Improving air quality assessment using physics-inspired deep graph learning

Existing methods for fine-scale air quality assessment have significant gaps in their reliability. Purely data-driven methods lack any physically-based mechanisms to simulate the interactive process of air pollution, potentially leading to physically inconsistent or implausible results. Here, we report a hybrid multilevel graph neural network that encodes fluid physics to capture spatial and temporal dynamic characteristics of air pollutants. On a multi-air pollutant test in China, 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.

Lianfa Li, Jinfeng Wang, Meredith Franklin, Qian Yin, Jiajie Wu, Gustau Camps-Valls, Zhiping Zhu, Chengyi Wang, Yong Ge, Markus Reichstein