Predictive Modeling of WQI of Trans Amadi Industrial Layout, Port Harcourt, Rivers State Nigeria Using Multiple Linear Regression

Abstract

It is important to monitor water quality and understand factors influencing indices like the Water Quality Index (WQI). This study aimed to assess water quality and to develop a predictive model for WQI based on common ions and using multiple linear regression analysis. Water samples were collected from 15 locations in Trans Amadi Industrial Layout, Port Harcourt and analyzed for 19 groundwater quality parameters (Temp, EC, DO, Turbidity, NO3, HCO3, pH, TDS, CI, SO₄, Fe, Na, Ca, Mg, Zn, Cu, Cr, Pb and Cd). Results of correlation analysis revealed that there were significant relationships between some of these parameters and the WQI. A multiple linear regression (MLR) model was developed to quantitatively examine relationships between the Water Quality Index (WQI) and key indicator variables and to predict the WQI based on the parameters. The model exhibited a strong coefficient of determination (R-squared = 0.9811), indicating a high level of accuracy in predicting the WQI. Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) values confirmed the model's predictive capability. Overall, this study contributed to understanding the factors influencing water quality and showed that linear regression is a reliable method for predicting WQI. The model accurately explains variation in WQI based on nitrate, chloride, sodium, calcium and magnesium levels.