GASP: Geolocated Allergen Sensing Platform
Source of Support: NSF CNS Division Of Computer and Network Systems
Award Amount: $149,984
Period Covered: 05/01/2015 to 04/30/2017
A wide range of health outcomes is affected by air pollution. In March 2014 the World Health Organization (WHO) released a report that in 2012 alone, a staggering 7 million people died as a result of air pollution exposure, one in eight of total global deaths. A major component of this pollution is airborne particulate matter, with approximately 50 million Americans have allergic diseases.
This project will develop and field the first integrated IoT in-situ sensor package tracking pollution and pollen to provide airborne particulate mapping for Chattanooga. Longer term it is hoped that the data collection approach and initial visualization tools developed in Chattanooga can be used to support a nationwide, open access dissemination platform on the order of Google’s StreetView, but called PollutionView. Such scaling of the project’s pilot results through a PollutionView tool will contribute significantly to a transformation of the Environmental Public Health field in the United States. The project involves real-time big data analysis at a fine-grain geographic level. This will involve trades with sensing and computing especially if the sensor package is to be deployed at scale. The project will help determine if real-time allergen collection and visualization can improve health and wellness. Thus, this project will combine Cyber Physical Systems (CPS) and gigabit networks to address major health concerns due to air pollution. A working demonstration of this project will be presented during the Global City Teams meeting in June 2015 with an update in June 2016.
Airborne particulate matter particularly affects the citizens of Chattanooga, TN. The objectives of this project are twofold: first, to develop and deploy an array of Internet of Things (IoT) in-situ sensors within Chattanooga capable of comprehensively characterizing air quality in real time, including location, temperature, pressure, humidity, the abundance of 6 criterion pollutants (O3, CO, NO, NO2, SO2, and H2S), and the abundance of airborne particulates (10-40 µm), both pollen-sized and smaller PM2.5 (<2.5 µm) particles; and second, to have a pollen validation campaign by deploying an in-situ pollen air sampler in Chattanooga to identify specific pollen types.
Lary, D.J., Lary, T., Sattler, B. (2015), Using Machine Learning to Estimate Global PM2.5 for Environmental Health Studies, Environmental Health Insights, Suppl. 1 41-52