Multiresolution Analysis of HRRR Meteorological Parameters and GOES-R AOD for Hourly PM2.5 Prediction

Abstract

High-resolution, comprehensive exposure data are crucial for accurately estimating the human health impact of PM_2.5. In recent years, satellite remote sensing data have been increasingly utilized in PM_2.5 models to overcome the limited spatial coverage of ground monitoring stations. However, data gaps in satellite-retrieved parameters such as aerosol optical depth (AOD), the sparsity of regulatory air quality monitors for model training, and nonlinear relationships between PM_2.5 and meteorological conditions can affect model performance and cause data gaps in most existing PM_2.5 models. In this study, spatial gaps in AOD obtained from Geostationary Operational Environmental Satellite-16 are filled using Goddard Earth Observing System Composition Forecasting AOD estimations. Furthermore, to improve model performance, meteorological predictors such as temperature from the High-Resolution Rapid Refresh model are preprocessed using Daubechies wavelet to extract low and high frequency components. The spatially gap-filled AOD, along with meteorological data, are ingested into a machine learning model to predict hourly PM_2.5 at a 1 km spatial resolution in California. The model evaluation metrics (OOB (out-of-bag) R² = 0.86 and RMSE (root-mean-square error) = 9.27 μg/m³ and 10-fold spatial cross-validation R² = 0.82 and RMSE = 9.82 μg/m³) demonstrate the model’s reliability in predicting ambient PM_2.5, especially for states like California that experience frequent episodes of wildfires.

By incorporating the spatially filled GOES-AOD high resolution product and using wavelet transforms, the hourly seamless PM_2.5 concentrations across California are well estimated at 1 km.