BlueAer: A fine-grained urban PM2.5 3D monitoring system using mobile sensing

This paper presents BlueAer, the first three-dimensional (3D) spatial-temporal fine particulate matter (PM_2.5) monitoring system, which is designed to understand urban PM_2.5 concentration distribution in a fine-grained level. For cost-efficient data collection, vast amount of 3D samples are collected by limited mobile carriers with built-in low-cost sensors. A 3D probabilistic concentration estimated method (3D-PCEM) is proposed to infer PM_2.5 concentration for undetected area, so that the accuracy of BlueAer is ensured. A prototype system of BlueAer has been implemented and worked throughout a year in a 64km² testing area with a population of 400,000 in Hangzhou, China. Experimental data has verified that BlueAer can achieve good performance in terms of stability as well as a fine grained 3D distribution of PM_2.5 concentration. The inference accuracy of 3D-PCEM is enhanced by 15.4% and 41.0%, comparing to Gaussian Process (GP) and Artificial Network (ANN) respectively. BlueAer can easily be extended for a larger scale and applied city-wise. Besides, our findings can help ordinary citizens better understand their immediate air quality and serve as a framework towards detailed national-wise real-time pollution management.