Developing a Machine Learning-Based Framework for Roadway Vulnerability and Impact Assessment Using Aerial Imagery

Abstract This study developed a machine learning-based framework for assessing roadway vulnerability and impacts in hurricane-prone regions, utilizing remote sensing techniques. To quantify the immediate and consistent impacts of hurricanes on the roadway network, the study developed two key metrics: the road closure impact index (RCII) and the roadway vulnerability index (RVI). The RCII assesses the severity of roadway closures by analyzing detected bounding boxes from high-resolution aerial imagery, offering insight into the spatial extent and severity of disruptions caused by each storm. In contrast, the RVI evaluates the consistency of roadway closure patterns across multiple events, revealing vulnerabilities within the transportation infrastructure through geospatial analysis. Also, by leveraging aerial imagery, remote sensing technology, and advanced machine learning models, the study assessed the impacts of Hurricanes Idalia and Debby on Taylor County, Florida, effectively classifying county roadway conditions in their aftermath into three categories: open, partially closed, and fully closed. Findings indicate that Hurricane Idalia caused significant structural damage due to wind and storm surge, while Hurricane Debby led to prolonged flooding and subsequent road submersion. By comparing the impacts of these two hurricanes, the study highlights the critical role of integrating machine learning, geospatial analysis, and remote sensing for enhanced disaster preparedness and response strategies. Ultimately, this framework provides critical insights for improving infrastructure resilience and planning efforts in coastal communities vulnerable to extreme weather events.