Monthly Low-Flow Forecasting Using a Stochastic Model and Adaptive Network Based Fuzzy Inference System

Document Type : Original Article

Authors

1 Associate Professor, Dept. of Irrigation and Reclamation Eng., Faculty of Water and Soil Eng., University of Tehran

2 Assistant Professor, Dept. of Water Eng., Faculty of Agriculture, University of Guilan

3 Former M.Sc. student, Dept. of Irrigation and Reclamation Eng., Faculty of Water and Soil Eng., University of Tehran

Abstract

Surface water management practices are directly influenced by the streamflow forecasting, especially for the low-flow context. In this paper, the monthly low-flow time series were modeled and forecasted using a traditional stochastic model (Autoregressive Integrated Moving Average-ARIMA) and an artificial intelligence based model (Adaptive Network based Fuzzy Inference System-ANFIS). Low-flow in each month was defined as the minimum value of one, three, and seven day moving averages of daily streamflow. The performance of the stochastic model was compared to the neuro-fuzzy model through application to the streamflow data from the NavroodRiver basin in the Guilan state, northern Iran. The results showed that the stochastic model resulted in more accurate forecasted values than the neuro-fuzzy model for one, three, and seven day low-flow time series. Furthermore, in all neuro-fuzzy and stochastic models the error in forecasting three-day low-flow is less than those for one- and seven-day low-flow.

Keywords

References

عراقی‌نژاد، ش. و کارآموز، م. (1384)، "پیش‌بینی بلند مدت رواناب با استفاده از شبکه‌های عصبی مصنوعی و سیستم استنتاج فازی"، تحقیقات منابع آب ایران، شمارة 2.
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000a). “Artificial neural networks in hydrology. I: Preliminary concepts”, J. Hydrologic Engineering, 5(2), pp. 115–123.
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000b). “Artificial neural networks in hydrology. II: Hydrologic applications”, J. Hydrologic Engineering, 5(2), pp. 124–137.
Box, G. E. P. and Cox, D. (1964), “An analysis of transformation with discussion”, J. Royal Statistical Society. Series B. Statistical Methodology, 26, pp. 211-246.
Bras, R.L. and Rodriguez-Iturbe, I. (1993), Random functions and hydrology, Dover Publications, Mineola, New York, 559p.
Chang, L. C. and Chang, F. J. (2001), “Intelligent control for modeling of real-time reservoir operation”, Hydrological Processes, 15, pp. 1621- 1631.
Chau, K. W., Wu, C. L. and Li, Y. S. (2005), “Comparison of several flood forecasting models in Yangtze River”, J. Hydrologic Engineering, 10(6), pp. 485- 491.
Chiu, S. L. )1994(, “Fuzzy model identification based on cluster estimation”, J. Intelligent Fuzzy Systems, 2, pp. 267- 278.
Firat, M. (2007), “Artificial intelligence techniques for river flow forecasting in the Seyhan River catchment, Turkey”, Hydrology and Earth System Sciences Discussions, 4, pp. 1369-1406.
Gorr, W. L., Nagin, D. and Szczypula, J. (1994), “Comparative study of artificial neural network and statistical models for predicting student grade point averages”, Int. J. Forecasting, 10, pp. 17–34.
Hirsch, R. M. and Slack, J. R. (1984), “A nonparametric trend test for seasonal data with serial dependence”, Water Resources Research, 20, pp. 727-732.
Jain, A. and Indurthy, S. K. V. P. (2003), “Comparative analysis of event based rainfall-runoff modeling techniques-deterministic, statistical, and artificial neural networks”, J. Hydrologic Engineering, 8(2), pp. 93- 98.
Jang, J. S. R. (1993), “ANFIS: adaptive network based fuzzy inference system”, IEEE Transactions on Systems, Man and Cybernetics, 23, pp. 665-683.
Jang, J. S. R. and Sun, C. T. (1995), “Neuro-fuzzy modeling and control”, Proceedings IEEE, 83, pp. 378–406.
Lewis, P. A. W. and Ray, B. K. (2002) “Nonlinear modeling of periodic threshold autoregressions using TSMARS”, J. Time Series Analysis, 23(4), pp. 459–471.
Ljung, G. M. and Box, G. E. P. (1978), “On a measure of lack of fit in time series models”, Biometrica, 65, pp. 67-72.
 
Maier, H. R. and Dandy, G. C. (1996), “The use of artificial neural networks for the prediction of water quality parameters”, Water Resources Research, 32(4), pp. 1013–1022.
Mishra, A. K., Desai, V. R. and Singh, V. P. (2007), “Drought forecasting using a hybrid stochastic and neural network model”, J. Hydrologic Engineering, 12(6), pp. 626-638.
Nayak, P. C., Sudheer, K. P., Rangan, D. M. and Ramasastri, K. S. (2004), “A neuro-fuzzy computing technique for modeling hydrological time series”, J. Hydrology, 291, pp. 52-66.
Salas, J. D., Delleur, J. W., Yevjevich, V. and Lane, W. L. (1988), Applied modeling of hydrologic time series, Water Resources Publications, Littleton, Colorado, 498p.
Schwarz, G. (1978), “Estimating the dimension of a model”, Annuals of Statistics, 6, pp. 461-464.
Smakhtin, V. U. (2001), “Low flow hydrology: A review”, J. Hydrology, 240, pp. 147-186.
Vogel, R. M. (1986), “The probability plot correlation coefficient test for normal, lognormal, and Gumbel distributional hypotheses”, Water Resources Research, 22, pp. 587-590.
Yurekli, K. and Kurunc, A. (2005), “Performances of stochastic approaches in generating low streamflow data for drought analysis”, J. Spatial Hydrology, 5(1), pp. 20-31.
Iran-Water Resources Research
Volume 5, Issue 2
June 2009
Pages 16-26

Files

History

  • Receive Date: 06 October 2007
  • Accept Date: 22 June 2009

Share

How to cite

Statistics