Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194844,
        author = {B. Manohar Prasad and D. Lakshmi Pavani and J.P S Sruthi and K. Moksha Sri Bhanu and K. Harsha Kumar},
        title = {Water Quality Analysis using Machine Learning Regression for Predicting Water Quality Parameters},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {8095-8100},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194844},
        abstract = {Monitoring water quality is essential for environmental sustainability, public health, and safe drinking water. Traditional laboratory testing methods are often expensive, time-consuming, and require trained personnel. With the advancement of Machine Learning (ML), predictive models can efficiently estimate water quality parameters. This study proposes a regression-based ML framework to predict important water quality parameters such as pH using physicochemical indicators including hardness, total dissolved solids, chloramines, sulfate, conductivity, organic carbon etc... The research uses the Water Potability dataset from Kaggle water samples. Data preprocessing techniques such as handling missing values, outlier detection, normalization, and multicollinearity analysis were applied. Multiple regression models including Multiple Linear Regression, Decision Tree Regression, and Random Forest Regression were implemented and compared. Water potability was also determined using classification models. Model performance was evaluated using MAE, MSE, RMSE, and R² score for regression, and accuracy, precision, recall, and F1-score for classification. Experimental results showed that Random Forest Regression achieved the highest R² value of 0.92, while the Random Forest Classifier reached 93% accuracy. The proposed system provides a reliable and cost-effective approach for water quality monitoring and decision-making.},
        keywords = {Environmental Monitoring, Water Quality Prediction, Regression Models, Classification Models, Random Forest, Machine Learning.},
        month = {March},
        }