Authors : Ayush Ram

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/4wcxmyk5

Scribd : https://tinyurl.com/3b8t7bad

DOI : https://doi.org/10.38124/ijisrt/26jun1814

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Access to safe drinking water remains a critical challenge in the coastal rural communities of Kerala, India, where groundwater salinisation and contamination affect millions of households. Conventional coping strategies—including bottled water consumption and firewood-based boiling—impose significant economic burdens and environmental costs while offering no real-time indication of water quality. This study presents Nyxera, a proposed decentralised water purification system integrating coconut-shell activated carbon filtration with solar distillation and an AI-based predictive maintenance pipeline. In the absence of a physical prototype, a physics-based synthetic dataset of 5,500 observations was generated using published benchmarks for Kerala solar irradiance (433–898 W/m²), coastal groundwater salinity (32,000 ppm TDS), and coconut-shell adsorption parameters. A Random Forest regression model trained on this dataset achieved an R² of 0.9987 and a mean absolute error (MAE) of 41.3 ppm on a held-out test set, identifying a theoretical filter saturation threshold at approximately 288 litres of cumulative throughput under median pre-monsoon conditions. A companion Life Cycle Assessment (LCA) projects annual CO2 savings of 21.98 tonnes across 25 households (100 people), primarily through displacement of plastic bottle consumption and biomass-based water boiling. This work establishes the computational and algorithmic foundation for a low-cost predictive maintenance alert system capable of notifying households before filter output exceeds the WHO potable limit of 500 ppm TDS. Field validation using a physical prototype remains the immediate next research phase.

Keywords : Water Purification, Activated Carbon, Solar Distillation, Predictive Maintenance, Random Forest, Machine Learning, Kerala, Groundwater, Life Cycle Assessment, Decentralised Water Treatment.

References :

1. World Health Organization. (2017). Guidelines for Drinking-Water Quality: Fourth Edition Incorporating the First Addendum. WHO Press, Geneva.
2. Kerala Water Authority. (2022). Annual Report on Groundwater Quality in Coastal Districts. KWA, Thiruvananthapuram.
3. Breeman, G., & Regan, C. (2021). Coconut-shell activated carbon: Properties, production and applications for water treatment—A review. Journal of Environmental Management, 287, 112–131.
4. Mathioulakis, E., Belessiotis, V., & Delyannis, E. (2007). Desalination by using alternative energy: Review and state-of-the-art. Desalination, 203(1–3), 346–365.
5. Goswami, D. Y., & Kreith, F. (Eds.). (2015). Energy Efficiency and Renewable Energy Handbook (2nd ed.). CRC Press.
6. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
7. Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
8. ISO 14044:2006. Environmental Management—Life Cycle Assessment—Requirements and Guidelines. International Organization for Standardization, Geneva.
9. Singh, R. (2015). Membrane Technology and Engineering for Water Purification (2nd ed.). Butterworth-Heinemann.
10. Nair, M., & Kumar, D. (2021). Salinization of coastal aquifers in Kerala: Magnitude, drivers, and remediation strategies. Hydrogeology Journal, 29(4), 1421–1439.
11. Tiwari, G. N., & Tiwari, A. K. (2008). Solar Distillation Practice for Water Desalination Systems. Anshan Publishers.
12. UNICEF / WHO. (2023). Progress on Household Drinking Water, Sanitation and Hygiene 2000–2022. UNICEF, New York.