Total views : 490

A Comparative Study of SWAT, RFNN and RFNN-GA for Predicting River Runoff


  • Faculty of Computer Science and Engineering, HCM University of Technology, Viet Nam
  • Faculty of Information Technology, Ton Duc Thang University, Viet Nam
  • Department of Computer Science, VSB-Technical University of Ostrava, Czech Republic
  • Xi’an Jiaotong-Liverpool University, Suzhou, China


Background/Objectives: Data-driven models such as Recurrent Fuzzy Neural Network (RFNN) have been proven to be great methods for modeling, characterizing and predicting various kinds of nonlinear hydrologic time series data such as rainfall, water quality and river runoff. In modeling and predicting river runoff, the most important advantage of data driven models is that they do not need as much data as do physical models such as the Soil and Water Assessment Tool (SWAT). In Vietnam, most of data which are required by SWAT are not available, thus data-driven models seem to be more suitable for predicting river runoff than SWAT. The objective of this study is to investigate the performance of SWAT, RFNN and an improvement of RFNN (RFNN-GA), which is a hybrid of RFNN and Genetic Algorithm (GA) in predicting the runoff of Srepok River in Central Highland of Vietnam. Methods/Statistical Analysis: Coefficient of correlation (R2) and mean absolute relative error (MARE) are used to analysis and compare the performance of SWAT, RFNN and RFNN-GA. Findings: The experimental results demonstrate that RFNN and RFNN-GA give the performance better than that of SWAT and they are able to be applied to real applications. Among these methods, RFNN-GA is the most superior. Application/Improvements: In the terms of MARE and R2, RFNN-GA improves RFNN 0.9% and 2.2%, respectively; and improves SWAT 27.4% and 12.5%, respectively. RFNN-GA was deployed to predict the runoff of Srepok River in Central Highland of Vietnam.


Srepok, Runoff, Prediction, Recurrent Fuzzy Neural Network, Genetic Algorithm.

Full Text:

 |  (PDF views: 291)


  • Besaw LE, Rizzo DM, Bierman PR, Hackett W. Advances in ungauged stream flow prediction using artificial neural networks. Journal of Hydrology. 2010; 386:27-37.
  • Can I, Yerdelen C, Kahya E. Stochastic modeling of Karasu River (Turkey) using the methods of artificial neural networks. Hydrology Days. 2007; p. 138-44.
  • Demirela MC, Venancio A, Kahya E. Flow forecast by SWAT model and ANN in Pracana Basin Portugal. Journal of Advances in Engineering Software. 2009; 40:467-73.
  • Hieu DN, Quyen NTN, Long BT, Hien NT, Vaclav S. Applying recurrent fuzzy neural network to predict the runoff of Srepok River. Vietnam: Proceedings of 13th International Conference on Computer Information System and Industrial Management Applications. 2014; p. 55–66.
  • He Z, Wen X, Liu H, Du J. 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. 2014; 509; 379–86.
  • Razavi S, Araghinejad S. Reservoir inflow modeling using temporal neural networks with forgetting factor approach. International Journal of Water Resource Management. 2009; 23:39–55.
  • Kar S, Dasb S, Ghoshb PK. Applications of neuro fuzzy systems: A brief review and future outline. Applied Soft Computting. 2014; 15:243–59.
  • Ankit C, Nitin J, Himanshu P. Rainfall Runoff Analysis Using Artificial Neural Network. Indian Journal of Science and Technology. 2015; 8(14).
  • Nur AA, Wan HWI, Ku RK-M. Neural Network Application in the Change of Reservoir Water Level Stage Forecasting. Indian Journal of Science and Technology. 2015; 8(13).
  • Quyen NTN, Liem ND, Loi NK. Effect of land use change on water discharge in Srepok watershed, Central Highland, Vietnam. International Soil and Water Conservation Research. 2014; 2:74-86.
  • Panhalkar S. Hydrological modeling using SWAT model and geoinformatic techniques. The Egyptian Journal of Remote Sensing and Space Science. 2014; 17:197-207.
  • Santhi C, Arnold JG, Williams JR, Dugas WA, Srinivasan R, Hauck LM: Validation of the SWAT model on the large river basin with point and nonpoint sources. Journal of American Water Resources Association. 2001; 37:1169–1188.
  • Jia W, Zhao D, Shen T, Su C, Hu C, Zhao Y. A New Optimized GA-RBF Neural Network Algorithm. Computational Intelligence and Neuroscience. 2014; 6 pages.
  • Sarangi PP, Sahu A, Panda M. A hybrid differential evolution and back-propagation algorithm for feed forward neural network training. Journal of American Water Resources Association. 2013; 84(14).
  • Harpham C, Dawson CW, Brown MR. A review of genetic algorithms applied to training radial basis function networks. Neural Computing and Applications. 2004; 13:193-201.
  • Chang WY. An RBF neural network combined with OLS algorithm and genetic algorithm for short-term wind power forecasting. Journal of Applied Mathematics. 2013; 9 pages.
  • Bhardwaj S, et al. Chaotic time series prediction using combination of hidden Markov model and neural nets. Poland: Proceedings of the 9th International Conference on Computer Information Systems and Industrial Management Applications. 2010; p. 585-89.
  • Du B, Xu W, Song B, Dinh Q, Chu SC. Prediction of chaotic time series of RBF neural network based on particle swarm optimization. Intelligent Data Analysis and its Applications. 2014; 298:489-97.
  • Ma QL, Zheng AL, Peng H, Zhong TW, Qin JW. Multi-step-prediction of chaotic time series based on coevolutionary recurrent neural network. Chinese Physics B. 2008; 17:1674-1056.
  • Todorov Y, Terziyska M. Modeling of chaotic time series by interval type-2 neo-fuzzy neural network. Artificial Neural Networks and Machine Learning. 2014; 8681:643-50.
  • Lee CH, Teng CC. Identification and control of dynamic systems using recurrent fuzzy neural networks. IEEE Transactions on Fuzzy Systems. 2000; 8(4):349-66.
  • Polyak BT. Some methods of speeding up the convergence of iteration methods. USSR Computational Mathematics and Mathematical Physics. 1964; 4(5):1–17.
  • Werbos P. Cambridge, MA: Harvard University: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD. Thesis. 1974 Aug.
  • Whitley D. The GENITOR Algorithm and Selection Pressure: Why Rank Based Allocation of Reproductive Trials is Best. Proceedings of the 3rd International Conference on Genetic Algorithms. 1989; 116-21.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.