Dense Air Quality Sensor Networks: Validation, Analysis, and Benefits

Abstract

Air pollution is known to be harmful to human health and the environment. Official air quality monitoring stations have been established across many smart cities around the world. Unfortunately, these monitoring stations are sparsely located and consequently do not provide high-resolution spatio-temporal air quality information. This article demonstrates how a dense sensor network deployment offers significant advantages in providing better and more detailed air quality information. We use data from a dense sensor network consisting of 126 low-cost sensors (LCSs) deployed in a highly populated district in Nanjing, China. Using data obtained from 13 existing reference stations installed in the same district, we propose three LCS validation methods to evaluate the performance of LCSs in the network. The methods assess the reliability, accuracy of tests, and failure and anomaly detection performance. We also demonstrate how the reliable data generated from the sensor network provides deep insights into air pollution information at a higher spatio-temporal resolution. We further discuss potential improvements and applications derived from the dense deployment of LCSs in cities.