Adaptive Hybrid Model-Enabled Sensing System (HMSS) for Mobile Fine-Grained Air Pollution Estimation

Abstract

Fine-grained city-scale outdoor air pollution maps provide important environmental information for both city managers and residents. Installing portable sensors on vehicles (e.g., taxis, Ubers) provides a low-cost, easy-maintenance, and high-coverage approach to collecting data for air pollution estimation. However, as non-dedicated platforms, vehicles like taxis usually prefer gathering at busy areas of a city where it is more likely to pick up riders. This leaves many parts of the city unsensed or less-sensed. In addition, due to the natural changes in a city and the movements of the vehicles, the sensed and unsensed areas change over time. Consequently, challenges of air pollution estimation with data collected by non-dedicated mobile platforms are twofold: <i>i.</i> data coverage is sparse; <i>ii.</i> data coverage changes over time. Therefore, the major research question is: how can we derive accurate and robust fine-grained field (e.g., air pollution) estimation given dynamic and sparse data collected from uncontrollable mobile sensing platforms? This paper presents adaptive <i>HMSS</i> , an adaptive <u>h</u> ybrid <u>m</u> odel-enabled <u>s</u> ensing <u>s</u> ystem for fine-grained air pollution estimation with dynamic and sparse data collected from uncontrollable mobile sensing platforms, which is achieved by combining the advantages of a <i>physics guided model</i> and a <i>data driven model</i> . To address the challenge of sparse coverage, the physical understanding of the spatiotemporal correlation for air pollution distribution in the <i>physics guided model</i> is utilized to infer values at unsensed sparse areas. Meanwhile, the <i>data driven model</i> is adopted to estimate the air pollution influential factors (e.g., buildings) not included in the <i>physics guided model</i> . To address the challenge of time-varying coverage, an adaptive model combination algorithm is designed to enable the system bias to either of the two models according to the amount of data collection and uncertainty of the model. To evaluate the system performance, we deployed 47 air pollution sensing devices on taxis and fixed locations in 2 cities for both controlled and uncontrolled experiments for over two weeks. The results show that with a resolution of <inline-formula><tex-math notation="LaTeX">$500 \;\mathrm m$</tex-math></inline-formula> by <inline-formula><tex-math notation="LaTeX">$500\;\mathrm m$</tex-math></inline-formula> by <inline-formula><tex-math notation="LaTeX">$1\;\mathrm {hour}$</tex-math></inline-formula> , our system achieves up to <inline-formula><tex-math notation="LaTeX">$3.2\times$</tex-math></inline-formula> error reduction when compared to the baseline approaches.