Instant water quality index (WQI) prediction via reaeration process and hydraulic parameters in the river system

Read the full article See related articles

Discuss this preprint

Start a discussion What are Sciety discussions?

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

This study presents a novel approach for predicting the Water Quality Index (WQI) in river systems by integrating reaeration processes and hydraulic parameters. Using a Genetic Programming (GP) model, the reaeration coefficient (K₂) is predicted and used as a predictor for the WQI, significantly improving the accuracy of water quality assessments. The model demonstrates that K₂ can be reliably calculated using only the Froude number (Fr), a dimensionless parameter representing the river's flow hydraulic regime. After several iterations of multivariate linear regressions (MLRs), the less effective parameters (LEPs) were identified and removed, leading to the development of a WQI prediction equation based on Fr while maintaining high prediction accuracy (R² >0.9). Unlike previous studies that utilized multiple predictors, this model relies on the Fr number as a sole hydraulic predictor. Furthermore, a bootstrap-enhanced GP model is introduced, linking K₂ with WQI, with key factors such as Turbidity (Tu), Temperature (T), and K₂ identified as the primary drivers of WQI dynamics. The proposed model is computationally efficient and provides a cost-effective framework for real-time river ecosystem monitoring. The findings suggest that this approach can be applied across different river systems, making it a valuable tool for sustainable water quality management and environmental monitoring. By reducing the reliance on traditional, costly field studies, the model facilitates better decision-making in managing water resources, particularly in regions with limited data. The study paves the way for future research to expand and apply the model to other river systems globally, incorporating seasonal and anthropogenic factors to improve its robustness and predictive accuracy.

Article activity feed