Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Building Fire Hazard Predictions Using Machine Learning

Published

Author(s)

Eugene Yujun Fu, Wai Cheong Tam, Tianhang Zhang, Xinyan Huang

Abstract

The lack of information on the fire ground has always been the leading factor in making wrong decisions . Wrong decisions can be made by individual firefighters, their local chiefs, and/or the incident commander. Any wrong decision at any level (scale) will propagate up increasing the safety hazards for both the firefighters and the burning structure. The rapidly expanding commercialization of and diversity of smart fire protection sensors, however, is about to change all of that. Real-time information on the fire ground will soon be available and this opens new opportunities for situation monitoring and analysis. However, these are three major challenges: 1) scarcity of real-world data, 2) data understanding and fire forecast, and 3) model validation. This chapter will provide details on steps and approaches to overcome each of these challenges and will describe how sensor data can be used to develop data-driven prediction models to provide real-time, trustworthy, and actionable information to enhance situation awareness, operational effectiveness, and safety for firefighting.
Citation
Intelligent Building Fire Safety and Smart Firefighting
Publisher Info
Springer, New York, NY

Keywords

Flashover, support vector regression, bi-directional long short-term memory, attention mechanism, graph convolutional neural network

Citation

Fu, E. , Tam, W. , Zhang, T. and Huang, X. (2024), Building Fire Hazard Predictions Using Machine Learning, Intelligent Building Fire Safety and Smart Firefighting, Springer, New York, NY, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=936750 (Accessed March 3, 2024)
Created January 26, 2024, Updated January 29, 2024