.svg)
To determine the most effective locations of the sewer network to monitor and stop sewer overflows.
A risk matrix was developed using consequence and likelihood metrics across environment and public health sectors.
The client had a risk management tool to inform the prioritisation of future network monitoring.
To have a more efficient method of detecting leaks within the sewer network.
A machine learning model was developed to predict likely locations of leaks within the network.
Optimisation of survey scheduling, prioritising field crew surveys and improving efficiency in finding more leaks with less survey.
Create an efficient asset management system that values a high cost benefit ratio and low long term maintenance expense.
Developed an automated analysis for maintaining sections of the water network based on replacement vs predicted future failure metrics.
Visibility of water network replacements that will have the highest cost benefit ratio and lowest long term maintenance cost.
