Trends and Applications of Model-Driven Approach for Leak Detection in Water Supply Networks

Water loss is a maj or challenge for water utilities and has received widespread attention. The detection and localization of leaks is vital owing to the necessity to optimize the operation of water supply systems to satisfy the worldwide growing water demand. Over the years, water utilities have adopted a multitude of methodologies to achieve leak detection in water supply networks. These methodologies range from simple visual inspection to the use of hardware systems and now software using models and algorithms. Due to the development of smart sensing devices, data from flow or pressure measurements necessary to analyze water networks is increasingly becoming available. Coupled with the adoption of geographic information systems (GIS), supervisory control and data acquisition (SCADA) in the water sector, the use of model-driven approaches for leak detection and localization, in particular, has found widespread use. This paper presents the current research trends and applications of model-driven methodologies for leak detection in water supply networks. Several model-driven approaches and research studies for each case are discussed. Some challenges and research gaps are also discussed.