SBIR Phase II: An Intelligent, Analytics-Driven System for Disaster Resilience and Situational Awareness

The broader/commercial impact of this Small Business Innovation Research (SBIR) Phase II project is a potentially significant reduction in the human and economic toll of disasters, which now cost the United States billions of dollars each year. Emergency managers often struggle with scattered, outdated information that delays critical decisions. By transforming diverse streams of data—ranging from mobility data to lifeline systems—into quantitative, near-real-time insights, this project aims to help agencies anticipate evacuations, identify failing lifelines such as power and water, and target assistance to exposed residents. Faster, data-driven responses can save lives, speed community recovery, and curb economic losses. The technology’s cloud-based delivery and seamless connection to widely used geographic information systems will lower adoption barriers for local and state agencies, creating a path to large-scale deployment. Commercially, the work addresses a rapidly growing disaster resilience market, with potential to generate high-skill jobs and new tax revenues while reducing the economic and societal impacts of disasters on people. The technical merit lies in the development of a unified platform consisting of a suite of predictive, analytical, and generative AI applications that fuse multi-modal data feeds into continuously updating situational-awareness layers - anticipating evacuations, detecting lifeline outages, and generating trusted, context-aware guidance for disaster responders. Building on validated prototype modules for evacuation and community-lifeline monitoring, Phase II focuses on hardening these capabilities for hurricanes, wildfires, and floods while introducing three new functions: predictive evacuation analytics that blend historical behavior with evolving hazard indicators; an AI-powered disaster co-pilot that converts complex data into best-practice guidance; and a public-health module that gauges hospital capacity, pharmacy access, and special-needs shelter demand. Core AI workflows will automate ingestion, transformation, and geospatial delivery of multi-format data into existing emergency-management platforms. Iterative testing in hazard-prone environments, supported by established agency partnerships, will refine algorithms, user interfaces, and trust metrics. Success will yield a scalable, secure, and difficult-to-replicate solution that empowers decision-makers across the disaster lifecycle, from blue-sky exposure assessments to dynamic incident response. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.