ارزیابی عملکرد روش‌های داده‌گرا در تخمین بار کل رسوبی رودخانه های شنی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشیار گروه مهندسی عمران آب دانشگاه تبریز

2 گروه مهندسی آب، داشکده عمران، دانشگاه تبریز، تبریز، ایران

چکیده

انجام مطالعات فراوان در رابطه با انتقال رسوب و به‌ویژه پیش­بینی این پدیده نشانگر اهمیت بسیار بالای آن در علوم مرتبط با مهندسی و مدیریت منابع آب می­باشد. در این بین روش­های هوشمند در سال­های اخیر به طور موفقیت‌آمیزی در پیش­بینی بار بستر، بار معلق و همچنین بار کل رسوب به کار گرفته شده است. با این حال با توجه به کمبود داده­های مرتبط به بار کل برای رودخانه­های با بستر شنی، مطالعات انجام گرفته در این راستا محدود می­باشد. هدف از تحقیق حاضر استفاده از روش­های قدرتمند ماشین بردار پشتیبان، شبکه­ عصبی مصنوعی و رگرسیون فرآیند گاوسی به منظور پیش­بینی بار کل رسوب در 19 رودخانه شنی واقع در ایالات‌متحده آمریکا و مقایسه نتایج حاصل با روش­های کلاسیک مرسوم می­باشد. بدین منظور پارامترهای بدون بعد مختلفی مبتنی بر هیدرولیک جریان و مشخصات رسوب تعریف و عملکرد روش­های مذکور مورد ارزیابی قرار گرفت. با توجه به نتایج به دست آمده شبکه عصبی مصنوعی با دارا بودن ضریب همبستگی و معیار ناش- ساتکیف به ترتیب برابر با 952/0 R= و 903/0 NSE= برای داده­های صحت­سنجی از عملکرد بهتری نسبت به دو روش دیگر برخوردار می­باشد. در نهایت با انجام تحلیل حساسیت، پارامتر نسبت سرعت متوسط به سرعت برشی جریان به عنوان تأثیرگذارترین پارامتر در پیش­بینی بار کل رسوب معرفی شد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Evaluating the Performance of Data-Driven Methods for Prediction of Total Sediment Load in Gravel-Bed Rivers

نویسندگان [English]

  • kiyoumars roushangar 1
  • Saman Shahnazi 2
1 Associate Professor, Department of Civil Engineering, University of Tabriz, Tabriz, Iran
2 Department of water engineering, Faculty of civil engineering, University of Tabriz, Tabriz, Iran
چکیده [English]

Numerous studies on sediment transport, especially prediction of this phenomenon, indicate its high importance in the sciences related to engineering and water resources management. In recent years, intelligent methods have been applied successfully to predict bed, suspended and total sediment load. However, due to the lack of measured data, limited researches have been done to deal with prediction of total load in gravel-bed rivers. The aim of this study is to apply Support Vector Machine (SVM), Artificial Neural Network (ANN) and Gaussian Process Regression (GPR) to predict total sediment load for 19 gravel-bed rivers and to compare the obtained results with well- known classic methods. For this purpose, different non-dimensional parameters based on hydraulic condition and sediment characteristics were defined and the performance of these methods was evaluated. According to the obtained results, the ANN model with correlation coefficient of R =0.952 and Nash–Sutcliffe efficiency (NSE=0.903) showed a better performance as compared to the other methods. Finally, by performing sensitivity analysis, the ratio of mean flow to shear velocity was introduced as the most effective parameter in predicting total sediment load.

کلیدواژه‌ها [English]

  • Total load
  • Gravel-bed rivers
  • Support vector machine
  • Artificial Neural Network
  • Gaussian process regression
Ackers, P. and White, W.R. (1973). Sediment transport: new approach and analysis. Journal of the Hydraulics Division, 99(hy11).

Bhattacharya, B., Price, R. K. and Solomatine, D. P. (2007). Machine learning approach to modeling sediment transport. Journal of Hydraulic Engineering, 133(4), 440-450.

Brownlie, W. R. (1981). Prediction of flow depth and sediment discharge in open channels. Report No. KH-R-43A, Keck Laboratory of Hydraulics and Water Resources, California Institute of Technology, Pasadena, CA, USA.

Chang, C. K., Azamathulla, H. M., Zakaria, N. A. and Ab Ghani, A. (2012). Appraisal of soft computing techniques in prediction of total bed material load in tropical rivers. Journal of earth system science, 121(1), 125-133.

Choi, S.U. and Lee, J. (2015). Assessment of total sediment load in rivers using lateral distribution method. Journal of Hydro-environment Research, 9(3): 381-387.

Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3): 273-297.

Doğan, E., Yüksel, İ. and Kişi, Ö. (2007). Estimation of total sediment load concentration obtained by experimental study using artificial neural networks. Environmental fluid mechanics, 7(4):271-288.

Einstein, H.A. (1950). The bed-load function for sediment transportation in open channel flows (Vol. 1026). Washington DC: US Department of Agriculture.

Engelund, F. and Hansen, E. (1967). A monograph on sediment transport in alluvial streams. Technical University of Denmark 0stervoldgade 10, Copenhagen K.

Falamaki, A., Eskandari, M. Baghlani, A., and Ahmadi, S. A. (2013). Modeling total sediment load in rivers using artificial neural networks. Journal of Soil and Water Resources Conservation. 2(3), 13-26. (In Farsi)

Karim, F. (1998). Bed material discharge prediction for nonuniform bed sediments. Journal of Hydraulic Engineering, 124(6):597-604.

Khorram, S. and Ergil, M. (2010). A Sensitivity Analysis of Total‐Load Prediction Parameters in Standard Sediment Transport Equations. JAWRA Journal of the American Water Resources Association, 46(6):1091-1115.

King, J.G., Emmett, W.W., Whiting, P.J., Kenworthy, R.P. and Barry, J.J. (2004). Sediment transport data and related information for selected coarse-bed streams and rivers in Idaho. General technical report. U. S. Department of Agriculture, Forest Service, Rocky Mountain Research Station, (131):26.

Kumar, B. (2012). Neural network prediction of bed material load transport. Hydrological sciences journal, 57(5), 956-966.

Molinas, A. and Wu, B. (2001). Transport of sediment in large sand-bed rivers. Journal of hydraulic research, 39(2):135-146.

Okcu, D., Pektas, A.O. and Uyumaz, A. (2016). Creating a non-linear total sediment load formula using polynomial best subset regression model. Journal of Hydrology, 539:662-673.

Rasmussen, C. E. and Williams, C. K. (2006). Gaussian process for machine learning. MIT press.

Roushangar, K. and Ghasempour, R. (2017). Prediction of non-cohesive sediment transport in circular channels in deposition and limit of deposition states using SVM. Water Science and Technology: Water Supply, 17(2):537-551.

Roushangar, K., Javan, F. P. (2014). Evaluation of artificial intelligent technique in prediction of sediment transport rate in Ajichai river. Journal of Geographic Space. 14(46), 173-197. (In Farsi)

Roushangar, K., Mehrabani, F.V. and Shiri, J. (2014). Modeling river total bed material load discharge using artificial intelligence approaches (based on conceptual inputs). Journal of hydrology, 514:114-122.

Sahraei, S., Alizadeh, M. R., Talebbeydokhti, N. and Dehghani, M. (2017). Bed material load estimation in channels using machine learning and meta-heuristic methods. Journal of Hydroinformatics, 20(1):100-116.

Shafai Bejestan, M. (2009). Basic theory and practice of Hydraulic of sediment transport. Shahid Chamran University.

Shen, H. W, and Hung, C. S. (1972). An engineering approach to total bed material load by regression analysis. Proc., Sedimentation Symposium, Chap. 14, 14.1–14.7.

Yang, C. T. (2006). Reclamation managing water in the west. Erosion and sedimentation manual. US Department of the Interior, Bureau of Reclamation.

Yang, C.T., Marsooli, R. and Aalami, M.T. (2009). Evaluation of total load sediment transport formulas using ANN. International Journal of Sediment Research, 24(3):274-286.

Zakaria, N. A., Azamathulla, H. M., Chang, C. K. and Ghani, A. A. (2010). Gene expression programming for total bed material load estimation—a case study. Science of the total environment, 408(21): 5078-5085.