تحلیل دقت و عدم قطعیت مدل‌های هوشمند در پیش‌بینی ضریب انتشار طولی رودخانه‌ها

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار، معاونت مؤسسه تحقیقات آب، وزارت نیرو، تهران

2 مؤسسه تحقیقات آب، وزارت نیرو، دانشجوی دکترای مهندسی محیط زیست، دانشکده محیط زیست، دانشگاه تهران

3 کارشناس مؤسسه تحقیقات آب، وزارت نیرو، دانشجوی دکترای مهندسی سازه‌های آبی، دانشگاه تربیت مدرس، تهران

4 مدیرعامل شرکت عمران زیست آزما (CELCO)، دانشجوی دکترای مهندسی محیط زیست، دانشکده محیط زیست، دانشگاه تهران

5 دانشجوی دکترای مهندسی محیط‌زیست، دانشکده محیط‌زیست، دانشگاه‌ تهران

چکیده

پیش‌بینی دقیق ضریب انتشار طولی در رودخانه‌های طبیعی تا حد بسیار زیادی در تعیین توزیع غلظت آلاینده‌ها در چنین محیط‌هایی مؤثر است. عدم قطعیت موجود در نتایج به‌دست آمده از مدل‌های پیش‌بینی می‌تواند در تصمیم‌گیری‌های مناسب برای برخورد با مواد آلاینده در رودخانه‌ها تأثیر منفی داشته باشد. به‌همین دلیل، تحلیل و تعیین عدم قطعیت مدل‌های مورد استفاده برای پیش‌بینی این پارامتر بسیار مفید است. در این تحقیق با توجه به اهمیت این امر، با استفاده از مدل‌های شبکه عصبی (ANN) و نروفازی تطبیقی (ANFIS)، ابتدا مدل مناسب برای پیش‌بینی ضریب انتشار طولی در رودخانه‌های طبیعی ارائه گردید و در ادامه تحلیل عدم قطعیت دو مدل مذکور بر مبنای روش مونت-کارلو انجام شد. برای این منظور از اطلاعات هیدرولیکی و هندسه جریان استفاده گردید. نتایج این تحقیق بیانگر این مطلب بود که اگرچه مدل ANN در پیش‌بینی ضریب انتشار طولی دارای عملکرد خوبی است، اما نتایج این مدل با عدم قطعیت زیادی همراه است. با مقایسه نتایج به‌دست آمده از تحلیل عدم قطعیت دو مدل ANN و ANFIS مشخص گردید که مدلANFIS  نسبت به مدل ANN از عدم قطعیت کمتری برخوردار است و از این لحاظ بر مدل ANN برتری دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Accuracy and Uncertainty Analysis of Intelligent Techniques for Predicting the Longitudinal Dispersion Coefficient in Rivers

نویسندگان [English]

  • Abbas Akbarzadeh 1
  • Roohollah Noori 2
  • Ashkan Farokhnia 3
  • Amir Khakpour 4
  • Mohammad Salman Sabahi 5
1 Assist. Prof., Water Research Institute, Ministry of Energy, Tehran
2 Member of Water Research Institute, Ministry of Energy, Ph.D. Student of Environmental Eng., Dept. of Environmental Eng., Tehran University
3 Member of Water Research Institute, Ministry of Energy, Ph.D. Student of Hydraulic Structures Eng., Tarbiat Modarres University, Tehran.
4 Management Director of CELCO., Ph.D. Student of Environmental Eng., Dept. of Environmental, Tehran University
5 Ph.D. Student of Environmental Eng., Dept. of Environmental, Tehran University
چکیده [English]

Accurate prediction of longitudinal dispersion coefficient (LDC) can be useful for the determination of pollutants concentration distribution in natural rivers. However, the uncertainty associated with the results obtained from forecasting models has a negative effect on pollutant management in water resources. In this research, appropriate models are first developed using ANN and ANFIS techniques to predict the LDC in natural streams. Then, an uncertainty analysis is performed for ANN and ANFIS models based on Monte-Carlo simulation. The input parameters of the models are related to hydraulic variables and stream geometry. Results indicate that ANN is a suitable model for predicting the LDC, but it is also associated with a high level of uncertainty. However, results of uncertainty analysis show that ANFIS model has less uncertainty; i.e. it is the best model for forecasting satisfactorily the LDC in natural streams.

کلیدواژه‌ها [English]

  • Monte-Carlo
  • Longitudinal Dispersion Coefficient
  • Neural Network
  • adaptive neuro-fuzzy inference system
  • Bound Wide Factor
1- Tayfur, G., and Singh, V.P. (2005). “Predicting longitudinal dispersion coefficient in natural streams by artificial neural network.” J. of Hydraulic Engineering, 131 (11) , 991-1000.
2- Kashefipour, M.S., and Falconer, R. A. (2002). “Longitudinal dispersion coefficients in natural channels.” Water Res., 36 (6), 1596-1608.
3- Fischer, B.H. (1975). “Discussion of ‘Simple method for predicting dispersion in streams,’ by R. S. McQuivey and T. N. Keefer.” J. of Environmental Engineering Div., 101 (3), 453-455.
4- Seo I. W., and Cheong, T.S. (1998). “Predicting longitudinal dispersion coefficient in natural Streams.” J. of Hydraulics Engineering, 124 (1), 25-32.
5- Deng, Z.Q., Singh, V.P., and Bengtsson, L. (2001). “Longitudinal dispersion coefficient in straight rivers.”
J. of Hydraulic Engineering, 127 (1), 919-927.
6- Toprak, Z. F., and Cigizoglu, H.K. (2008). “Predicting longitudinal dispersion coefficient in natural streams by artificial intelligence methods.” Hydrol. Process, 22 (20), 4106-4129.
7- Noori, R., Karbassi, A., Farokhnia, A., and Dehghani, M. (2009). “Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques.” Environmental Engineering Science, 26 (10), 1503-1510.
8- Riahi-Madvar, H., Ayyoubzadeh, S.A., Khadangi, E., and Ebadzadeh, M.M. (2009). “An expert system for predicting longitudinal dispersion coefficient in natural streams by using ANFIS.” Expert Systems with Applications, 36 (4), 8589-8596.
9- Kashefipour, M. (2007). “Prediction of longitudinal dispersion coefficient in natural rivers using artificial neural networks.” Iranian J. of Hydraulic, 3, 15-25. (In Persian)
10- Riahi madvar, H., and Ayyaoubzadeh, S. A. (2008). “Estimating longitudinal dispersion coefficient of pollutants using adaptive neuro-fuzzy inference system.” J. of Water and Wastewater, 67, 34-46. (In Persian)
11- Tibshirani, R. (1994). A comparison of some error estimates for neural network models, No. 94-10, Technical Working Report, Department of Statistics, University of Toronto.
12- Dybowski, R. (1997). Assigning confidence intervals to neural network predictions, Technical report, Division of Infection (St Thomas’ Hospital), King’s College, London.
13- 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, 342-355.
14- Aqil, M., Kita, I., Yano, A., and Nishiyama, S. (2007). “Analysis and prediction of flow from local source in a river basin using a Neuro-fuzzy modeling tool.” J. of Environmental Management, 85 (1), 215-223.
15- Noori, R., Abdoli, M.A., Farokhnia, A., and Abbasi, M. (2009). “Results uncertainty of solid waste generation forecasting by hybrid of wavelet transform-ANFIS and wavelet transform-neural network.” Expert Systems with Applications, 36 (6), 9991-9999.
16- Fischer, H.B. (1968). “Dispersion predictions in natural streams.” J. of Hydraulic Division, 94(5), 927-943.
17- Godfrey, R.G., and Frederick, B.J. (1970). “Stream dispersion at selected sites.” U.S. Geological Survey, Prof. Paper 433-K, WashingtonD.C.
18- Yotsukura, N., Fischer, H.B., and Sayre, W.W. (1970). “Measurement of mixing characteristics of the Missouri River between Sioux City, Iowa and Plattsmouth, Nebraska.” US Geological Survey Water-Supply, Paper 1899-G, Washington, D.C.
19- McQuivey, R.S., and Keefer, T.N. (1974). “Simple method for prediction dispersion in streams.” J. of Environment Engineering, 100 (4), 997-1011.
20- Nordin, C.F., and Sabol, G.V. (1974). “Empirical data on longitudinal dispersion in rivers.” U.S. Geological Survey Water Resources Investigation, Washington D.C., 20-74.
21- Haykin, S. (1999). Neural networks: A comprehensive foundation, 2nd Ed., Prentice Hall, New Jersey.
22- Noori, R., Abdoli, M.A., Jalili-Ghazizade, M., and Samifard, R. (2009). “Comparison of ANN and PCA based multivariate linear regression applied to predict the weekly municipal solid waste generation in Tehran.” Iranian J. of Public Health, 38 (1), 74-84.
23- Jalili-Ghazizade, M., and Noori, R. (2008). “Prediction of municipal solid waste generation by use of artificial neural network: A case study of Mashhad.” International J. of Environmental Research, 2 (1), 22-33.
24- Noori, R., Farokhnia, A., Morid, S., and Riahi Madvar, H. (2009). “Effect of input variables preprocessing in artificial neural network on monthly flow prediction by PCA and wavelet transformation.” J. of Water and Wastewater, 69, 13-22. (In Persian)
25- Jang, J.S.R., and Gulley, N. (1995). The fuzzy logic toolbox for use with MATLAB, Mathworks Inc., Massachusetts.
26- 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.
27- Jang, J.S.R. (1991). “Rule extraction using generalized neural networks.” Proc. of the 4th IFSA World Congress, 82-86.
28- Eckhardt, K., Breuer, L., and Frede, H.G. (2003). “Parameter uncertainty and the significance of simulated land use change effects.” J. of Hydrology, 273 (1-4), 164-176.
29- Efron, B., and Tibshirani, R.J. (1993). An introduction to the bootstrap, Chapman and Hall, New York.
30- 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.” J. of Hydrology, 333 (2-4), 413-430.
31- Jang, J. S. R., and Sun, C. T. (1995). “Neuro-fuzzy modeling and control.” Proc. of the IEEE, 83, 378-406.
32- Chiu, S.L. (1994). “Fuzzy model identification based on cluster estimation.” J. of Intelligent and Fuzzy Systems, 2 (3), 267-278.