City of Pittsburgh Tests Predictive Analytics for Air Quality Incident Preparation


The city partnered with the University of Pittsburgh and Intermedix to host a workshop as a part of the ONEPGH initiative.

The city of Pittsburgh has teamed up with the University of Pittsburgh Graduate School of Public Health and Intermedix to host an emergency preparedness workshop, part of the ONEPGH initiative. The one-day program examined how emergency response technology and predictive analytics could work together to prepare the city for a major heatwave and air quality incident like the 1948 Donora smog that killed 20 and sickened over 7,000.

“Through public engagements as part of ONEPGH, we recognize that air quality is one of the primary stressors facing the region,” said Grant Ervin, chief resilience officer for the City of Pittsburgh. “In talking with emergency response professionals, some of their concerns center around the question of what happens when normal events occur simultaneously to create cascading effects that put strains on systems. What we aim to do is model a historical event, like the Donora smog, and place it in a modern context.”

The university’s predictive model, dubbed FRED, was used in the workshop. It was originally designed to predict infectious disease epidemics and the effects of mitigation strategies and personal health behavior, and has now been expanded to include social and environmental factors that affect health.

“In this scenario, we are using FRED to estimate the clinical impact of heat and smog on different demographics within our population,” said Mark Roberts, chair of the Department of Health Policy at Pitt Public Health. “FRED allows us to pinpoint critical conditions and the effect of potential interventions to better educate response efforts. For example, we can use the model to predict how many instances of acute respiratory disease warranting a 911 call would occur in the context of this environmental event.”

Optima Predict, a predictive response planning and simulation solution created by Intermedix, can then be used to determine appropriate resource allocation and emergency response deployments using the data collected by FRED.  Communication and coordination challenges between first responders, emergency management and critical organizations such as hospitals and utilities were also examined during the event. More than 50 public health, air quality and emergency management professionals in Western Pennsylvania attended.

“Using technology and professional experience together is a great way for us to model how systems interact, and we can also use different scenarios and circumstances to replicate the process in the future,” said Rebecca Kiernan, Senior Resilience Coordinator for the City of Pittsburgh.


Data in disasters: Using real-time analytics to save lives

Sue Walsh

About Sue Walsh

Sue Walsh is News Writer for RTInsights, and a freelance writer and social media manager living in New York City. Her specialties include tech, security and e-commerce. You can follow her on Twitter at @girlfridaygeek.

Leave a Reply

Your email address will not be published. Required fields are marked *