Modeling of water quality index for irrigation in Shatt Al-Arab river using artificial intelligence

Irrigated agriculture relies on a sufficient supply of good quality water. Since water quality is so important for so many activities, the water of the Shatt Al-Arab River was evaluated for irrigation purposes by applying water quality index (WQI) for the years 2011 to 2020 in 15 water treatment pla...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdulkareem, Iman Ali, Dawood, Ammar Salman, Abbas, Abdulhussain A.
Format: Conference Proceeding
Language:English
Subjects:
Adsorption
Artificial intelligence
Artificial neural networks
Correlation coefficients
Electrical resistivity
Irrigation
Irrigation water
Magnesium
Prediction models
Sodium
Water quality
Water treatment
Water treatment plants
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Irrigated agriculture relies on a sufficient supply of good quality water. Since water quality is so important for so many activities, the water of the Shatt Al-Arab River was evaluated for irrigation purposes by applying water quality index (WQI) for the years 2011 to 2020 in 15 water treatment plants (WTPs) along the SAR. Six irrigation water quality variables, including electrical conductivity (EC), pH, sodium adsorption ratio (SAR), percentage sodium (Na %), magnesium adsorption ratio (MAR), and Kelly's ratio (KR), were taken into account for computing WQI. Applying a multiple linear regression (MLR) and artificial neural network (ANN) model, the WQI value was predicted based on pH, EC, SAR, Na%, MAR, and KR values. In MLR analysis, the multiple correlation coefficient (R) was found to be 1. Many networks are created by altering the number of neurons in order to attain the minimum mean squared error (MSE) achieving best accuracy. In this research, the 6-19-1 network structure was determined as the best prediction model.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0163309