مدل سازی بارش – رواناب روزانه رودخانه دره رود واقع در استان اردبیل

نوع مقاله: مقاله پژوهشی

نویسندگان

1 استادیار گروه مهندسی آب دانشگاه محقق اردبیلی

2 استادیار گروه علوم و مهندسی آب، دانشکده کشاورزی، دانشگاه کردستان.

3 دانش آموخته کارشناسی مهندسی آب دانشگاه محقق اردبیلی

چکیده

مدل‌سازی بارش- رواناب یکی از پراهمیت‌ترین موضوعات در مدیریت منابع آب‌های سطحی برای اتخاذ تدابیر مناسب در مواقع سیلاب و بروز خشک‌سالی‌ها است. در این تحقیق از مدل‌های شبکه­های عصبی مصنوعی، برنامه­ریزی بیان ژن، موجک- عصبی و حداقل مربعات ماشین بردار پشتیبان به­منظور تخمین جریان روزانه رودخانه دره­رود استفاده شد. داده‌های دبی و بارش روزانه ایستگاه مشیران واقع بر رودخانه مذکور و در بالادست سد عمارت به­کار گرفته شد. نتایج نشان داد که الگوی تعریف شده بر اساس دبی روز قبل و بارش همان روز می­تواند بهترین برآورد را از رواناب روزانه داشته باشد. هم­چنین نتایج بیانگر عملکرد قابل قبول مدل­ها و برتری مدل موجک- عصبی با بیشترین ضریب همبستگی (952/0=R)، کمترین ریشه میانگین مربعات خطا (589/1=RMSE) و ضریب نش ساتکلیف برابر 905/0 در مرحله صحت­سنجی بود. در برآورد دبی بیشینه نیز مدل مذکور با میانگین خطای نسبی 97/25 درصد، از خطای کمتری نسبت به سایر مدل­ها برخوردار بود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Daily Rainfall – Runoff Modeling of Darreh-Rud River in Ardabil Province, Iran

نویسندگان [English]

  • Mohammad Reza Nikpour 1
  • Hadi Sanikhani 2
  • Sajad Mahmodi Babelan 3
  • Saeid Nastarani Amuqin 3
1 Assistant Professor, Department of Water Engineering, University of Mohaghegh Ardabili.
2 Assistant Professor, Department of Water sciences and Engineering, Faculty of Agriculture, University of Kurdistan, Sanandaj, Iran.
3 Graduate Student, Department of Water Engineering, Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili, Ardabil, Iran.
چکیده [English]

Rainfall- runoff is one of the most complicated hydrological processes that is affected by various physical and hydrological variables. Therefore, understanding and predicting runoff formation processes and their transfer to the outlet point of the watershed is one of the most important issues of hydrological sciences (Salajegheh et al., 2009). Botsis et al., (2011) simulated daily rainfall-runoff of a catchment in the California, USA. They compared the performance of SVM with three types of kernel function with ANN. Finally, the SVM had a more accurate simulation of rainfall-runoff. Nourani et al., (2009) applied the hybrid of wavelet-ANN to model rainfall-runoff of Lighvan-Chay basin in Iran. The results showed that the proposed model is capable to predict long-term and short-term rainfall events due to the use of the time series with multiple scales as input layer of ANN. Darreh-rud river as the most important branch of Aras border region in Iran, is one of the main rivers of Ardabil province and the main source of water supply in different parts of the province. On the other hand, the Emarat reservoir dam is under construction on the river. Therefore, ANN, WNN, GEP and LS-SVM models were evaluated for estimating the inflow of Emarat dam (located on Darreh-rud river, Ardabil province).

کلیدواژه‌ها [English]

  • Gene Expression programming
  • Estimation of Streamflow
  • Least-squared Support Vector Machines
  • Artificial Neural Networks
  • Hybrid of Wavelet-ANN

1-    Aytek, A. and Alp, M., 2008. An application of artificial intelligence for rainfall-runoff modeling. Journal of Earth System Science, 117(2), pp.145-155.

 

2-    Behzad, M. Asghari, K. Eazi, M. and Palhang, M., 2009. Generalization performance of support vector machines and neural networks in runoff modeling. Expert Systems with Applications, 36(4), pp.7624-7629.

 

3-    Botsis, D. Latinopoulos, P. and Diamantaras, K., 2011. Rainfall-Runoff Moeling Using Suport Vector Regression and Artificial Neural Networks. In 12th International Conference on Environmental Science and Technology, Rhodes, Greece.

 

4-    Ferreira, C., 2006. Automatically defined functions in gene expression programming. In Genetic Systems Programming. Springer Berlin Heidelberg.

 

5-    Ferreira, C., 2001. Gene Expression Programming: a new adaptive algorithm for solving problems. Complex Systems, 13(2), pp.87–129.

 

6-    Ghorbani, M.A. and Dehghani, R., 2015. Application of bayesian neural networks, support vector machines and gene expression programming analysis of rainfall - runoff monthly (case study: Kakarza river). Irrigation Sciences and Engineering, 39(2), pp.125–138. (In Persian).

 

7-    He, Z. Wen, X. Liu, H. and Du, J., 2014. A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region. Journal of Hydrology, 509, pp.379-386.

 

8-    Jayawardena, A.W. Muttil, N. and Fernando, T.M.K.G., 2005. Rainfall-runoff modeling using genetic programming. In International Congress on Modeling and Simulation Society of Australia and New Zealand.

 

9-    Kisi, O., 2008. Stream flow forecasting using neuro‐wavelet technique. Journal of Hydrological Processes, 22(20), pp.4142-4152.

 

10- Marofi, S. Amir-Moradi, K. and Parsafar, N., 2012. River flow prediction using Artificial Neural Network and Wavelet Neural Network models (Case study: Barandozchay River). Water and Soil Science, 23(3), pp.93–103. (In Persian).

 

11- Nabizadeh, M. Mosaedi, A. and Dehghani, A.A., 2012. Intelligent estimation of stream flow by Adaptive Neuro-Fuzzy Inference System). Water and Irrigation Management, 2(1), pp.69–80. (In Persian).

 

12- Nourani, V. Komasi, M. and Mano, A., 2009. A multivariate ANN-wavelet approach for rainfall–runoff modeling. Journal of Water Resources Management, 23(14), pp.2877-2894.

 

13- Rezaei, E. Khashei-Siuki, A. and Shahidi A., 2014. Design of groundwater level monitoring network, using the model of least squares support vector machine (LS-SVM). Iranian Journal of Soil and Water Research, 45(4), pp.389-396. (In Persian).

 

14- Salajegheh, A. Fathabadi, A. and Mahdavi, M., 2009. Investigation on the efficiency of neuro-fuzzy method and statistical models in simulation of rainfall-runoff process. Journal of Range and Watershed Management, 62(1), pp.65-79.

 

15- Shafiee-Jood, M. Abrishamchi, A. and Salavitabar, A., 2012. Evaluation of water resources development plans in multi-reservoir darehrood sub catchment system using performance indices. Journal of Water and Wastewater, 3, pp.22-32. (In Persian).

 

16- Shu, C. and Ouarda, T.B.M.J., 2008. Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system. Journal of Hydrology, 349(1), pp.31-43.

 

17- Soltani, A. Ghorbani, M.A. Fakheri-Fard, A. Darbandi, S. and Farsadizadeh, D., 2010. Genetic programming andi application in rainfall-runoff modeling. Water and Soil Science, 20(4), pp.62–71. (In Persian).

 

18- Suykens, J.A. De Brabanter, J. Lukas, L. and Vandewalle, J., 2002. Weighted least squares support vector machines, pp. robustness and sparse approximation. Neurocomputing, 48(1), pp.85-105.

 

19- Taheri, H. and Ghafouri M., 2012. Comparison between active learning method and support vector machine for runoff modeling. Journal of Hydrology and Hydromechanics, 60(1), pp.16-32.

 

20- Tokar, A.S. and Markus, M., 2000. Precipitation-runoff modeling using artificial neural networks and conceptual models. Journal of Hydrologic Engineering, 5(2), pp.156-161.

 

21- Vapnic, V.N., 1998. Statistical Learning Theory. Wiley, New York, USA.

 

22- Yu, P.S. Chen, S.T. and Chang, I.F., 2006. Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328(3), pp.704-716.