Markov Decision Process Approximation Methods for Water Distribution Network Inspection and Maintenance: A Case Study of the U.S. Virgin Islands
2026-07-06 • Computational Engineering, Finance, and Science
Computational Engineering, Finance, and Science
AI summaryⓘ
The authors created a method to help decide when and where to inspect and fix water pipes, especially in places where it's hard to gather detailed data. They use a special mathematical model combined with realistic water flow simulations to understand the system without needing sensors on each pipe. Their approach shows that some system measurements can hint at specific pipe problems, which helps plan repairs more efficiently. This method works well in locations with limited resources and incomplete information.
water distribution networksMarkov decision processhydraulic simulationpipeline failureinspection planningmaintenance decision-makingresource-constrained environmentsvirtual sensing
Authors
Minsuk Seo, Daniel A. Eisenberg, Jefferson Huang
Abstract
We develop a repair-oriented inspection and maintenance decision framework for water distribution networks. This work is motivated by utilities operating in data-sparse environments, such as in remote locations like the U.S. Virgin Islands, where data collection about network state and underground pipeline outages is limited to above-ground and easy to access information (e.g., water tank levels and pump operations). We formulate the problem as a discounted Markov decision process and integrate it with high-fidelity hydraulic simulation. The model captures latent system dynamics without requiring pipe-level sensing. The results reveal state-dependent optimal policies and heterogeneous failure characteristics across pipes, including rare but high-impact behaviors. We further show that certain observable system states uniquely correspond to specific pipe failures, enabling a form of virtual sensing. These findings demonstrate that system-level dynamics can support inspection planning and maintenance decisions under uncertainty in resource-constrained settings.