Application of artificial neural networks in the river water quality modeling: Karoon river, Iran

To achieve goals of this research program, Karoon river in Iran is selected to assess the capability of ANNs for water quality simulation. This river is the longest river in Iran. It is located in Khuzestan province, South-West of the country. Several water quality variables including; C03, HC03, S04, Cl, Na, Ca, Mg, K, EC, TDS and SAR have been simulated. Data from 1985 to 2006 at monitoring stations including; Arabhasan, Valiabad, Molasani, Ahwaz, Farsiat and Darkhoyen have been used for training of the selected ANN. Qnet 2000 ANN is selected for modeling purposes in the present research. Results show that Qnet 2000 is able to predict water quality variables of the Karoon River very successfully with more than 90% accuracy. © 2008 Asian Network for Scientific Information.