Artificial Neural Network Modeling of Total Dissolved Solid in the Simineh River, Iran
Original Article, D2 NematiS, Naghipour L and Fazeli Fard MH. Journal. Civil Eng. Urban. 4(1): 08-13. 2014
ABSTRACT:This research aims to model Total Dissolved Solid (TDS) values at the Simineh River in northwest Iran by application of Artificial Neural Networks (ANNs) to evaluate existing water quality conditions and also to predict future conditions in this river. The input parameters of the ANNs model are Calcium (Ca), Chloride (Cl), Magnesium (Mg), Sodium (Na), Bicarbonate (HCO3), Sulfate (SO4), and water discharge (Q) from 1993 to 2011. The performance of the ANNs model was assessed in accordance with Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2) between the measured and predicted values. The study also includes an estimation of the relative importance of these variables to determine appropriate input combinations. A method is used in this paper to calculate the relative importance of each input parameters, showing that magnesium and calcium concentrations are the most and least influential parameters, with approximate values of 18 and 12 %, respectively. The ANNs with different numbers of neurons in the hidden layer were constructed, and the model with 14 hidden neurons was selected as the best. Comparisons between the measured and predicted values show that the ANNs model could be successfully applied and provide high accuracy and reliability for water quality parameters forecasting. Keywords:Artificial Neural Networks, Total Dissolved Solid, Simineh River, Relative Importance, Water Quality
منبع:
[Hidden Content]
دانلود:
[Hidden Content].,14-02-08-13.pdf
J. Civil Eng. Urban.,14-02-08-13.pdf