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

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.