Real-time information driven decision support system for evacuation planning

Mass traffic evacuations during Hurricanes Rita and Katrina demonstrated limitations of static planning-based evacuation models based on data from historical events. Evacuation dynamics are complex due to the number of people and vehicles, road networks, the uncertainty and perception of the event, public safety advisories, and human decisions regarding evacuation routes and behaviors. We describe a system under development for real-time information driven decision support system for evacuation planning and response. This system consists of an evacuation traffic prediction model injected with situational information extracted from traffic sensors and social networking sites. The situational awareness information obtained from multiple sources is fused with historic stated-preferences behavior data. Our model is novel because it augments standard evacuation models with evacuee sentiment via social media networks.