Flooding is a widespread and costly disaster, with significant human and economic losses, as well as environmental impacts. Current infrastructure for managing floods is outdated and unseen, leading to static and ineffective responses. What if AI and sensor networks, like those used in autonomous vehicles, could create a dynamic, data-driven approach to flood management? This could involve retrofitting existing infrastructure with sensors and controllers to adapt to real-time conditions, potentially reducing flood damage by 30% with early predictions. This new generation of smart water systems might reduce urban flooding plaguing coastal cities with relatively low-cost interventions compared to massive new infrastructure project budgets. Branko Kerkez an Arthur F. Thurnau associate professor in the College of Engineering at the University of Michigan. He was recognized in 2018 by the National Academy of Engineering as a Gilbreth Lecturer for his contributions to smart water systems. Kerkez is committed to cultivating collaboration, as demonstrated in his Real-Time Water Systems Lab, which is open to graduate students, undergraduate student groups, senior design teams, community members and high school students. This “Hacker Space,” originally funded by U-M’s Third Century Initiative, provides tools and supplies for safely deploying water sensor networks and systems that can reduce flooding and improve water quality. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at https://www.ted.com/tedx