This study proposes the risk assessment framework of water distribution networks with a focus on the determination of weights of various risk indices. First, the pipe risk list is built, in which pipe failure probability and consequence are considered. By integrating the analytic hierarchy process (AHP) and the entropy weighting method (EWM), the weights of these indices are obtained by the combined weighting method (CWM), by which both human experience and data distribution can be considered comprehensively. Taking a real WDN in an industrial zone in China as an example, the proposed method is demonstrated in detail and the risks of all pipes are determined. The accuracy of the CWM is validated from the perspective of risk levels of pipes with historical failure records. It is found that the AHP or EWM underestimates or overestimates pipe risks, respectively. Compared to them, the CWM provides reasonable results. In addition, the risks of plastic pipes, newly buried pipes less than five years old, and pipes over twenty years old are much higher.

The reliability of urban water distribution networks (WDNs) is critical for ensuring sustainable infrastructure management. However, traditional failure prediction models often overlook the complex interdependencies between water pipelines and road networks, leading to suboptimal predictive accuracy. This study introduces a novel pipeline failure prediction framework that leverages Graph Neural Networks (GNNs) to incorporate coupled road–pipeline network features. By integrating traffic-related indicators, such as intersection proximity, pipeline–road angles, and network topology, this approach systematically assesses their impact on failure risk. A comparative evaluation of various GNN architectures, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), and GraphSAGE, demonstrates that GraphSAGE achieves the highest predictive performance, significantly surpassing traditional machine learning methods. The findings underscore the necessity of incorporating network topology into predictive models, validating the role of spatial dependencies in accurately assessing pipeline failure risks. This study contributes to advancing infrastructure resilience modeling by providing a robust predictive framework that supports proactive maintenance strategies and enhances risk mitigation in urban water distribution systems.