Determining water quality along the river with using evolutionary artificial neural networks (Case Study, Karoon River , Shahid Abbaspur-Arab Asad reach)

Document Type: Original Article

Authors

1 Civil Engineering, Sama technical and Vocational training college, Islamic Azad University, Ahvaz Branch, Ahvaz, Iran.

2 , Islamic Azad University, Ahvaz Branch, Civil Engineering, Ahvaz, Iran.

3 Islamic Azad University, Ahvaz Branch, Geography Department, Ahvaz, Iran.

4 , Islamic Azad University, Ahvaz Branch, Geology Department, Ahvaz, Iran.

Abstract

Rivers are important as the main source of supply for drinking, agriculture and industry.However, drinking water quality in terms of qualitative parameters, is the most important variable. Studias and predicting  changes in quality parameters along a river, are one of the goals of water resources planners and managers. In this regard, many water quality models in order to maintain better water quality management are developed. The artificial neural network models that are inspired by the structure of the human brain, as the best option will be investigated and evaluated. In this research was done  on the Karoon River, the largest river in the country and using the parameters in the stations along the river (Shahid Abbaspur-Arab Asad reach). To this end , discharge , month , along river and electrical conductive in the measured in Shahid Abbaspur , Pole Shalu , Gotvand and Arab Asad station were  considered as the input model and using neural network model , sodium adsorption ratio (SAR) and total dissolve salts (TDS) were  measured in the same stations.Including those in this study as a new method has been used to determine water quality parameters are simultaneously at several stations. In order to optimize each of evolutionary artificial neural network models was used genetic algorithm.The results  showed  that chosen artificial neural network model to station non-linear regression model of skills , flexibility and more accurate in productivity water quality in rivers is capable.
 

Keywords


- Faruk, D. O. (2010). A hybrid neural network and ARIMA model for water quality time series prediction. Engineering Applications of Artificial Intelligence,pp. 23 (4).

- Gavin J, G. C. (2004). Input determination for neural network models in water resources applications. Part 1-background and methodology. Journal Of Hydrology Elsevier.

- Kuo, j. T, Y.-Y. W.-S. (2006). A hybrid neural–genetic algorithm for reservoir water quality management. Water Research, 40 (6).

- Misaghy, K. M. (2005). predictIion of changes in river water quality using artificial neural networks. Second National Student Conference on Water and Soil Resources .

- Nushady, M. A. (2008). Simulation and prediction of calcium, magnesium, sodium, potassium, and sulfate in Zayandehrood river  using artificial neural networks. Fourth National Conference on Watershed Management Science and Engineering of watershed management.

- Paulo Chaves, T. K. (2007). Deriving reservoir operational strategies considering water quantity and quality objectives by stochastic fuzzy neural networks. Advances in Water Resources , 30 (5), PP.1329-1341.

- Singh, A. B.  Kunwar, P. (2009). Artificial neural network modeling of the river water quality ,A case study. Ecological Modelling, 220 (6).

- Yazdani, M. K. S. (2008). Using artificial neural networks in assessing the quality status of rivers. Fourth National Conference on Watershed Management Science and Engineering of watershed management. NeuroSolutions Getting Started Manual Version 4. (2010). Retrieved from Neurosolutons Getting Started Manunal Version 4. (2010). Reterieveh from Neurosolutions: www.nd.com.

- Yarmohammadi, E. C.-m. ,.-Z. (2007). Using artificial neural networks in simulation Karkheh river water quality . First Conference on Environmental Engineering .

- Zhang, Q.S.J, (1998). Forecasting raw-water quality parameters for the North Saskatchewan River by neural network modeling. Water Research , 31 (9).