Abstract
In this study, the quality of TGRIS River is studied at the intake of Al-Rashediya Water Station using neural network
analysis. 14 measured parameters of water quality, daily periods for 11 years (2013-2023), monthly mean averaged
were studied which are: K+, Na+, T.S.S, T.D.S, SO42-, Cl-, Mg2+, Ca2+, T.H, Alk., E.C, pH, Turb, and Temp., from
which WQI was calculated. In this study, a sophisticated artificial neural network (ANN) model. to predict water
quality (WQIى). Neural network fitting app. is applied using multi-layer feed- forward neural network with back
propagation algorithm. The data were randomly divided into three phases, training (70%), validation (15%), and
testing (15%). Efficiency statistics were used to evaluate the model prediction abilities. The results showed that the
model performed well with high predicting ability for the water quality index (WQI), and the model performed best
with accuracy (R .9921, and MSE 221.7468) at the testing phase, which will help to enhance the WQ using cheap and
valuable method. The Predicted WQI mathematical model is estimated by the equation:
Output WQI=0.99target WQI+1.1, which can be used for the becoming years.
analysis. 14 measured parameters of water quality, daily periods for 11 years (2013-2023), monthly mean averaged
were studied which are: K+, Na+, T.S.S, T.D.S, SO42-, Cl-, Mg2+, Ca2+, T.H, Alk., E.C, pH, Turb, and Temp., from
which WQI was calculated. In this study, a sophisticated artificial neural network (ANN) model. to predict water
quality (WQIى). Neural network fitting app. is applied using multi-layer feed- forward neural network with back
propagation algorithm. The data were randomly divided into three phases, training (70%), validation (15%), and
testing (15%). Efficiency statistics were used to evaluate the model prediction abilities. The results showed that the
model performed well with high predicting ability for the water quality index (WQI), and the model performed best
with accuracy (R .9921, and MSE 221.7468) at the testing phase, which will help to enhance the WQ using cheap and
valuable method. The Predicted WQI mathematical model is estimated by the equation:
Output WQI=0.99target WQI+1.1, which can be used for the becoming years.
Keywords
Artificial Neural Network (ANN)
deep learning
Water Quality Index