A Seasonal Streamflow Forecasting Model Using Neurofuzzy Network

  • R. Ballini
  • M. Figueiredo
  • S. Soares
  • M. Andrade
  • F. Gomide
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 516)


A class of neurofuzzy networks and a constructive, competition - based learning procedure is presented as a vehicle to develop fuzzy models. Seasonal streamflow forecasting models are of particular interest here because it poses substantial modeling challenges, and it is of paramount importance when solving water resources systems operation planning problems. The network learns membership functions parameters for each input variable from training data, processes data following fuzzy reasoning principles, and has input space partition automatically adjusted to cover the whole input space. These are essential design issues when developing fuzzy models of systems and processes. The problem of seasonal streamflow forecasting is solved using a database of average monthly inflows of three Brazilian hydroelectric plants located at different river basins. Comparison of the neurofuzzy model with multilayer neural network and periodic autoregressive models are also included to illustrate the performance of the approach. The results show that the neurofuzzy model provides a better one-step-ahead streamflow forecasting, with forecasting errors significantly lower than the other approaches.


Artificial Neural Network Fuzzy Rule Forecast Error Neural Fuzzy Network Hydroelectric Plant 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    M. Castro, J. Delgado. Fuzzy systems with defuzzification are universal imators. IEEE Transactions on Systems, Man, and Cybernetics, 26(1):149–152, 1996.CrossRefGoogle Scholar
  2. [2]
    G. Cybenko. Approximation by superpositions of a sigmoidal function. Mathe-matical Control Signals Systems, (2):303–314, 1989.MathSciNetMATHCrossRefGoogle Scholar
  3. [3]
    M. Delgado, A. Skarmeta, and F. Martin. A neural fuzzy network: Structure and learning. volume 1, pages 563–568, Spain, 1996. Proceedings of the 6th International Conference of IPMU’96.Google Scholar
  4. [4]
    M. Figueiredo and F. Gomide. Adaptive neuro fuzzy modelling. In Proceedings of FUZZ-IEEE’97, pages 1567–1572, 1997.Google Scholar
  5. [5]
    M. Figueiredo and F. Gomide. Fuzzy system design using neurofuzzy networks. volume 2, pages 1416–1422, Paris, 1998. Proceedings of the 7th International Conference of IPMU’98.Google Scholar
  6. [6]
    F. Gomide, M. Figueiredo, and W. Pedrycs. A neural fuzzy network: Structure and learning. In Fuzzy Logic and Its Applications, Information Sciences and Intelligent Systems, pages 177–186, Netherlands, 1995. Bien, Z. and Min, K., Kluwer Academic Publishers.Google Scholar
  7. [7]
    J. Kacprzyk and M. Fedrizzi. Fuzzy regression Analysis. Studies in Fuzziness, volume 1. Physica-Verlag, Heidelberg, 1992.Google Scholar
  8. [8]
    G.. Lachtermacher and J. D. Fuller. Backpropagation in time-series forecasting. Journal of Forecasting, 14(4):193–381, January 1995.CrossRefGoogle Scholar
  9. [9]
    A. I. MecLeod. Diagnostic checking of periodic autoregression. Journal of Time Series Analysis, 15(2):221–223, 1994.Google Scholar
  10. [10]
    W. Pedrycz and F. Gomide. An Introduction to Fuzzy Sets: Analysis and Design. MIT Press, Cambridge, 1998.MATHGoogle Scholar
  11. [11]
    J. D. Salas, D. C. Boes, and R. A. Smith. Estimation for arma models with seasonal parameters. Water Resources Research., 18(4):1006–1010, 1982.CrossRefGoogle Scholar
  12. [12]
    A. V. Vecchia. Maximum likelihood estimation for periodic autoregressive-moving average models. Technometrics, 27:375–384, 1985.CrossRefGoogle Scholar
  13. [13]
    A. S. Weigend, D. E. Rumelhart, and B. A. Huberman. Generalization by weight-elimination applied to currency exchange rate prediction. In Proceedings of the IEEE/IJCNN, pages 837–841, 1991.Google Scholar
  14. [14]
    R. Yager and D. Filev. Essentials of Fuzzy Modeling and Control. Wiley Interscience, New York, 1994.Google Scholar

Copyright information

© Springer Science+Business Media New York 2000

Authors and Affiliations

  • R. Ballini
    • 1
  • M. Figueiredo
    • 2
  • S. Soares
    • 1
  • M. Andrade
    • 3
  • F. Gomide
    • 1
  1. 1.Faculty of Electrical and Computer EngineeringState University of CampinasCampinasBrazil
  2. 2.Department of InformaticsState University of MaringaMaringaBrazil
  3. 3.Institute of Mathematics and Computer SciencesUniversity of São PauloSão CarlosBrazil

Personalised recommendations