نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانش‌آموخته دکتری مهندسی منابع آب، دانشکده کشاورزی، دانشگاه ارومیه
2 استادیار، دانشکده کشاورزی، دانشگاه ارومیه
3 استاد، دانشکده کشاورزی دانشگاه ارومیه
4 دانشیار، دانشکده محیط زیست، دانشگاه صنعتی ارومیه
چکیده
تخمین صحیح و دقیق جریان رودخانه می‌تواند نقش مهمی در کاهش اثرات ناشی از خسارات سیلاب ایفا کند. در این تحقیق، از مدل برنامه‌ریزی بیان‌ژن (GEP) و شبکه بیزین (BN) برای پیش‌بینی جریان روزانه رودخانه مهاباد واقع در حوزه آبخیز دریاچه ارومیه استفاده شد. بر این اساس، از چهار الگوی ورودی با تأخیرهای یک تا چهار روزه برای پیش‌بینی مقادیر جریان روزانه در زمان t+1 در یک دوره 23 ساله استفاده و از 75 درصد داده‌ها به‌منظور آموزش مدل‌ها و از 25 درصد باقی‌مانده برای مرحله آزمون استفاده شد. نتایج نشان داد که الگوی برتر در هر دو روش، مدل با مقادیر ورودی تا سه گام زمانی تأخیر می‌باشد. همچنین، بر اساس سه شاخص ارزیابی ضریب همبستگی (R)، مجذور میانگین مربعات خطا (RMSE) و ضریب نش-ساتکلیف (E) در مرحله آزمون، روش برنامه‌ریزی بیان ژن با آماره‌های ارزیابی 2.71=R=0.902 ،RMSE و 0.812=E نسبت به روش شبکه بیزین با آماره‌های ارزیابی 2.679=R=0.905 ،RMSE و 0.817=E دارای دقت بالاتری می‌باشد. در حالت کلی، هر دو روش دارای دقت قابل قبول و نسبتاً یکسان هستند، ولی به‌دلیل مدل‌سازی آسان‌تر روش شبکه بیزین این مدل می‌تواند به‌عنوان یک روش کارآمد در پیش‌بینی جریان رودخانه‌ها مورد استفاده قرار گیرد.
کلیدواژه‌ها
عنوان مقاله [English]
Daily river flow estimation based on intelligent models, case study: Mahabad River
نویسندگان [English]
- Abbas Abbasi 1
- Keivan Khalili 2
- Javad Behmanesh 3
- Akbar Shirzad 4
1 PhD, Faculty of Agriculture, Urmia University, Urmia, Iran
2 Assistant Professor, Faculty of Agriculture, Urmia University, Urmia, Iran
3 Professor, Faculty of Agriculture, Urmia University, Urmia, Iran
4 Associate Professor, Faculty of Environment, Urmia University of Technology, Urmia, Iran
چکیده [English]
The correct and accurate estimation of river flow can play an important role in reducing the effects of flood damage. In this research, Gene Expression Programming (GEP) model and Bayesian Network (BN) were used to predict daily flow of Mahabad River in Urmia Lake Basin. Accordingly, four input models with a delay of one to four days used to estimate daily flow at time t+1 over a 23-years period and 75% of data was used to train the models and 25% of the remaining data was used for the test stage. Results showed that the best model in both methods was the input pattern with three-time lags. Also, based on the correlation coefficient (R), Root Mean Square Error (RMSE) and Nash-Sutcliffe (E) coefficient in the test stage of the GEP method with R=0.902, RMSE=2.71(m3s-1) and E=0.812 compared to the BN method with R=0.905, RMSE=2.679(m3s-1( and E=0.817 is more accurate. In general, both methods have acceptable accuracy and are they relatively similar, but because of the simpler modeling, Bayesian Network method can be used as an efficient method for predicting river flow.
کلیدواژه‌ها [English]
- Bayesian Network
- Flood
- Gene Expression Programming
- Prediction
- Urmia Lake
- Ahmadi, F., F. Radmanesh and R. Mirabbasi Najafabadi. 2016. Comparing the performance of support vector machines and bayesian networks in predicting daily river flow, case study: Barandoozchay River. Journal of Water and Soil Conservation, 22(6): 171-186 (in Persian).
- Ahmadi, F., F. Radmanesh and R. Mirabbasi Najafabadi. 2016. Application of bayesian networks and genetic programming for predicting daily river flow, case study: Barandoozchay River. Irrigation Sciences and Engineering, 39(4): 213-223 (in Persian).
- Awchi, T.A. 2014. River discharges forecasting in northern Iraq using different ANN techniques. Water Resources Management, 28(3): 801–814.
- Box, G.E., G.M. Jenkins and G.C. Reinsel. 2011. Time series analysis: forecasting and control (Vol. 734). John Wiley and Sons, 712 pages.
- Brandt, G. and H.J. Henriksen. 2003. Protection of drinking water sources for quality and quantity. Groundwater protection in the greater copenhagen area. In Future Scenarios for Water Management in Europe. FIRMA Conference, 19-20 February, Barcelona,
- Dorado J., J.R. Rabunal, A. Pazos, D. Rivero, A. Santos and J. Puertas. 2003. Prediction and modeling of the rainfall-runoff transformation of a typical urban basin using ANN and GP. Applied Artificial Intelligence, 17: 329-343.
- Ferreira, C. 2001. Gene expression programming: a new adaptive algorithm for solving problems. Complex System, 13(2): 87–129.
- Ghorbani, M.A. and R. Dehghani. 2016. Application of bayesian neural networks, support vector machines and gene expression programming analysis of monthly rainfall-runoff, case study: Kakareza River. Irrigation Sciences and Engineering, 39: 125-138 (in Persian).
- Guven, A. 2009. Linear genetic programming for time-series modeling of daily flow rate. Journal of Earth System Science, 118(2): 157-173.
- He, Z., X. Wen, H. Liu and J. Du. 2014. A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semi-arid mountain region. Journal of Hydrology, 509: 379-386.
- Khu, S.T., S.Y. Liong, V. Babovic, H. Madsen and N. Muttil. 2001. Genetic programming and its application in real-time runoff forming. Journal of American Water Resources Association, 37(2): 439-451.
- Neapolitan, R.E. 2003. Learning Bayesian networks. Prentice Hall Series in Artificial Intelligence, 693 pages.
- Reggiani, P. and A.H. Weerts. A Bayesian approach to decision-marking under uncertainty: an application to real-time forecasting in the river Rhine. Journal of Hydrology, 356: 56-69.
- Rezaei, E., B. Shahinejad and H. Yonesi. 2019. Analysis and evaluation of effective parameters on the amount of total dissolved solids in rivers. Watershed Engineering and Management, 11(1): 147-165 (in Persian).
- Terzi, O. and G. Ergin. 2014. Forecasting of monthly river flow with autoregressive modeling and data-driven techniques. Neural Computing and Applications, 25(1): 179-188.
- Zhang, H., V.P. Singh, B. Wang and Y. Yu. 2016. CEREF: a hybrid data-driven model for forecasting annual streamflow from a socio-hydrological system. Journal of Hydrology, 540: 246-256.
)