The National Science Foundation (NSF) awarded a $199,976 EAGER (Early-concept Grants for Exploratory Research) project grant to the University of Delaware to develop an open-source, AI-enabled synthetic population inventory to facilitate disaster impact assessment studies. The project aims to create comprehensive and accurate synthetic datasets integrating people, the built environment, and behavior, which can serve as crucial data sources for training and testing resilience tools as well as informing disaster policies. The research project introduces a novel generative AI framework to learn patterns in microdata and produce diverse, realistic synthetic populations, while also revealing explicit household and building relationships through machine learning. This work has the potential to transform how synthetic populations are used in various fields, making disaster planning and policy development more effective and accessible. No sub-awards are planned under this 24-month project, which runs from December 2024 to November 2026.
Generated 3/4/25, 7:03 AM