RAPID: Tuning and Assessing Lahaina Wildfire Models with AI Enhanced Data

There is an urgent need to collect data from the Lahaina Fire on Maui that is critical for on-going wildland and urban fire modeling efforts. Being an isolated location with limited wind and environmental observations, other data sources must be tapped to advance modeling and simulation research before these sources are lost. The data capture from multiple sources including social media and time-stamped photos, organized with AI-enhanced methods for data gathering, processing, and infusion will be led by Maui-based researchers working with Maui students.

The work will show the importance of data in the understanding of fire propagation inside the community and interaction with urban structures with an additional goal of educating the public and enabling the Hawaii government and emergency response personnel to make decisions to counteract the disaster. This will aid in the development of policies to reduce the likelihood of major loss of life and property damage in the future.

Advanced AI techniques deployed on High Performance Computing (HPC) resources at the University of Hawai’i, the NSF’s Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support (ACCESS) program and other national infrastructure will be used to process the large volumes of data to obtain required information needed to tune and validate fire propagation and atmospheric simulations. The collected data will be archived and made publicly available in the Data Depot repository supported by NSF’s Natural Hazards Engineering Research Infrastructure (NHERI) program.

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.