Case Study: University of Texas at Austin achieves scalable national flood forecasting and improved public safety with Microsoft Azure

Centralizing National Flood Data in the Cloud Can Help Save Lives and Property

The National Flood Interoperability Experiment (NFIE), led by researchers at the University of Texas with federal agencies, first responders and Microsoft Research, set out to close the gap between national flood forecasting and local emergency response. Faced with floods that cause the most deaths and highest costs of any U.S. disaster—and with regional systems that could not scale nationally—the team needed a way to centralize diverse hydrologic data, standardize formats, and deliver timely, location-specific forecasts to communities and responders.

Using Microsoft Azure, NFIE deployed the RAPID river-routing model on virtual machines with a Data Wolf workflow, and adopted a common data language (WaterML) to standardize and share time‑series data. The cloud prototype demonstrated the ability to scale far beyond university systems—aiming to deliver actionable forecasts for an estimated 2.67 million locations (a >700× increase in spatial density over current forecasts)—and produced a reusable template to improve real-time decision making, public safety, and potential life- and cost-savings.

University of Texas at Austin

David Maidment

Professor of Civil Engineering