. 2007. Artificial neural networks based on principal component analysis input selection for clinical pattern recognition analysis. Talanta. 73 (1):68-75.

Files

Share

How to cite

Statistics