Sodium adsorption ratio (SAR) is considered as a measure of the water suitability for irrigation usage. This study examines the effect of the physicochemical parameters on water quality and SAR, which included Calcium(Ca+2), Magnesium(Mg+2), Sodium (Na+), Potassium (K), Chloride (Cl-), Sulfate(SO4-2), Carbonate (CO3-2), Bicarbonate (HCO3-), Nitrate (NO3-), Total Hardness (TH), Total Dissolved Salts (TDS), Electrical Conductivity (EC), degree of reaction (DR), Boron (B) and the monthly and annually flow discharge (Q). The water samples were collected from three stations across the Tigris River in Iraq, which flows through Samarra city (upstream), Baghdad city (central) and the end of Kut city (downstream) for the periods of 2016-2018. Results showed that the water quality of the Tigris River water is within the world health organization (WHO) specifications for drinking water except for Sulfate concentration. An artificial neural network (ANN) was used to develop the model for the three locations to predict SAR. The sum of the squared error function and the coefficient of determination (R2) were used to evaluate the amount of error in predicting values of SAR and performance evaluation of the model. The results showed that the highest value of the coefficient of determination was 0.992, 0.986, and 0.955 for Samarra, Baghdad, and Kut, respectively and the ANN analysis indicated that the prediction of SAR was effected by Sodium for three stations. Thus, the ANN model has been found to provide SAR prediction tool that can be used effectively to describe the suitability of river water quality for irrigation purposes.