1. Home
  2. RIP
  3. View Record
https://www.nationalacademies.org/trb/events

Flood-resilient Transport System Through Integrated Modeling, ML & Immersive AR/VR

Extreme rainfall events increasingly disrupt urban transportation systems by overwhelming drainage infrastructure and causing localized road flooding that impedes last-mile freight delivery, delays emergency response, and disrupts the broader multimodal supply chain. These disruptions limit access to essential services, delay emergency response, and threaten public safety. Building on the research team's previously developed framework (F25-26), this project advances a data-driven approach for high-resolution prediction of urban road flooding in Jackson, Mississippi, integrating geospatial databases, process-based H-H modeling (aligning with rigorous U.S. Army ERDC methodologies), and machine learning (ML) and artificial intelligence (AI) techniques to identify flood-prone road and railway segments. The ML-based surrogate models will maintain computational efficiency, enable timely identification of vulnerable transportation networks, and support emergency response by feeding into JSU Water Lab’s broader web-based-visualization interfaces. This project introduces an interactive K–12 STEM module, age-appropriate hands-on activities along with STEM curriculum module designed for upper-level Civil Engineering undergraduate and graduate students at JSU. This initiative transforms research outcomes into the classroom to modernize workforce training using integrated Augmented Reality (AR) and Virtual Reality (VR) and will be tested with summer student exchange programs. Students can explore and 3D print several transportation infrastructure components, such as culverts, bridges, and urban drainage systems, and evaluate their performance under simulated flood conditions, and experience AR/VR based immersive simulators. Using AR/VR tools, including the Meta Quest platform, available in the PI lab, future transportation engineers will visualize flood scenarios in immersive 3D environments built from existing topographical assets in Unity or Unreal Engine. By combining advanced predictive modeling with experiential learning, the project promotes advanced STEM engagement, and high-tech workforce development, aligning with broader goals of improving multimodal transportation system resilience. While the primary focus is on urban road and rail flooding, these transportation corridors serve as critical connectors to Mississippi's inland waterway freight network, including facilities linked to the Pearl River system and regional multimodal freight movements. Roadway disruptions during extreme rainfall events can delay freight access to ports, intermodal terminals, water-dependent industrial facilities, and affect supply-chain resilience. By identifying flood-vulnerable roadway and railway segments, the proposed framework will support more reliable connectivity between surface transportation infrastructure and maritime freight operations