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{207111,
        author = {Utkarsh Kumar and Samarth Maheswari and Samriddhi Shukla and Megha Saxena},
        title = {Forecasting River Water Quality Using Random Forest Regression Model: A Real-Time Sensory Approach on The River Ganga},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {76-81},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207111},
        abstract = {Water quality deterioration is a serious environmental issue, especially in important river ecosystems like the Ganga (holding a very large population it's bank throughout its runoff). Traditional ways of measuring the Water Quality Index (WQI) depends heavily on time-consuming lab tests of factors like biological oxygen demand and coliform bacteria. This leads to a reactive approach in managing pollution. This study focuses on predicting WQI quickly using a simple, machine learning framework. In this research, we have used a Random Forest Regressor model to predict WQI based on real-time, sensor-compatible physicochemical metrics. The dataset contains high-frequency continuous data using five input parameters: Dissolved Oxygen (DO), pH, Oxidation-Reduction Potential (ORP), Conductivity, and Temperature. We reprocessed the data to ensure there were no missing values, creating a strong basis for model training. To make sure the model could understand complex physicochemical relationships without any temporal bias, we have separated the dataset randomly, allocating 80% for training and 20% for testing. The tuned Random Forest model produced highly accurate results, achieving an R² value of 0.954. By minimizing the dependency on delayed lab data, the proposed framework shows that an IoT-deployable, low-cost system can provide immediate water quality assessments and early warnings for controlling river pollution.},
        keywords = {Random Forest Regression; Machine Learning; WQI; Ganga River; Environmental Monitoring; Real-Time Data Analysis; IoT-Based Water Monitoring.},
        month = {July},
        }