Predicting Contamination Events

Accurately predicting contamination events in complex water distribution networks based on vast, real-time data from sensors and models is a computationally demanding task for traditional methods.

Quantum computers are promised to enable the analysis of complex data sets through e.g. quantum machine learning or quantum anomaly detection to learn complex patterns in water quality data. These methods could be used to identify measurement anomalies that may indicate contamination. 

Implementing such sophisticated analytical tools can lead to earlier detection of contamination, reducing false alarms and improving the effectiveness of early warning systems, ultimately protecting public health and minimising service disruptions.