Application of LS-SVM, ANN, WNN and GEP in rainfall- runoff modeling of Kiyav-Chay River

Document Type : Research Article

Authors

1 Assistant Professor, Department of Water Engineering, University of Mohaghegh Ardabili, Ardabil, Iran

2 Assistant Professor, Department of Water Engineering, University of Kurdistan, Kurdistan, Iran

3 Water Engineering Expert, Department of Water Engineering, University of Mohaghegh Ardabili, Ardabil, Iran

Abstract

Streamflow forecasting is necessary for water resources management and planning in rivers, lakes, reservoirs and protection of river banks during flood. In this study, different soft computing models including artificial neural networks (ANN), the hybrid of wavelet-artificial neural networks (WANN), gene expression programming (GEP) and least square-support vector machines (LS-SVM) were utilized for river flow estimation of Khiav-Chay. Statistical measures and ANOVA test were used for evaluation of applied models. The results indicated that WANN model was the best model with the highest correlation coefficient (R=0.877) and the lowest root mean squared error (RMSE=0.696) and Nash Sutcliff coefficient (NS=0.767) in validation phase. The results of ANOVA test were in agreement with statistical criteria values and WANN model with the lowest F statistic (F=0.11) and the highest significant resultant (0.75) was selected as the best model. Furthermore, in estimation of maximum discharge, WANN with mean relative error of 30.19% has the minimum error of estimation compared to other models.

Keywords

Main Subjects


  1.  

    1. Saeedi Farzad B. Intelligent simulation of rainfall-runoff using a semi-distributed model with time variables. Ph.D. thesis in civil engineering, Faculty of Engineering, University of Tabriz, Tabriz. 2014. [Persian]
    2. Whigham PA, Crapper PF. Modeling rainfall–runoff using genetic programming. Mathematical and Computer Modeling. 2001;33:707–721.
    3. Liong SY, Gautam TR, Khu ST, Babovic V, Keijzer M , Muttil N. Genetic programming: A new paradigm in rainfall runoff modeling. J Am Water Res Assoc. 2001;38:705-718.
    4. Jayawardena AW, Muttil N, Fernando TM. Rainfall-Runoff Modeling Using Genetic Programming. International Congress on Modeling and Simulation Society of Australia and New Zealand. 2005: 1841-1847.
    5. Aytek A, Alp M. An application of artificial intelligence for rainfall-runoff modeling. Journal of Earth System Science. 2008;117(2):145-155.
    6. Nourani V, Baghanam AH, Adamowski J, Gebremichael M. Using self-organizing maps and wavelet transforms for space–time pre-processing of satellite precipitation and runoff data in neural network based rainfall–runoff modeling. Journal of Hydrology. 2013;476:228-243.
    7. Nayak PC, Venkatesh B, Krishna B, Sharad KJ. Rainfall-runoff modeling using conceptual, data driven, and wavelet based computing approach. Journal of Hydrology. 2013;493:57-67.
    8. Badrzadeh H, Sarukkalige R, Jayawardena AW. Hourly runoff forecasting for flood risk management: Application of various computational intelligence models. Journal of Hydrolog. 2015;529:1633-1643.
    9. Nourani V. An Emotional ANN (EANN) approach to modeling rainfall-runoff process. Journal of Hydrology. 2016;544:267-277.
    10. Behzad M, Asghari K, Eazi M, Palhang M. Generalization performance of support vector machines and neural networks in runoff modeling. Expert Systems with applications. 2009;36(4):7624-7629.
    11. Botsis D, Latinopoulos P, Diamantaras K. Rainfall-Runoff Moeling Using Suport Vector Regression and Artificial Neural Networks. 12th International Conference on Environmental Science and Technology (CEST2011), Rhodes, Greece, 8-10 September. 2011
    12. Adamowski J. Using support vector regression to predict direct runoff, base flow and total flow in a mountainous watershed whit limited data in Uttaranchal, India. Journal of Land Reclamation. 2013;45(1):71-83.
    13. Ghorbani M. A., and Dehghani R. 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. 2016;39(2):125-138. [Persian]
    14. Nazeri Tahroodi M, Hashemi R, Ahmadi F, Nazeri Tahroodi Z. Accuracy investigation of ANFIS, SVM and GP models in modelling of river discharge values. Journal of Echo Hydrology. 2016;3(3):361-347. [Persian]
    15. Vapnic VN. Statistical Learning Theory. Wiley, NEW YORK, USA. 1998
    16. Suykens JA, De Brabanter J, Lukas L, Vandewalle J. 2002. Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing. 2002;48(1):85-105.
    17. Ghafari G, Vafakhah M. Simulation of rainfall-runoff process using artificial neural network and adaptive neuro-fuzzy interface system (Case study: Hajighoshan watershed). Journal of Watershed Management Research. 2013;4(8):120-136. [Persian]
    18. Dehghani A, Zanganeh MA, Mosaedi A, Kouhestani N. Comparison of suspended load estimation using sediment rating curve and artificial neural networks. Journal of Researches on Water and Soil Conservation. 2009;16(1):30-41. [Persian]
    19. Nourani V, Hosseini Baghanam A, Adamowski J, Kisi, O. Applications of hybrid wavelet–Artificial Intelligence models in hydrology. A review. Journal of Hydrology. 2014;514(1):358-377.
    20. Marofi S, Amir Moradi K, Parsafar N. River flow prediction using Artificial Neural Network and Wavelet Neural Network models (Case study: Barandozchay River). Journal of Water and Soil Science. 2013;23(3):93-103. [Persian]
    21. Ferreira C. Gene Expression Programming: a New Adaptive Algorithm for Solving Problems. Complex Systems. 2001;13(2):87–129.
    22. Ferreira C. Automatically defined functions in gene expression programming. In Genetic Systems Programming. Springer Berlin Heidelberg. 2006:21-56.

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