Using machine learning to understand the temporal morphology of the PM_2.5 annual cycle in East Asia

PM_2.5 air pollution is a significant issue for human health all over the world, especially in East Asia. A large number of ground-based measurement sites have been established over the last decade to monitor real-time PM_2.5 concentration. However, even this enhanced observational network leaves many gaps in characterizing the PM_2.5 spatial distribution. Machine learning provides a variety of algorithms to help deal with these large spatial gaps-combining both remotely sensed and in situ observation data to estimate the global PM_2.5 concentration. This study used a PM_2.5 data product of six regions from the results of an unsupervised self-organizing map (SOM) with optimized ensemble learning approaches to highlight the most important meteorological and surface variables associated with PM_2.5 concentration. These variables were then examined via multiple linear regression models to provide physical mechanistic insights into the morphology of the PM_2.5 annual cycles.