Fighting Fires with Big Data
The term “smart” has been used to describe everything from refrigerators to plastic cards with built-in microprocessors.
But smart has taken on a new meaning for researchers and public safety professionals tasked with merging the world of sensor technologies and fire service. They call this combination smart firefighting. The National Institute of Standards and Technology (NIST) defines it as the ability to “fully exploit select data to perform work tasks in a highly effective and efficient manner.”
While this type of work is not new, it’s only in the past six months to a year that the phrase has gained traction, says Casey Grant, research director at the Fire Protection Research Foundation.
The New York City Fire Department has become the poster child for smart firefighting and how the exploitation of Big Data can empower firefighters to perform their duties effectively and efficiently.
More than a year ago FDNY deployed a data analytics algorithm called FireCast 2.0, which helps the department manage the buildings it inspects and prioritize which structures are at greatest risk of experiencing a fire, according to the NFPA Journal — the official magazine of the National Fire Protection Association. Fire department officials say the tool eases their workloads, simplifies complex tasks and ensures that firefighters tend to buildings that are most prone to fires. The tool powers the department’s Risked-Based Inspection System program, which was created to assess and prioritize buildings that firefighters inspect each year.
Mining the Data for Answers
In July, StateTech reported on the use of applied analytics to improve building safety. In New York City, officials use a wealth of data to understand which buildings are most prone to fires. They found that older structures, buildings at the center of ongoing foreclosure proceedings and buildings with active tax liens and complaints were more likely than illegal conversions to go up in flames.
The FDNY plans to launch FireCast 3.0 early next year. The algorithm will sift data collected from 17 city agencies and the city’s non-emergency 311 reporting service, while also accounting for some 7,500 fire risk factors, such as building specifications, trash violations and noise complaints. The NFPA Journal explains how the algorithm will work:
Every night, powerful computers at FDNY’s sleek modern headquarters in downtown Brooklyn will use the FireCast 3.0 algorithm to analyze three years’ worth of data for every building in the city. Using the variables and each neighborhood’s unique fire history, FireCast 3.0 will perform a complex statistical analysis and assign every building FDNY inspects with a fire risk score.
The buildings with the highest risk score will be placed near the top of a building-inspection to-do list, assigned daily to each of New York’s 341 fire companies. FireCast also considers buildings that the fire department is legally required to inspect on a set schedule—schools, buildings under construction, and condemned buildings, for example—and adds those to the top of the list. The entire computational process will take about 90 minutes.
Grant isn’t aware of other fire departments around the nation that have this capability, but his organization is partnering with NIST to create a Research Roadmap for Smart Fire Fighting. The project is expected to wrap up spring 2015.
With the rise of sensor technology, Big Data and the Internet of Things, Grant says, “emergency responders want to know how we are going to pull it all together.”