پیش‌بینی ضریب انتشار طولی در رودخانه‌های طبیعی با مدل توسعه یافته شبکه عصبی

نوع مقاله: یاداشت‌ فنی

نویسندگان

1 دانشجوی دکترای مهندسی محیط زیست، دانشکده محیط‌زیست، دانشگاه تهران

2 استادیار، دانشکده محیط زیست، دانشگاه تهران

3 کارشناس ارشد مهندسی شیمی، پژوهشگاه صنعت نفت، تهران

چکیده

هدف اصلی این مقاله پیش‌بینی ضریب انتشار طولی در رودخانه‌های طبیعی با استفاده از مدل توسعه داده شده شبکه عصبی مصنوعی بر مبنای توابع آموزش شبه-نیوتنی بود. به این منظور از اطلاعات هیدرولیکی و هندسه جریان استفاده گردید. مجموع کل اطلاعات مورد استفاده در این تحقیق، 100 سری داده بود که به سه دسته آموزش، دسته نظارت بر آموزش و دسته آزمایش تقسیم شد. در این تحقیق، ابتدا با دیدی انتقادی به مرور برخی از مهم‌ترین تحقیقات انجام گرفته در این زمینه پرداخته شد که نتیجه آن نمایان ساختن اشکالات موجود در برخی از این مطالعات بود. در گام بعدی به‌منظور ارائه مدلی که قادر به مدل‌سازی ضریب انتشار طولی در رودخانه‌های طبیعی باشد، رویکردی جدید از شبکه عصبی بر مبنای توابع آموزش شبه-نیوتنی که کمتر مورد توجه محققان بوده، معرفی شد. در نهایت نیز با بررسی نقش این دسته از توابع آموزش بر عملکرد شبکه، بهترین ساختار شبکه برای این منظور پیشنهاد گردید. نتایج به‌دست آمده از این تحقیق بیانگر دقت قابل قبول مدل پیشنهادی بود به‌طوری که مقادیر ضریب تعیین و میانگین قدرمطلق خطا برای مرحله آزمایش به‌ترتیب معادل 0/85 و 53 بود.

کلیدواژه‌ها


عنوان مقاله [English]

Predicting the Longitudinal Dispersion Coefficient in Natural Streams Using Developed Artificial Neural Network Model

نویسندگان [English]

  • Roohollah Noori 1
  • Abdulreza Karbassi 2
  • Hamid Mehdizadeh 3
1 Ph.D. Student of Environmental Eng., Dept. of Environmental Eng., University of Tehran
2 Assist. Prof., Dept. of Environmental Eng. University of Tehran
3 M.Sc. of Chemistry Eng., Research Institute of Petroleum Industry, Tehran
چکیده [English]

The main objective of the present work is to predict the longitudinal dispersion coefficient in natural streams using a neural network (NN) model which was developed based on Quasi-Newton training functions. For this reason, we used the hydraulic and geometric data easily obtained in natural streams. A total number of 100 data sets was used which were split into three subsets: training, validation, and testing sets.The most cited literature in the field was first reviewed  in an attempt to identify possible deficiencies and inadequacies in previous studies. In a second stage, a new approach less commonly used by researchers, i.e. the NN model based on Quasi-Newton training functions, was employed for predicting the longitudinal dispersion coefficient in natural streams. Finally, the effect of Quasi-Newton training function on the performance of the NN model was investigated and the best architecture was selected for the model developed. The results obtained in this study showed that the proposed model enjoys a satisfactory level of accuracy. The two statistics of the model, i.e. determination coefficient and mean absolute error in testing step, were found to be equal to 0.85 and 53, respectively.

کلیدواژه‌ها [English]

  • Longitudinal Dispersion Coefficient
  • Artificial Neural Network
  • Quasi-Newton Training Functions
  • prediction
1- Fischer, H. B., List, E. J., Koh, R. C. Y., Imberger, J., and Brooks, N. H. (1979). Mixing in inland and coastal waters, 1st Ed., Academic,New York.

2- Iwasa, Y., and Aya, S. (1991). “Predicting longitudinal dispersion coefficient in open-channel flows.” Proc. Int. Symp. on Environmental Hydrology, Hong Kong, 505-510.

3- Seo, I.W., and Cheong, T. S. (1998). “Predicting longitudinal dispersion coefficient in natural Streams.” J. of Hydraulics Eng., 124 (1), 25-32.

4- Kashefipour, M. S., and Falconer, R. A. (2002). “Longitudinal dispersion coefficients in natural channels.” Water Res., 36(6), 1596-1608.

5- 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.

6- Noori, R., Karbassi, A.R., Farokhnia, A., and Dehghani, M. (2009). “Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques.” Environmrntal Engineering Science, 26 (10), 1503-1510.

7- Noori, R., Karbassi, A., Mehdizadeh, H., Vesali-Naseh, M. and Sabahi, M. S. (2010). “Development of a framework for predicting the longitudinal dispersion coefficient in natural streams using artificial neural network.” Environmental Progress and Sustainable Energy, DOI: 10.1002/ep.10478.

8- Huber, P.J. (1981). Robust statistics, 1st Ed., John Wiley and Sons Inc.,New York.

9- Deng, Z. Q., Singh, V. P., and Bengtsson, L. (2001). “Longitudinal dispersion coefficient in straight rivers.” J. Hydraul. Eng., 127(11), 919-927.

10- Fischer, H. B. (1975). “Discussion of simple method for predicting dispersion in streams.” J. of Environ Eng Div ASCE, 101, 453-455.

11- Haykin, S. (1999). Neural networks: A comprehensive foundation, 2nd Ed.,Prentice Hall,New Jersey.

12- Maier, H.R., and Dandy, G.C. (2000). “Neural networks for the prediction and forecasting water resources variables: A review of modeling issues and applications.” J. Env. Model. Soft., 15 (23), 101-124.

13- Noori, R., Farokhnia, A., Morid, S., and Riahi Madvar, H. (2008). “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)

14- Noori, R., Hoshiyaripour, G.A., Ashrafi, K., and Araabi, B.N. (2009). “Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration.” Atmospheric Environment, 44 (4), 476-482.

15- Noori, R., Khakpour, A., Omidvar, B., and Farokhnia, A. (2010). “Comparison of ANN and principal component analysis-multivariate linear regression models for predicting the river flow based on developed discrepancy ratio statistic.” Expert Systems with Applications, 37 (8), 5856-5862.

16- Noori, R., Karbassi, A.R., and Sabahi, M.S. (2009). “Evaluation of PCA and gamma test techniques on ANN operation for weekly solid waste prediction.” J. of Environmental Management, 91 (3), 767-771.

17- Dennis, J.E., and Schnabel, R.B. (1983). Numerical methods for unconstrained optimization and nonlinear equations, 1st Ed.,Prentice-Hall,New York.

18- Battiti, R., (1992), “First and second order methods for learning: Between steepest descent and Newton’s method.” Neural Computation, 4(2), 141-166.

19- Fletcher, D, and Goss, E. (1993). “Forecasting with neural networks: An application using bankruptcy data.” Inf. Management, 24 (32), 159-167.