Research Team: PI: Aydogan Ozcan Team:
About this project:
UCLA will develop a field-portable computational imaging and deep-learning enhanced aerosol analysis device, termed c-Air, to characterize PM due to transportation systems. In additional to particle counting and sizing, UCLA will further enhance its system above the current gold standard by classifying particles based upon physical features and volatility using computational imaging and deep learning. The research team will deploy several sensor prototypes to simultaneously assess air quality through detection of PM and volatile and evaporating particles in strategic locations (i.e. bus-only lane projects, and high and low congestion traffic routes).
What problem does this research aim to address?
Evaluation of particulate matter (PM) due to transportation systems is of interest to public health professionals and policymakers in California and Southern California, specifically. Poor air quality can lead to short-term eye, throat, and nose irritations, as well as long-term cancers. While PM can be reduced through new regulations including bus-only lane projects, carpooling, and the adoption of clean air vehicles, there is a need for highly accurate, yet cost-effective sensors which can assess the efficacy of these improvements.
What are the expected impacts and benefits of the research?
Monitoring PM air quality as a function of space and time is critical for understanding the effects of industrial activities, studying atmospheric models, and providing regulatory and advisory guidelines for transportation, residents, and industries. Through this proposal UCLA will develop a superior tool for CARB to gather data, assess air quality improvement initiatives, and track long term outcomes.