Author(s): Prisha Puri; Sudarshan Kurwadkar; Doina Bein

Linked Author(s): Sudarshan Kurwadkar

Keywords: Data Clustering; Drinking Water; Risk Assessment

Abstract: United Nations recognized access to safe drinking water as a human right, yet many countries in the developing world lack access to potable water. Recurrent incidences of water-borne illnesses have a devastating effect on the morale and personal well-being of many people living in developing countries, contrasting the achievement of the UN’s objective. Qualitative and semi-quantitative approaches used for risk assessment are often ineffective, time-consuming, and do not discern the risk due to ingestion of unsafe drinking water at the global scale. This research utilizes a global dataset of drinking water facilities to evaluate the risks using a clustering approach. Extensive data analysis involving predetermined risk thresholds, the exceedance of which indicates the potential adverse risk. These risk-thresholds are based on the JMP Service Ladder, which effectively utilizes density-based spatial clustering of applications. Risk analysis of 132 datasets was conducted to designate the risk categories ranging from low, medium, and high-risk. Of the dataset analyzed, 90 areas were designated as a low-risk category while 42 were medium-risk. Overall, the clustering approach is an excellent tool to analyze a large dataset for risk assessment which will help the potential stakeholder, including the water utility manager, to assess the potential risk due to declining water quality quickly. Additionally, the clustering approach can be further harnessed for better data visualization, long-term performance evaluation of water utility, and real-time drinking water quality monitoring.

DOI: https://doi.org/10.3850/IAHR-39WC2521711920221253

Year: 2022