Authors:
Raja Brahmendra Chowdary Veerepalli, S. Rubin Bose, J. Angelin Jeba, R. Regin, T. Shynu, M. Mohamed Sameer Ali
Addresses:
Department of Computer Science and Engineering, Texas State University, San Marcos, Texas, United States of America. School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India.
Abstract:
In this paper, researchers propose a machine learning (ML) - based predictive analytics platform for water quality assessment without the use of physical sensors. The proposed system uses advanced regression models and ensemble learning techniques to estimate critical water quality indicators from historical datasets, environmental parameters, and contextual factors. The platform provides scalable, efficient, and accurate predictions of water health through a data-driven architecture that replaces costly and maintenance-intensive sensor networks. Experimental studies have shown that it is robust in predicting metrics such as pH, turbidity, and dissolved oxygen with high fidelity, even when the data are noisy and incomplete. Besides its technical performance, the framework provides timely insights for early detection of contamination, resource optimisation, and sustainable management of aquatic ecosystems. The results show the potential of ML-driven platforms to revolutionise water monitoring practices, reduce reliance on infrastructure, and help decision-makers maintain safe, dependable, and environmentally friendly water management. Future work will include real-time environmental feeds, dynamic model adaptation, integration with IoT platforms, if necessary, and the development of explainable AI methods to enhance transparency and trust in water quality predictions.
Keywords: Water Quality Prediction; Artificial Intelligence; Machine Learning; Predictive Analytics; Sensor-Free Monitoring; Environmental Data Modelling; Sustainable Water Management; ML-Driven Platforms.
Received on: 11/12/2024, Revised on: 02/02/2025, Accepted on: 19/04/2025, Published on: 03/03/2026
DOI: 10.64091/ATIAS.2026.000294
AVE Trends in Intelligent Applied Sciences, 2026 Vol. 2 No. 1 , Pages: 30-44