Copyright © 2025 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{176533,
        author = {Jai Ranjan Jha and Avishek Kumar Singha and Sandeep Kumar},
        title = {Integrated Machine Learning Approach for Water Quality Assessment of the River Ganges},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {7301-7311},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176533},
        abstract = {One of the principal water bodies in India, the Ganges River, is heavily polluted from industrial discharge, domestic sewage, and agricultural runoff, and the use of advanced analytical methods for effective water quality assessment is thus needed. Machine learning (ML) has been proposed to improve accuracy and efficiency due to the inherent limitations of conventional water monitoring techniques in terms of scalability, real-time prediction, and pattern recognition. The study investigates the use of different ML algorithms, both in supervised and unsupervised learning approaches to evaluate water quality indicators like pH, DO, BOD, COD, and TDS. Using feature selection methods, a dataset included historical and real-time water quality data collected from various monitoring stations along the Ganges was processed and analysed to determine major pollutants impacting river health. We trained different ML models, including decision trees, random forests, SVM, and neural networks based on deep learning, and compared their multiple performance metrics, including accuracy, precision, recall, and F1-score. The results show that ensemble-based ML models are superior to conventional statistical approaches for predicting water quality trends and localizing pollution hotspots. Moreover, the study emphasizes the integration of real-time IoT sensors with ML models to enable continuous monitoring, which provides a proactive method for environmental management. The new findings can help policymakers develop data-driven policies related to river conservation, pollution control and sustainable water resource management. The potential for future work includes hybrid ML approaches, and the integration of satellite- or drone- based data to improve predictive power and spatial coverage [30].},
        keywords = {Ganges River, water quality analysis, machine learning, pollution monitoring, predictive modelling, environmental management, IoT sensors.},
        month = {April},
        }