CAREER: Scalable AI-Driven Microclimate Simulation for Urban Heat Mitigation

Extreme heat events are the leading cause of climate-related deaths in U.S. cities. Mitigating the impacts of these events on human health requires understanding the outdoor distribution of heat in urban settings. Tools are available to model heat distributions for buildings and neighborhoods, but they cannot simulate city-wide areas in a reasonable time. This project will integrate artificial intelligence, urban microclimate modeling, and remote sensing to develop a scalable and efficient simulation platform for urban heat mapping and analysis. Components of the platform will be packaged and made available to the public as open-source software. The software will enable researchers and urban planners to test strategies that mitigate urban heat and improve human comfort in summertime. The project will support hands on training for students in artificial intelligence, data science and urban planning. Cities are increasingly exposed to more frequent and intense extreme heat events, making heat stress a critical and growing environmental hazard. This project will integrate physics-based microclimate modeling with publicly accessible, nationally available, high-resolution aerial remote sensing datasets. Machine learning methods will be developed to automatically derive fine-scale ground surface and urban geometry models from multispectral aerial imagery and geospatial data, enabling detailed representation of buildings, vegetation, and surface materials across large urban areas. Artificial Intelligent (AI) algorithms will be used to emulate key physical modeling processes and accelerate the generation of hyperlocal urban heat maps. The resulting AI algorithms will be packaged into an open-source toolkit to facilitate innovative research in artificial intelligence, geospatial data science, urban planning and design, urban environmental health, urban environmental science, and sustainability. This highly efficient platform will enable systematic evaluation of heat mitigation strategies and improvements in human thermal comfort. The platform will provide critical insights for developing effective adaptation and mitigation measures for extreme heat in cities. 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. NSF Award ID: 2543192 | Program: 01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Xiaojiang Li | Institution: University of Pennsylvania, PHILADELPHIA, PA | Award Amount: $586,660 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2543192 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2543192.html