Estimation of Sodium Absorption Ration (SAR) in Groundwater Using the Artificial Neural Network and Linear Multiple Regression: Case Study: The Bajestan Plain
As the SAR of irrigation water is a major determinant of the sustainability of agriculture and development on groundwater, the foreknowledge of its value is of utmost importance. As this parameter is highly related to the geological settings, and this in a region maybe somehow dependent on geographical coordinates, the longitude and latitude of 69 wells, along with the pH, electrical conductivity (EC) and total dissolved solids (TDS) of their water were determined. To correlate these data to the SAR of water, this parameter was assigned as the dependent variable and the other 5 as the independent variables. The linear multiple regression (LMR) and artificial neural network (ANN) methods were applied to establish their correlations, and the sensitivity analysis was performed for the ANN to single out the most important independent variable. It was observed that the LMR and ANN explain 23.9 % and 80.0 % of the variations of the SAR, respectively. The sensivity analysis indicated that the water pH was the strong predictor of the groundwater’s SAR value.
p, H., & b, A. (2014). Estimation of Sodium Absorption Ration (SAR) in Groundwater Using the Artificial Neural Network and Linear Multiple Regression: Case Study: The Bajestan Plain. Water Resources Engineering, 7(21), 67-80.
MLA
h. p; a. b. "Estimation of Sodium Absorption Ration (SAR) in Groundwater Using the Artificial Neural Network and Linear Multiple Regression: Case Study: The Bajestan Plain". Water Resources Engineering, 7, 21, 2014, 67-80.
HARVARD
p, H., b, A. (2014). 'Estimation of Sodium Absorption Ration (SAR) in Groundwater Using the Artificial Neural Network and Linear Multiple Regression: Case Study: The Bajestan Plain', Water Resources Engineering, 7(21), pp. 67-80.
VANCOUVER
p, H., b, A. Estimation of Sodium Absorption Ration (SAR) in Groundwater Using the Artificial Neural Network and Linear Multiple Regression: Case Study: The Bajestan Plain. Water Resources Engineering, 2014; 7(21): 67-80.
)
