Artificial Intelligence-Assisted Water Quality Model: Long-Term Follow-Up Data

This article presents the results of developing a model for assessing water quality using the artificial intelligence method. The presented model is based on linear regression, which, when evaluated, revealed a statistically significant interdependence between the combined water quality indicators. It was found that among the measured parameters, the most influential predictor of acidity, conductivity, turbidity and redox potential is water temperature. The discovered relationship between the measured indicators is mainly associated with the influence of temperature on the physical and chemical processes that occur when the temperature of river water increases and decreases.