Using a gradient boosting model to improve the performance of low-cost aerosol monitors in a dense, heterogeneous urban environment

Abstract

The increased availability and improved quality of new sensing technologies have catalyzed a growing body of research to evaluate and leverage these tools in order to quantify and describe urban environments. Air quality, in particular, has received greater attention because of the well-established links to serious respiratory illnesses and the unprecedented levels of air pollution in developed and developing countries and cities around the world. Though numerous laboratory and field evaluation studies have begun to explore the use and potential of low-cost air quality monitoring devices, the performance and stability of these tools has not been adequately evaluated in complex urban environments, and further research is needed. In this study, we present the design of a low-cost air quality monitoring platform based on the Shinyei PPD42 aerosol monitor and examine the suitability of the sensor for deployment in a dense heterogeneous urban environment. We assess the sensor's performance during a field calibration campaign from February 7th to March 25th 2017 with a reference instrument in New York City, and present a novel calibration approach using a machine learning method that incorporates publicly available meteorological data in order to improve overall sensor performance. We find that while the PPD42 performs well in relation to the reference instrument using linear regression (R2 = 0.36–0.51), a gradient boosting regression tree model can significantly improve device calibration (R2 = 0.68–0.76). We discuss the sensor's performance and reliability when deployed in a dense, heterogeneous urban environment during a period of significant variation in weather conditions, and important considerations when using machine learning techniques to improve the performance of low-cost air quality monitors.