Real-Time Assessment of Water Quality Degradation in Mining-affected and Urban Watersheds using IoT Sensors and ML Models
Disaster Advances · 31.07.2026 · 19 (9) · 98
DOI: 10.25303/199da0980108 ↗Kurz gefasst
Fachartikel in der Zeitschrift Disaster Advances, online erschienen am 31.07.2026. Verfasst von Rajeswari U. und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Urbanism and mining of local resources in Singrauli (Madhya Pradesh) and Dudhi (Uttar Pradesh) have caused continuous deterioration of water quality. This study proposes a framework for near real-time assessment using IoT sensors integrated with machine learning algorithms to monitor and predict metal contamination in watershed systems. The study targets: (1) Establishment of continuous monitoring network to record multi-metal fluctuations and (2) Developing a risk-based machine learning methodology for human health impact quantification. HQ results indicated strong spatial and demographic differences. Maximum HQ values in Singrauli ranged from 50–60 for Fe, 30– 36 for Mn and 4–4.8 for Pb among adults and children, while slightly lower values were observed in Dudhi. Median HQ findings indicated chronic exposure risks, particularly in children, whose HQ values were 20– 30% higher than adults for most metals. Cr and Cd were also identified as contaminants posing health risks through mining discharge and surface runoff. Integration of IoT sensing with ML predictive capability improved early warning through rapid detection of contamination spikes. These hybrid systems are effective for water governance in miningaffected and urbanizing regions.
Zitieren
APA
U., R., Devi, C., S., G., S., T., P., Gupta, S., & V., P. (2026). Real-Time Assessment of Water Quality Degradation in Mining-affected and Urban Watersheds using IoT Sensors and ML Models. Disaster Advances, 19(9), 98. https://doi.org/10.25303/199da0980108
Vancouver
U. R, Devi, C. S, G. S, T. P, Gupta S, et al. Real-Time Assessment of Water Quality Degradation in Mining-affected and Urban Watersheds using IoT Sensors and ML Models. Disaster Advances. 2026;19(9):98. doi:10.25303/199da0980108
BibTeX
@article{U2026,
author = {U., Rajeswari and Devi and C., Srikanth and G., Shyamala and T., Pradeep and Gupta, Sheifali and V., Priya},
title = {Real-Time Assessment of Water Quality Degradation in Mining-affected and Urban Watersheds using IoT Sensors and ML Models},
journal = {Disaster Advances},
year = {2026},
volume = {19},
number = {9},
pages = {98},
doi = {10.25303/199da0980108}
}
EUVIMED