Mitigating the adverse impacts caused by increasing flood risks in urban coastal communities requires effective flood prediction for prompt action. Typically, physics-based 1-D pipe/2-D overland flow models are used to simulate urban pluvial flooding. Because these models require significant computational resources and have long run times, they are often unsuitable for real-time flood prediction at a street scale. This study explores the potential of a machine learning method, Random Forest (RF), to serve as a surrogate model for urban flood predictions. The surrogate model was trained to relate topographic and environmental features to hourly water depths simulated by a high-resolution 1-D/2-D physics-based model at 16,914 road segments in the coastal city of Norfolk, Virginia, USA. Two training scenarios for the RF model were explored: (i) training on only the most flood-prone street segments in the study area and (ii) training on all 16,914 street segments in the study area. The RF model yielded high predictive skill, especially for the scenario when the model was trained on only the most flood-prone streets. The results also showed that the surrogate model reduced the computational run time of the physics-based model by a factor of 3,000, making real-time decision support more feasible compared to using the full physics-based model. We concluded that machine learning surrogate models strategically trained on high-resolution and high-fidelity physics-based models have the potential to significantly advance the ability to support decision making in real-time flood management within urban communities.
Climate change and sea level rise have increased the frequency and severity of flooding events in coastal communities. This study quantifies transportation impacts of recurring flooding using crowdsourced traffic and flood incident data. Agency-provided continuous count station traffic volume data at 12 locations is supplemented by crowd-sourced traffic data from location-based apps in Norfolk, Virginia, to assess the impacts of recurrent flooding on traffic flow. A random forest data predictive model utilizing roadway features, traffic flow characteristics, and hydrological data as inputs scales the spatial extent of traffic volume data from 12 to 7736 roadway segments. Modeling results suggest that between January 2017 and August 2018, City of Norfolk reported flood events reduced 24 h citywide vehicle-hours of travel (VHT) by 3%, on average. To examine the temporal and spatial variation of impacts, crowdsourced flood incident reports collected by navigation app Waze between August 2017 and August 2018 were also analyzed. Modeling results at the local scale show that on weekday afternoon and evening periods, flood-impacted areas experience a statistically significant 7% reduction in VHT and 12% reduction in vehiclemiles traveled, on average. These impacts vary across roadway types, with substantial decline in traffic volumes on freeways, while principal arterials experience increased traffic volumes during flood periods. Results suggest that analyzing recurring flooding at the local scale is more prudent as the impact is temporally and spatially heterogeneous. Furthermore, countermeasures to mitigate impacts require a dynamic strategy that can adapt to conditions across various time periods and at specific locations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.