Understanding Network Wide Hurricane Evacuation Traffic Pattern from Large-scale Traffic Detector Data

In this study, we develop a data pipeline incorporating automated data quality checking, data imputation, and spatiotemporal visualization of large-scale traffic data to understand the changes in traffic patterns during hurricane evacuation as it unfolds. We collect large-scale Microwave Vehicle Detection System (MVDS) data during Hurricane Irma from four highways in Florida: I–75, I–95, I–4, and Florida Turnpike that served majority of the evacuation traffic. Based on an extensive analysis, we provide insights on network wide spatiotemporal evacuation traffic patterns of Hurricane Irma. Such insights will help transportation agencies recognize the utility of large-scale real-time data, previously unused, to better understand the extent and spatiotemporal distribution of evacuation traffic. To demonstrate this, we analyze the processed data to understand the influence of different spatiotemporal factors on the changes in evacuation traffic pattern. Our results show at least an 18-hour (approximately) time lag between the time of issuing an evacuation order and the time when people first started to evacuate in large numbers. Such findings have potential implications to deal with the challenges of mass evacuation in real time and allows us to develop large-scale network level evacuation traffic prediction model.