Collaborative Research: FIRE-WUI: Harnessing AI and Engineering Innovation for Post-Fire Property Decontamination and Economic Recovery
INSTITUTION
University of California-Los Angeles, CA
PRINCIPAL INVESTIGATOR
Sanjay K Mohanty
FUNDING
$325K
YEAR
2026
MOONBASE SCORE
Still being scored
LOADING MOONBASE SCORE
Abstract
Fires at the wildland-urban interface damage property and infrastructure and release hazardous materials. After a fire, stakeholders must assess the safety of contaminated property and infrastructure. This project aims to improve assessment of post-fire property and infrastructure contamination and enhance the accessibility of these assessments for stakeholders. The project will advance fundamental understanding of contamination during wildland-urban interface fires, improve sampling and testing, and develop an AI-supported platform for access to testing data, thereby enhancing decontamination and economic recovery efforts. This project will address gaps in necessary post-fire property sampling and testing, along with better understanding the needs of residents. The project focuses on three research objectives: 1) examining the fundamental processes governing the fate and transport of wildfire contaminants in wildland-urban interface fires, and applying this knowledge to guide water and soil testing post-fire, 2) identifying residents’ needs, and 3) leveraging AI to assess how best to navigate multiple data sources and using this assessment to develop an interactive online platform to support decontamination and economic recovery efforts. Partners from fire-impacted communities will be engaged. Key project activities include analyzing contaminants generated during the burning of mixed household products and examining their transport into the plumbing system and through burned soils. Results will shed light on exposure risks after a wildfire. To capture community needs, residents impacted by specific fires will be interviewed to identify key factors influencing community priorities. Further, a tool combining large language model-assisted and rule-based methods will harmonize disparate data sources into a structured report for use by stakeholders. 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.
Are you the primary organization running this research?
The two tools below are built for the principal investigator & host institution behind this project.