AI-Driven Classification and Correlation Analysis of Water Quality Parameters

View at publisher Summarise with VIRAT
Authors: Tanaya Gharge, Sakshi P. Barde, Rakshitha R Shetty, Avantika Warrier, Varunakshi Sachin Bhojane
Cited by: 0
References: 22

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Assessment of water quality is vital for monitoring environmental health and ensuring safe drinking water. Traditional laboratory-based testing methods, though accurate, are often time-consuming, costly, and unsuitable for large-scale or real-time applications. With recent progress in Artificial Intelligence, machine learning techniques have emerged as efficient alternatives for predicting and classifying water quality based on parameters such as Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), Chloride, Conductivity, Dissolved Oxygen (DO), Nitrate, Total Organic Carbon (TOC), Turbidity, Temperature, and pH. This study proposes an Artificial Neural Network (ANN)-based model integrated with anomaly detection, data imputation, and correlation analysis to automate water quality monitoring. The framework leverages deep learning techniques to analyze complex parameter relationships and support real-time classification of water potability. The proposed system enhances efficiency, interpretability, and decision-making accuracy, contributing to sustainable and data-driven water resource management.

Fields of Study & Subjects

Water Quality Monitoring Technologies Water Quality Monitoring and Analysis Water Quality and Pollution Assessment

Publication details

Journal / source
Biennial International Conference on Nascent Technologies in Engineering (ICNTE)
Pages
1–5
Publication date
16 January 2026
Language
EN