One of the most significant challenges facing water utilities is managing water losses, also known as “non-revenue water” (NRW), defined as water produced but not billed to customers. This paper investigates the use of Internet of Things (IoT) devices to monitor real-time changes in smart water networks known as smart water distribution management (SWDM) monitoring. Any sudden data shift signal indicates potential issues, allowing continuous monitoring and analysis to identify operational problems. The study aims to simulate the behavior of the network during maintenance and operation. The proposed machine learning models have been integrated with various applications, including geographic information systems (GIS) and physical data, which require comprehensive and measured information. This paper proposed an approach for monitoring the water distribution network to maintain a low NRW level. The study verified that polynomial regression outperformed other machine learning algorithms with an R2 score of 0.996.