Improving Air Quality Assessment Using Physics-inspired Deep Graph Learning

Air pollution has major adverse effects on health and climate, leading to more than 8 million deaths in 2018. To accurately evaluate its effects and inform effective control strategies, reliable and finely-resolved air pollution estimates are needed. Here, we report a hybrid multilevel graph neural network that encodes fluid physics to capture spatial and temporal dynamic characteristics of air pollutants. Our method consistently improved extrapolation accuracy by an average of 11-22% compared to several baseline machine learning methods, and generated physically consistent spatiotemporal trends of air pollutants at fine spatial and temporal scales.