Collaborative Analysis for Computational Risk in Urban Water Supply Systems

Urban Water Supply (UWS) is one of the most critical and sensitive systems to sustain overall city operations. The European Union (EU) has strict water quality regulations that currently depend on periodic laboratory tests of selected parameters in most of the cases. The tests of some biological parameters can take up to 48 hours, which leads to the delay of risk detection and lengthens the response time for taking countermeasures in UWS. This situation increases the risk of negative impacts to the health of mass population. To address this challenge, we propose a data-driven risk analysis method which is low-cost and efficient. First, we build a framework for risk evaluation and prediction, within which a risk evaluation model is introduced considering the Quantitative Microbiological Risk Assessment (QMRA) process suggested by the World Health Organization (WHO). Second, we present a collaborative method to analyze biological risk features and similarities across different locations. Third, we propose a new risk prediction algorithm. We apply this method on the real-world data collected from 4 UWS systems in Norway. The preliminary results are depicted in risk maps and prediction accuracies are compared with different strategies. The application results show that our method is practical with good accuracy and explainability.