The City of the Future Has Fewer Fires, Thanks to CMU
By Scott Barsotti
A predictive model developed by CMU’s Metro21 Smart Cities Institute is extremely accurate at pinpointing risk of fire in commercial properties. It is now being utilized by the Pittsburgh Bureau of Fire and has the potential to make communities safer across the country and worldwide.
“What if you could use technology to determine the next building that was going to catch on fire?”
Pittsburgh Mayor Bill Peduto excitedly asked this question at a recent press conference. The City of Pittsburgh’s tech-forward executive is a proponent of using technology and data analytics to improve civic life, and it was plain to see that the prospect of a predictive model that could identify which properties in the city were at the highest risk of fire had him ecstatic.
Not only could such a tool save lives, it would have economic benefits by minimizing property damage, lowering the cost of commercial insurance in the city, and reducing the amount of resources expended by fire departments.
To get a sense of just how effective this tool is, consider this:
There are over 22,000 commercial properties in the City of Pittsburgh. With so many buildings in the city limits—many of them aging—it is impossible for the Bureau of Fire to inspect them all in a timely fashion. That means many buildings with a high risk of fire may go years without a proper inspection. For Michael Madaio, Ph.D. student at Carnegie Mellon’s Human-Computer Interaction Institute, that was a glaring problem that urgently needed a solution.
This will make us one of the safest cities in the world for fire prevention.Pittsburgh Mayor Bill Peduto
Madaio refers to some recent high-profile and deadly fire incidents, such as the "Ghost Ship" warehouse fire in Oakland, California in 2016, and others in London and Brooklyn in 2017.
“Those incidents revealed that those properties were on the radar of other municipal agencies for safety violations, but had not recently been inspected for fire safety violations,” said Madaio. “[This was] due to a lack of inter-agency data sharing and, perhaps, a lack of data-driven proactive risk reduction efforts.”
Madaio added that many cities, Pittsburgh included, face a big challenge in working with limited personnel and budgets. That gap between the need to reduce risk and the resources available made this project all the more urgent.
From Heinz College, graduate students Bhavkaran Singh, Qianyi Hu, and Palak Narang—all from the Master of Information Systems Management (MISM) program—collaborated on the project as well.
The team built a predictive algorithm, training it on historical fire incident and inspection data as well as business permits and property condition information. The resulting tool analyzed the city’s commercial properties and assigned each property a fire risk score. The algorithm scanned those 22,000+ properties and labeled 57 as having the highest risk.
The model’s prediction was extremely accurate. Of those 57 high risk properties, 50 experienced a fire incident of some type within a year of being tagged by the system.
You don’t have to be a data scientist to know that 57 is a much more manageable number than 22,000. With that kind of predictive power in hand moving forward, officials from the Fire Bureau can prioritize which properties get inspected and stop more fires before they occur.
“This will make us one of the safest cities in the world for fire prevention,” said Peduto.
According to Madaio, the model he and Metro21 created is currently the state of the art in fire prevention, nearly twice as predictive as the next most accurate model.
She said that getting to work on a project with this kind of impact was more than she ever expected when she came to Heinz.
“This is big. This is a commercially viable model that is going to be used.”
SMART CITIES ARE SAFER CITIES
The Metro21 Smart Cities Institute, a university-wide research center housed at Heinz College, is ambitiously pursuing smart cities research that can be deployed to not only improve the lives and opportunities of citizens, but also make communities measurably safer.
The success and accuracy of this fire prevention tool—a tool which will only get more accurate over time—is a testament to Metro21’s impact in the region. Soon, the impact of this project will spread to other parts of the country.
“The [Pittsburgh] fire department is already using this,” said Madaio, “and we are partnering with fire departments from several other cities, including Dallas, to help them adapt the model to their cities.”
The National Fire Protection Association (NFPA) named this research program a “best practice” for improving public safety, and GovTech awarded the project “Innovation of the Month” in January 2018. The model has been promoted to the MetroLab Network—of which Metro21 is a founding member—and Metro21 has made their code open-source in order to facilitate further adoption.
The results from this work have also been accepted for publication in the prestigious Knowledge Discovery and Data Mining (KDD) 2018 conference in London.
“We may never know for certain how many fires, fire deaths, and amount of property damage may be avoided with risk reduction policies informed by predictive risk modeling. But in 2016 alone, there were 475,500 structure fires in the United States, causing almost 3,000 civilian deaths and nearly $8 billion in property damage, according to the NFPA,” said Madaio.
“We hope that cities' adoption of this model to inform their risk reduction efforts can help fire departments reduce those numbers and improve public safety.”