Having regular and current information on the condition of underground water assets would empower Councils to optimise the deployment of resources and prioritise repairs, maintenance and renewals.
However, water infrastructure can span vast areas and network characteristics vary significantly in terms of material, age, diameter and depth. When you add external influencing factors like soil, land stability and vegetation into the mix, being able to have a good understanding of the entire network, the different risks and where to spend the limited budget is a considerable challenge.
One solution to this problem that has been trialed and implemented successfully internationally is the use of Geospatial Artificial Intelligence (AI) which uses machine learning processing of satellite imagery combined with input data such as pipeline attributes and failure history. The process enables a likelihood of Failure score to be generated for every pipeline section based on a range of risk factors and types of events.