Understanding leakage is an important challenge within the water sector to minimise waste, energy use and carbon emissions. Every Water Distribution Network (WDN) has leakage, usually approximated as Minimum Night Flow (MNF) for each District Metered Area (DMA). However, not all DMAs have instruments to monitor leakage directly, or the ...
Understanding leakage is an important challenge within the water sector to minimise waste, energy use and carbon emissions. Every Water Distribution Network (WDN) has leakage, usually approximated as Minimum Night Flow (MNF) for each District Metered Area (DMA). However, not all DMAs have instruments to monitor leakage directly, or the main dynamic factors that contribute to it. Therefore, this article will estimate the leakage of a DMA by using the recorded features of its pipes, making use of readily available asset data collected routinely by water companies. This article interprets this problem as a feature construction task and uses a multi-objective multi-gene strongly typed genetic programming approach to create a set of features. These features are used by a linear regression model to estimate the average long-term leakage in DMAs and Shapley values are used to understand the impact and importance of each tree. The methodology is applied to a dataset for a real-world WDN with over 700 DMAs and the results are compared to a previous work which used human-constructed features. The results show comparable performance with significantly fewer, and less complex features. In addition, novel features are found that were not part of the human-constructed features.
