Application of Shannon Entropy for Selecting the Optimum input Variables in River Flow Simulation using Intelligent Models (Case Study: SofyChay)

Document Type : Research Paper


1 Ms.c student of Water Resources Engineering, University of Tabriz, Iran

2 Associate Professor, University of Tabriz, Iran.


       Accurate   prediction of the  river flow is  an  important  element  in  the management  of  surface  water  resources, dam  reservoir  operation, flood control and drought. Selecting appropriate inputs for intelligent models is vital to increase the accuracy and efficiency of the models. Since river flow prediction is of great importance in water resources, researchers have been exploring different approaches over the past several decades.  Various methods have been devised to predict the flow of the river over the past years. In general, we can classify conceptual models and data-driven methods.  Over the past four decades, time series models have been widely used in river flow prediction (Dawson et al., 2008). Intelligent systems are used to predict nonlinear phenomena. The Bayesian Network and the Artificial Neural Network are among these methods. Ahmadi et al. (2014) studied the  comparison of performance of support vector machine and network methods in forecasting daily flow of the Barandozachay River. The results showed that, both methods are close to each other and are suitable for river flow simulation. But in mid-range forecasting and the minimum backup car model, it's much better than the business network model. Shannon entropy theory was first developed by Shannon and then widely used in various scientific issues.
The purpose of this study is to use the Shannon Entropy Theory to find the best combination of input variables for artificial neural network and Bayesian network models to predict the flow. Therefore, for this purpose, the Sufi River of the studied area was selected.


Main Subjects

1-     Abdolahpour, M.R., and Satari, M.T., 2014. Prediction of Ahar River flow by using artificial neural networks and comparing it with fuzzy-neural network inference system. Journal of Water and Soil Conservation, 22(1) ,pp. 287-298 ( In Persian).
2-     Ahmadi, F., Radmanesh, F.and Mirabasi Najafabadi, R., 2014. Comparing the performance of Support Vector Machines and Bayesian networks in predicting daily river flow (Case study: Baranduz Chai River), Journal of Water and Soil Conservation, 22(6), pp.171-186 ( In Persian).
3-     Ahmadi, F., Dinpazhoh, Y. Fakherifard, A. and Darbandi, S., 2013. Comparing nonlinear time series models and genetic programming for daily river flow forecasting (Case study: Barandouz-Chai River), Journal of Water and Soil Conservation, 22(1), pp.151-169 ( In Persian).
4-     Bohrani, A. and Fatehi, A., 2008. Application of Artificial Neural Network in Stream Flow Forecasting using Climatic Indices (Case Study: Nazloochay River Basin), Journal of Civil and Environmental Engineering University of Tabriz, 35(3),pp. 51-62.( In Persian).
5-     Cain, J.  2001.  Planning   improvement  in  natural  resource  management. Centre for Ecology and Hydrology (CEH).  Wallingford, UK.
6-     Chiang, W. Hui-Chung, Y. 2014. Spatiotemporal Scaling Effect on Rainfall Network Design Using Entropy. Journal of Entropy. 16,pp. 4626-4647.
7-       Davies, P.  2007.  Conservation  of  Freshwater Ecosystem Values Project,  Department of Primary Industries and Water Resources Division.
8-     Dawson, C.W. Abrahart, R.J. Shamseldin, A.Y. Wibly, R.L. 2008. Flood estimation at ungauged sites uzingartifitial neural networks. Journal of Hydrology. 319,pp. 391-409.
9-     Ghorbani, M.A. Ahmad Zadeh, H. Isazadeh, M. Terz, O. 2016a. A comparative study of artificial neural network (MLP, RBF) and support vector machine models for river flow prediction, Journal Environmental Earth Science. 75,,pp.465-476.
10-  Ghorbani, Kh., Sohrabiyan, A. and Salari jezi, M., 2016b. Assessment of hydrological and data mining methods in simulating and predicting monthly flow flow (Case study: Arzakoush Hydrometry Station), Journal of Water and Soil Conservation, 23(1) ,pp. 203-217.( In Persian).
11-  Ghorbani, M.A.,and Dehgani, R.,2015. Application of Bayesian Neural Networks, Support Vector Machines and Gene Expression Programming Analysis of Rainfall - Runoff Monthly (Case Study: Kakarza River). Journal of Irrigation Sciences and Engineering, 20. 39(2), pp.125-138.( In Persian).
12-  Gizilbash, Z., Zakeriniya, M. Hezarjaribi, A. and Dehgani, A., 2014. Performance comparison of gene expression programming   and artificial neural network methods to estimate water  distribution uniformity in sprinkler irrigation, Journal of Water and Soil Conservation, 22(6) ,pp. 95-114.( In Persian).
13-  Jalali, M., Pirniya, A. Soleimani, K. and Habibneghad roshan, M.,2015. Investigating the Function of Artificial Neural Network in River Flow Forecasting (Case Study: Ghareaghaj Basin of Fars Province). Journal of the Ecosystem of Desert Engineering,6(4), pp.15-26.( In Persian).
14-  Kuikka  S.  and O.,  Varis  1997.  Uncertainties  of  climate  change  impacts  in  Finnish  watershedsa Bayesian network  analysis of expert knowledge,  Journal of Boreal Environment  Research. 2,pp.109-128.
15-  Masoumi, F. and Kerachiyan, R., 2007. Optimal Design of Groundwater Groundwater Quality Monitoring Systems Using Discrete Entropy Theory Case Study: Tehran Aquife, Third National Congress of Civil Engineering, Shahid Beheshti,Tehran. ( In Persian).
16-  Mohajerani, H., Mosaedi, A. Kholgi, M. and Meftah halgi, M., 2010. Introduction of business decision making networks and its application in water resource management, First National Conference on Coastal Water Resources Management.Sari, Mazandaran. ( In Persian).
17-  Nikmanesh, M., 2014. Prediction of monthly average discharge using the hybrid model of artificial neural network and wavelet transforms (Case study: KorRiver-Pol-e-Khan Station), Journal of Water and Soil Conservation, 22(3) ,pp. 231-239.( In Persian).
18-  Pollino,  C.  and Hart, B., 2006.  Bayesian network   models  in natural resource management. Integrated Catchment Assessment and Management (ICAM) Centre of the Australian. National water commission.
19-  Rajaee, T. and Ebrahimi, H., 2013. Application of neural network-wavelet model for prediction of non-stationary and non-linear characteristics of time series of groundwater level. Journal of Water and Soil Conservation,22(5), pp.99-115 ( In Persian).
20-  Sadedin,  A.,  Letcher,  R.  A.,  Jackeman,  A.  J.  and Newham L.  A.,  2005.  Bayesian  decision network  approach  for  assessing  the  ecological  impact  of  salinity  management.  Journal of Mathematics  and Computer  in Simulation,  69, pp. 162-176.
21-  Selgi, A., Radmanesh, F. and Soltani, K., 2014. Intelligent Modeling of the Monthly Period of Shur Ghorve River Basin with Artificial Neural Network. Journal of Water and Soil Conservation, 22(1), pp. 309-318.( In Persian).
22-  Shannon, CE. 1948. A mathematical theory of communications, Journal of The Bell System Technical, 27,pp. 379-423.
23-  Sheikhalipour, Z., Hasanpour, F. and Azimi, V.,2014. Comparison of artificial intelligence methods in estimation of suspended sediment load (Case Study: Sistan River), Journal of Water and Soil Conservation, 22(2) ,pp. 41-60.( In Persian).
24-  Sonuga, J.O., 1976. Entropy principle applied to the rainfall-runoff process. Journal of Hydrology, 30(1-2), pp.81-94.
25-    Xu, L. J.  Wang, J. Guan, and F.  Huang.  2007.  A Support Vector Machine Model for Mapping of Lake Water Quality from Remote-Sensed Images. Journal of Intelligent Computing in Medical Sciences & Image Processing , 1(1),pp. 57-66.
26-  Wu, J.  Li, P. and Qian, H.  2015. On the sensitivity of entropy weight to sample statistics in assessing water qualitystatistical analysis based on large stochastic samples. Journal of Environmental Earth Science. 74, pp.2185-2195.
27-  Zhang JL, Ren J. 2011. The deficiencies and amendments of the calculation formulate of entropy and entropy weight in the theory of entropy. Journal of Statistics and Information Forum China Academic, 26(1), pp.1–5 (in Chinese).
Volume 41, Issue 2
June 2018
Pages 183-195
  • Receive Date: 01 August 2016
  • Revise Date: 15 January 2017
  • Accept Date: 01 March 2017
  • Publish Date: 22 June 2018