Predictive Analytics and Early Warning System for Urban Water Quality Management using Machine Learning

K Bhargav Prasad, Karthik Katuri, Venkata Sai Pranav C., C. Jyotsna, Aiswariya Milan K

2025

Closed access Metadata (CSL-JSON)
DOI 10.1109/icecmsn68058.2025.11383319
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The study presents a smart system for predicting and assessing water quality in urban environments by using machine learning techniques. The system predicts the contamination levels by analyzing key water quality parameters such as Total Dissolved Solids (TDS), Electrical Conductivity (EC), Chloride and Sodium. On the surface, the system offers actionable insights into sustainable water management in urban areas and also provides an Early Warning System (EWS) that helps in real-time monitoring and predictions, and ultimately leads to quick and effective solutions to water quality issues. Comprehensive Exploratory Data Analysis (EDA) and robust machine learning models achieved a high predictive accuracy (R2> 0.90 for critical parameters). The approach suggested and built is a cost-effective data-driven urban water quality management system.