Deep learning in airborne particulate matter sensing: a review

Abstract

Airborne particulate matter pollution is a global health problem that affects people from all demographics. To reduce the impact of such pollution and enable mitigation and policy planning, quantifying individuals’ exposure to pollution is necessary. To achieve this, effective monitoring of airborne particulates is required, through monitoring of pollution hotspots and sources. Furthermore, since pollution is a global problem, which varies from urban areas to city centres, industrial facilities to inside homes, a variety of sensors might be needed. Current sensing techniques either lack species resolution on a world scale, lack real-time capabilities, or are too expensive or too large for mass deployment. However, recent work using deep learning techniques has expanded the capability of current sensors and allowed the development of new techniques that have the potential for worldwide, species specific, real-time monitoring. Here, it is proposed how deep learning can enable sensor design for the development of small, low-cost sensors for real-time monitoring of particulate matter pollution, whilst unlocking the capability for predicting future particulate events and health inference from particulates, for both individuals and the environment in general.