Hourly and Daily PM2.5 Estimations Using MERRA‐2: A Machine Learning Approach.

Health and environmental hazards related to high pollution concentrations have become a serious issue from public policy perspectives and human health. Using Machine Learning (ML) approach, this research aims to improve the estimation of grid‐wise PM2.5, a criteria pollutant, by reducing systematic bias from speciation provided by MERRA‐from the Modern‐Era Retrospective analysis for Research and Applications version 2 (MERRA‐2). The ML model was trained using various meteorological parameters and aerosol species simulated by MERRA‐2 and ground measurements from Environmental Protection Agency (EPA) air quality system stations. The ML approach significantly improved performance and reduced mean bias in the 0–10 μg m−3 range. We also used the Random Forest ML model for each EPA region using 1 year of collocated data sets. The resulting ML models for each EPA region were validated, and the aggregate data set has a Spearman Rank correlation (SR) of 0.73 (RMSE = 4.8 μg m−3) and 0.69 (RMSE = 5.8 μg m−3) for training and testing, respectively. The SR (and RMSE in μg m−3) increased to 0.81 (3.9), 0.89 (1.6), and 0.90 (1.1) for daily, monthly, and yearly averages, respectively. The results from the initial implementation of the ML model for the global region are encouraging. Still, they require more research and development to overcome challenges associated with data gaps in many parts of the world. Plain Language Summary: PM2.5 is one of the most critical pollutants monitored globally since it is a serious health and environmental hazard. Monitoring of PM2.5 helps understand the air quality and provides advisory to the public. This advisory becomes more critical in the scenarios of natural or anthropogenic events where there is a sudden increase in its concentration. Although a ground‐based monitor can detect a high pollution episode, its spatial extent is limited. Numerical model outputs like Modern‐Era Retrospective analysis for Research and Applications version 2 (MERRA‐2) reasonably estimate various meteorology and aerosol fields to understand the spatial distribution. However, coarse resolution and averaging large grid boxes result in certain uncertainties, leading to biases. In this study, we implemented a machine learning model to better estimate PM2.5 at the grid level using MERRA‐2 as a base model. The developed machine learning model estimated the PM2.5 with good accuracy and low biases. Key Points: Machine learning (ML) model to estimate grid‐wise PM2.5 from Modern‐Era Retrospective analysis for Research and Applications version 2 meteorology and aerosols was developedML model was successful in estimating PM2.5 when compared with surface measurementsRegional ML models performed better than the overall ML model [ABSTRACT FROM AUTHOR]