"Integrating Digital Twins, GeoAI, and SUMO for Flood-Resilient Urban Transportation Systems"

Abstract: Flooding poses a significant threat to transportation infrastructure, yet research on the effects of dynamic flood levels on road networks remains limited. In smart cities, there is potential to harness digital data on travel demand, infrastructure, and water levels to enhance flood management and address social inequities—particularly since vulnerable populations, such as those without access to vehicles, are disproportionately affected during flooding events. However, traditional traffic simulation models often overlook critical factors like terrain, landscape types, and elevation, limiting their effectiveness in accurately assessing infrastructure interdependencies during floods. Prior studies underscore the importance of integrated urban planning in managing these interdependencies.
Our research aims to model the interplay between water and transportation infrastructures, evaluating flood risks and their impact on road networks. We develop an interoperable digital twin framework that integrates road networks with simulations of rising water levels, focusing on rerouting strategies during flash floods to assess infrastructure vulnerabilities in both Hyde County, NC (a rural area) and Wilmington, NC (an urban area). Using a combination of tools including SUMO, Rhino, Urbano, and Python, along with publicly available elevation and Height Above Nearest Drainage (HAND) datasets, we simulate flooding scenarios and identify high-risk roads and intersections.
The results show that (a) open-source tools effectively capture the impact of rising water levels by identifying submerged roads, which can lead to partial or complete lane closures in traffic simulations, supporting dynamic rerouting, and (b) interoperable flood and transportation models can facilitate timely identification of flood-prone roads, helping mitigate the effects of flash floods. Our findings contribute to improved disaster preparedness and more efficient emergency response strategies.