تحلیل عدم قطعیت مدل های شبکه عصبی و نروفازی در پیش بینی جریان رودخانه

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری /سازه های آبی، دانشگاه تربیت مدرس

2 دانشیار/گروه سازه های آبی، دانشگاه تربیت مدرس

چکیده

پیش بینی آورد رودخانه در مدیریت منابع آب از اهمیت فراوانی برخوردار است، اما به دلیل عدم قطعیت بالا در عواملی که فرآیند بارش- رواناب را سبب می‌گردند، همواره با مشکلاتی همراه بوده است. یکی از روش‌هایی که می‌تواند این مشکل را تا حدی کاهش دهد، تحلیل‌ عدم قطعیت پیش‌بینی‌های انجام شده می‌باشد. این تحلیل‌ها در مدل‌های آماری سابقه طولانی دارند، ولی برای مدل‌های شبکه عصبی و نروفازی کمتر مورد استفاده قرار گرفته و این در شرایطی است که در سال‌های اخیر به مراتب توجه بیشتری به این تکنیک‌ها شده است. در مطالعه حاضر عدم قطعیت نتایج مدل‌های شبکه عصبی و نروفازی در پیش‌بینی 1 تا 3 ماه آینده جریان رودخانه مورد ارزیابی قرار گرفته و منطقه مطالعاتی رودخانه صوفی‌چای در محل ایستگاه تازه‌کند در نظر گرفته شده است. نتایج نشان می‌دهد که مدل نروفازی از دقت بالاتر در پیش‌بینی و عدم قطعیت کمتری برخوردار است، اما بطور مشخص برای پرآبی‌ها در هر دو مدل عدم قطعیت بیشتر شده که خطرپذیری (ریسک) کاربرد نتایج را افزایش می‌دهد.

کلیدواژه‌ها


عنوان مقاله [English]

Uncertainty Analysis of Artificial Neural Networks and Neuro-Fuzzy Models in River Flow Forecasting

نویسندگان [English]

  • A Farokhnia 1
  • S Morid 2
1 Ph.D. Student, Dep. of Water Structures Eng., Tarbiat Modares University, Tehran, Iran
2 Associate Professor, Dep. of Water Structures Eng., Tarbiat Modares University, Tehran, Iran
چکیده [English]

River flow forecasting in water resources management is of great importance. But, due to the high uncertainty in the factors affecting the rainfall-runoff process, the results are usually problematic. One of the procedures that can alleviate this problem is incorporating uncertainty analysis in forecasted results. Such an analysis has been traditionally used for statistical methods but less attention has been given to the Artificial Neural Networks (ANNs) and the Neuro-Fuzzy (ANFIS) models. These models have gained much popularity in recent years. This research has aimed to analyze the uncertainty of these techniques for 1 to 3 months forecasting of river flow. Sofy-Chay River  at Tazekand gauging station in the northwest of Iran is selected as the study site to explore the methodology. The results show that ANFIS overall gave more accurate forecasts and less uncertainty. But, when it comes to high flows, the confidence interval for the two models increases quite obviously and this increases the risk for application of the results.

کلیدواژه‌ها [English]

  • River Flow Forecasting
  • Uncertainty
  • Artificial Neural Network
  • Neuro-Fuzzy
Abbaspour, K. C., Yang, J., Maximov, I., Siber, R., Bogner, K., Mieleitner, J., Zobrist, J. and Srinivasan, R. (2007), "Modelling hydrology and water quality in the pre-alpine/alpine Thur watershed using SWAT." Journal of Hydrology, 333, pp. 413-430.
Aqil, M., Kita, I., Yano, A. and Nishiyama, S. (2007a), "A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoff." Journal of Hydrology, 337, pp. 22-34.
Aqil, M., Kita, I., Yano, A. and Nishiyama, S. (2007b), "Analysis and prediction of flow from local source in a river basin using a Neuro-fuzzy modeling tool." Journal of Environmental Management, 85(1), pp. 215-223.
ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000a), "Artificial neural networks in hydrology. I: Preliminary concepts." Journal of Hydrologic Engineering, ASCE, 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." Journal of Hydrologic Engineering, ASCE, 5(2), pp. 124-137.
Bowden, G. J., Dandy, G. C. and Maier, H. R. (2005), "Input determination for neural network models in
 
       water resources applications. Part 1—background and methodology." Journal of Hydrology, 301, pp. 75-92.
Chiu, S. L. (1994), "Fuzzy Model Identification Based on Cluster Estimation." Journal of Intelligent and Fuzzy Systems, 2(3), pp. 267-278.
Coulibaly, P., Anctil, F. and Bobee, B. (2000), "Daily reservoir inflow forecasting using artificial neural networks with stopped training approach." Journal of Hydrology, 230, pp. 244-257.
Cybenko, G. (1989), "Approximation by superpositions of a sigmoidal function." Mathematics of Control, Signals and System , 2(4), pp. 303-314.
Dibike, Y. B. and Solomatine, D. P. (2001), "River Flow Forecasting Using Artificial Neural Networks." Physics and Chemistry of the Earth, Part B: Hydrology, Oceans and Atmosphere, 26(1), pp. 1-8.
Dybowski, R. (1997), "Assigning confidence intervals to neural network predictions." Technical report, Division of Infection (St Thomas’ Hospital), King’s CollegeLondon.
Eckhardt, K., Breuer, L. and Frede, H. G. (2003), "Parameter uncertainty and the significance of simulated land use change effects." Journal of Hydrology, 273, pp. 164-176.
Efron, B. and Tibshirani, R. J. (1993), An Introduction to the Bootstrap, Chapman & Hall, New York.
Hornik, K., Stinchcombe, M. and White, H. (1989), "Multilayer feedforward networks are universal approximators." Neural networks, 2, pp. 359-366.
Jang, J. S. R. and Gulley, N. (1995), The Fuzzy Logic Toolbox for Use with MATLAB, The Mathworks Inc, Natick, MA.
Jang, J. S. R. and Sun, C. T. (1995), "Neuro-Fuzzy Modeling and Control." Proceedings of the IEEE, 83, pp. 378-406.
Jang, J. S. R. (1993), "ANFIS: Adaptive-Network-Based Fuzzy Inference System." IEEE Transactions on Systems, Man, AND Cybernetics, 23(3), pp. 665-685.
Jang, J. S. R., Sun, C. T. and Mizutani, E. (1997), Neuro-fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice-Hall, New Jersey.
Kumar, D. N., Raju, K. S. and Sathish, K. (2004), "River Flow Forecasting Using Recurrent Neural Network." Water Resources Management, 18, pp. 143-161.
Maier, H. R. and Dandy, G. C. (2000), "Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications." Journal of Hydrology, 15, pp. 101-124.
Marce, R., Comerma, M., García, J. C. and Armengol, J. (2004), "A neuro-fuzzy modeling tool to estimate fluvial nutrient loads in watersheds under time-varying human impact." Limnology and Oceanography: Methods, 2, pp. 342-355.
Nayak, P. C., Sudheer, K. P., Rangan, D. M. and Ramasastri, K. S. (2004), "A neuro-fuzzy computing technique for modeling hydrological time series." Journal of Hydrology, 291, pp. 52-66.
Nayak, P. C., Sudheer, K. P, Rangan, D. M, and Ramasastri, K. S. (2005), "Short-term flood forecasting with a neurofuzzy model." Water Resources Research, 41, pp. 2517-2530.
Sajikumar, N. and Thandaveswara, B. S. (1999), "A non-linear rainfall-runoff model using an artificial neural network." Journal of Hydrology, 216, pp. 32-55.
Sugeno, M. and Yasukawa, T. (1993), "A fuzzy-logic based approach to qualitative modelling." IEEE Transactions on Fuzzy Systems, 1(1), pp. 7-31.
Tang, Z. and Fishwick, P. A. (1993), "Feedforward neural nets as models for time series forecasting." ORSA Journal on Computing, 5(4), pp. 374-385.
Tibshirani, R. (1994), "A Comparison of Some Error Estimates for Neural Network Models." Technical Working Paper No. 94-10, Department of Statistics, University of Toronto.
Valenca, M. J. S., Ludermir, T. B. and Valenca, A. C. B. (2005), "River Flow Forecasting for Reservoir Management Through Neural Networks." In: The Fifth International conference on Hybrid Intelligent Systems, Rio de Janeiro. Proceedings of HIS05. Los Alamitos: IEEE Computer Society, p. pp. 545-547.
Yager, R. and Filev, D. (1994), "Generation of fuzzy rules by mountain clustering." Journal of Intelligent and Fuzzy Systems, 2(3), pp. 209-219.
Zadeh, L. A. (1965), "Fuzzy sets." Information Control, 8(3), pp. 338-353.
Zealand, C. M., Burn, D. H. and Simonovic, S. P. (1999), "Short term streamflow forecasting using artificial neural network." Journal of Hydrology, 214, pp. 32-48.