Developing a robust and scalable calibration approach to low-cost AQ sensing

Poor air quality represents a major public health risk, contributing to an estimated one of every eight deaths worldwide. Low-cost air quality sensors have developed rapidly over the last few years and offer the opportunity to make air quality monitoring widespread at an affordable price. However, low-cost sensors are currently unable to deliver accurate, reliable data due to a lack of understanding of what parameters impact performance and a lack of adequate calibration methods. This project is developing a robust, scalable calibration technique, involving a laboratory calibration chamber for rapid exposure of sensors to the full range of atmospheric and pollutant conditions and a sophisticated, adaptive machine learning algorithm. The end result of the Phase II project will be a calibration method that enables rapid calibration of tens of low-cost sensors at a time, and sufficient information about the longer-term behavior of the sensors to scale the calibration method to hundreds of sensors for use in large, distributed networks. In addition, a new database architecture will ingest, analyze and display the air quality data for a variety of end users, including atmospheric scientists, public health researchers and government agencies.