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

High-resolution, comprehensive exposure data are crucial for accurately estimating the human health impact of PM. In recent years, satellite remote sensing data have been increasingly utilized in PM 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 and meteorological conditions can affect model performance and cause data gaps in most existing PM 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 at a 1 km spatial resolution in California. The model evaluation metrics (OOB (out-of-bag) R = 0.86 and RMSE (root-mean-square error) = 9.27 μg/m and 10-fold spatial cross-validation R = 0.82 and RMSE = 9.82 μg/m) demonstrate the model's reliability in predicting ambient PM, especially for states like California that experience frequent episodes of wildfires.