با همکاری انجمن آبخیزداری ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 ارشد

2 دانشجو

3 استاد

چکیده

شبیه‌سازی فرآیند بارش -رواناب به عنوان مهمترین گام در مطالعات مهندسی آب و مدیریت منابع آب است. برنامه‌ریزی بهره‌برداری از منابع آبهای سطحی و زیرزمینی، ساماندهی رودخانه‌ها و هشدار سیل نیاز به پیش‌بینی آبدهی رودخانه و رواناب حوزه آبخیز دارد. در مطالعه حاضر به منظور مدل‌سازی بارش- رواناب از روش شبکه عصبی توسعه یافته با فیلتر کالمن (EKFNN) استفاده شد و سپس نتایج با روش برنامه‌ریزی بیان ژن (GEP) که در اکثر مطالعات اخیر عملکرد خوبی از خود در مدل‌سازی بارش- رواناب نشان داده بود، مقایسه گردید. داده‌های مورد استفاده در این مطالعه بارش و رواناب روزانه ایستگاه‌های باران‌سنجی و آب‌سنجی دشت ملایر که شامل ایستگاه‌های پیهان، مرویل و نامیله است در طول دوره آماری 1380 تا 1392 می‌باشد. نتایج نشانگر برتری مدل EKFNNنسبت به مدل‌ دیگر در مدل‌سازی جریان روزانه رودخانه در دشت ملایر داشت. علاوه بر این سرعت اجرای مدل برنامه‌ریزی بیان ژن بیشتر بود و در زمان کوتاهی قادر به ارائه نتایج بود. در نهایت مدل EKFNN به عنوان مدل برتر برای دشت ملایر انتخاب شد.

کلیدواژه‌ها

عنوان مقاله [English]

Evaluation of Extended Kalman Filter-based Neural Network (EKFNN) model and Gene Expression Planning in Rainfall-Runoff Modelin

نویسندگان [English]

  • asrin hosseini 1
  • mohammad reza golabi 2
  • safar marofi 3
  • nasim khalediyan 1
  • mohammad solatani 2

1 MSc

2 student

3 professor

چکیده [English]

Simulation of the rainfall-runoff process is the most important step in water engineering and water resource management studies. Exploitation of surface water and underground water resources, river management and flood warning requires prediction of river and runoff discharges of the watershed. In this study, Extended Kalman Filter-based Neural Network (EKFNN) method was used for rainfall-runoff modelling. Then, the results were compared with the Gene Expression Planning method, which showed good performance in rainfall-runoff modelling in most recent studies. The data used in this study is related to daily runoff and rainfall of the rain gauge and hydrometric stations of Malayer plain which includes Peyhan, Marvil and Namyleh stations, during the period of 2001 to 2013. The results indicated that the EKFNN model was superior to GEP model in daily river flow modelling in Malayer plain. In addition, the speed of implementation of the Gene Expression Planning model was greater and was able to present results in a short time. Finally, EKFNN model was selected as the superior model for Malayer plain.

کلیدواژه‌ها [English]

  • Rainfall
  • Runoff
  • EKFNN
  • GEP
  • Malayer
  1.  

    1. Ahmadi, F., F. Radmanesh and R. Mirabbasi. 2015. Comparison between genetic programming and support vector machine methods for daily river flow forecasting, case study: Barandoozchay River. Journal of Water and Soil, 28(6): 1162-1171 (in Persian).
    2. Alami, M.T., S. Sadeghfam, M.H. Fazelifard and L. Naghipour. 2014. Modeling the data series. University of Tabriz, 304 pages (in Persian).
    3. Danandeh Mehr, A. and M.R. Majdzadeh Tabatabai. 2010. Prediction of daily discharge trend of river flow based on genetic programming. Journal of Water and Soil, 24(2): 325-33 (in Persian).
    4. Dehghani, R., M.A. Ghorbani, M. Teshnelab and A. Rikhtehgar Gheasi. 2015. Comparison and evalution of bayesian neural network, gene expression programming, support vector machine and linear regression in river discharge estimation, case study: Sufi Chay Basin. The Iranian Society of Irrigation and Water Engineering, 5(20): 66-85 (in Persian).
    5. Feldkamp, L.A. and G.V. Puskorius. 1994. Training controllers for robustness: multi-stream DEW. In Proceedings of the IEEE International Conference on Neural Networks, Orlando, 6: 2377-2382.
    6. Ferreira, C. 2001. Gene expression programming: a new adaptive algorithm for solving problems. Complex System, 13:87-129.
    7. Ferreira, C. 2006. Gene expression programming: mathematical modeling by an artificial intelligence (studies in computational intelligence). Springer-Verlag New York, Inc., Secaucus, NJ, USA.
    8. Ghorbani, M.A. and R. Dehghani. 2016. Application of bayesian neural networks, support vector machines and gene expression programming analysis of rainfall–runoff monthly, case study: Kakarza River. Irrigation Science and Engineering, 39(2): 125-138 (in Persian).
    9. Golabi, M.R., A.M. Akhondali and F. Radmanesh. 2013. Comparison of the performance of different artificial neural network algorithms in seasonal rainfall modeling, case study: selected stations in Khuzestan Province. Journal of Applied Geosciences Research, 13(30): 151-169 (in Persian).
    10. Heimes, F. 1998. Extended Kalman Filter neural network training: experimental results and algorithm improvements. Systems, Man and Cybernetics, IEEE International Conference on San Diego, CA, USA.
    11. Karimi, S., J. Shiri, O. Kisi and A.A. Shiri. 2015. Short-term and long-term streamflow prediction by using 'wavelet–gene expression' programming approach. ISH Journal of Hydraulic Engineering, 3: 1-15 (in Persian).
    12. Motamednia, M., A. Nohegar, A. Malekian, M. Saberi and K. Karimi. 2017. Runoff prediction using intelligent models. Journal of Ecohydrology, 4(4): 955-968 (in Persian).
    13. Naeimi Kalourazi, Z., Kh. Ghorbani, M. Salarijazi and A.A. Dehghani. 2017. Investigation of effect of basin’s physiographic and climatic parameters in seasonal river flow simulation. Ecohydrology, 3(4): 545-555 (in Persian).
    14. Nash, J.E. and J.V. Sutcliffe. 1970. River flow forecasting through conceptual models part I, a discussion of principles. Journal of Hydrology, 10(3): 282–290.
    15. Noori, R., M.A. Abdoli, A. Ameri and M. Jalili-Ghazizade. 2008. Prediction of municipal  solid  waste generation  with  combination  of  support  vector  machine  and  principal  component  analysis, a  case  study  of Mashhad. Environmental Progress and Sustainable Energy, 28­(2): 249-258.
    16. Noori, N., L. Kalin. 2016. Coupling SWAT and ANN models for enhanced daily streamflow prediction. Journal of Hydrology, 533: 141–151.
    17. Noori, R., A. Karbassi, A. Farokhnia and M. Dehghani. 2009. Predicting the longitudinal dispersion coefficient using support vector machine and adaptive neuro-fuzzy inference system techniques. Environmental Engineering Science, 26(10): 1503-1510.
    18. Puskorius, G.V. and L.A. Feldkamp. 1991. Decoupled Extended Kalman Filter training of feed forward layered networks. In Proceedings of the International Joint Conference on Neural Networks, Seattle.
    19. Puskorius, G.V and L.A. Feldkamp. 1997. Multi-stream Extended Kalman Filter training for static and dynamic neural networks. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetic, Orland.
    20. Singh, G., R.K. Panda and M. Lamers. 2015. Modeling of daily runoff from a small agricultural watershed using artificial neural network with resampling techniques. Journal of Hydroinformatics, 17(1): 56-74.
    21. Singhal, S. and L. Wu. 1989. Training multilayer perceptions the Extended Kalman Algorithm. Advances in Neural Information Processing Systems, San Meteo, CA: Morgan Kaufmann, 133-­140.
    22. Solgi, A., H. Zarei and M.R. Golabi. 2017. Performance assessment of gene expression programming model using data preprocessing methods to modeling river flow. Journal of Water and Soil Conservation, 24(2): 185-201 (in Persian).
    23. Solgi, A., H. Zarei, M. Shehnidarabi and S. Alidadi. 2018. Monthly precipitation forecast using gene expression planning models and support vector machine. Journal of Applied Geosciences Research, 50: 91-103 (in Persian).