To advance, streamline, and modernize their water utility infrastructure, Sugar Land, Texas built what they call a dual-horizon predictive management system. The framework works to predict long-term pipe wear and flags pipes at risk using Artificial Intelligence (AI) and machine learning.

Just last week Alence Poudel, PE, the Senior Engineering Manager in Sugar Land, presented these findings at PWX in a session about AI, engineering, and future-proofing Sugar Land's water system.

We caught up with him and his colleague Trevor Surface, the Utility Field Operations Manager in Sugar Land, who also presented at PWX, to learn more.

The dual-horizon predictive management system works. We know that the model correctly flagged more than 82% of the pipes that failed in Sugar Land. By 2025, main breaks had dropped 25 percent.

But sometimes AI falls short, and while everyone is excited to introduce tech to meet the demands of growing costs, budget concerns, and rising community expectations, both Alence and Trevor agree that introducing a shiny new piece of sophisticated tech might not always be needed (or smart). While the promise of what this technology can do is incredible, they remind us not to forget we still have a long way to go, and nothing right now can replace human judgement.

Public Works Radio is hosted by Bailey Dickman, Senior Digital Marketing Specialist with APWA. Each episode dives into a wide range of topics designed to educate and inspire, making public works more visible to everyone, from the general public and elected officials to industry peers and the media. If you haven't already, please subscribe wherever you get your podcasts, rate and review the show, forward it to a friend, and drop us a note at podcast@apwa.org so we can hear your feedback directly!

More Show Notes and Resources

Alence Poudel, PE on LinkedIn: https://www.linkedin.com/in/alence-poudel-pe-6452a0179

Trevor Surface on LinkedIn: https://www.linkedin.com/in/trevor-surface-361050161/

Sugar Land Public Works: https://www.sugarlandtx.gov/98/Public-Works

Several of the research papers referenced in this episode are available here:

Dual-Horizon Water Main Planning Using Anchored Weibull and Enhanced XGBoost Models

A governance audit framework for large language model advice in civil infrastructure decision-making illustrated with local risk models in Sugar Land, Texas

Governance risks of AI reasoning in urban infrastructure through Delphi audit of human and large language model judgment

Hybrid human-AI governance framework for accountable decision-making in urban infrastructure management