River Water Salinity Impact on Drinking Water Treatment Plant Performance Using Artificial neural network

  • Sabreen Hayder Abbas College of Engineering-University of Baghdad
  • Basim Hussein Khudair College of Engineering-University of Baghdad
  • Mahdi Shanshal Jaafar Researcher in the Ministry of Science and Technology - Ministry of Science and Technology
Keywords: Salinity impact, Drinking water, Tigris River, ANN, TDS, WTP

Abstract

The river water salinity is a major concern in many countries, and salinity can be expressed as total dissolved solids. So, the water salinity impact of the river is one of the major factors effects of water quality. Tigris river water salinity increase with streamline and time due to the decrease in the river flow and dam construction from neighboring countries. The major objective of this research to developed salinity model to study the change of salinity and its impact on the Al-Karkh, Sharq Dijla, Al-Karama, Al-Wathba, Al-Dora, and Al-Wihda water treatment plant along Tigris River in Baghdad city using artificial neural network model (ANN). The parameter used in a model built is (Turbidity, Ec, T.s, S.s, and TDS in) to predict the salinity TDSout.  Results showed that the effectiveness of the artificial neural network model to predicting the salinity is a good agreement between observed and the predicted value of the TDS, through the determination coefficient of the model is (0.998, 0.966, 0.997, 0.998, 0.996, and 0.996) for Al. Karkh, Sharq Dijla, Al.Karama, Al.Wathba, Al.Dora and Al.Wihda respectively. From this value can be shown that ANN is a successful tool for predicting the nonlinear equation of the salinity under different and complicated environmental case along the river.

 

Downloads

Download data is not yet available.
Published
2019-07-31
How to Cite
Abbas, S., Khudair, B. and Jaafar, M. (2019) “River Water Salinity Impact on Drinking Water Treatment Plant Performance Using Artificial neural network”, Journal of Engineering, 25(8), pp. 149-159. doi: 10.31026/j.eng.2019.08.10.

Most read articles by the same author(s)