NFPA Journal peers into the world of fire and big data and looks at how communities and fire departments around the country are using data analytics in imaginative ways to predict a host of risk factors and reduce fires.
Firebird has improved all aspects of the AFRD fire inspection process using machine learning, geocoding, and visualization software.
AFRD currently uses Firebird to compute fire risk scores for over 5,000 buildings in the city with true positive rates of up to 71% in predicting fires.
Applying AFRD’s criteria for fire inspection, Firebird has identified over 6,000 new potential commercial properties to inspect.
The National Fire Protection Association (NFPA) has highlighted Firebird as a best practice for using data to inform fire inspections.
The Atlanta Fire Rescue Department (AFRD) actively works to reduce fire risk by inspecting commercial properties for potential hazards and fire code violations. Most municipal fire department inspection practices rely on tradition and intuition rather than utilizing data-driven processes. However, AFRD has updated their inspection process to include the Firebird open source framework for predicting and reducing fires.
Firebird was developed through the Data Science for Social Good partnership between AFRD and Georgia Tech. This open source framework is designed to help municipal fire departments identify and prioritize commercial property fire inspections. Firebird has improved all aspects of the AFRD fire inspection process using machine learning, geocoding, and visualization software. Firebird integrates fire incidents, property information and risk scores into an interactive map that helps AFRD make informed decisions about fire inspections.