| Summary: | Satellite-based models for estimating concentrations of particulate matter with an aerodynamic diameter less than 2.5 μm (PM<sub>2.5</sub>) have seldom been developed in islands with complex topography over the monsoon area, where the transport of PM<sub>2.5</sub> is influenced by both the synoptic-scale winds and local-scale circulations compared with the continental regions. We validated Multi-Angle Implementation of Atmospheric Correction (MAIAC) aerosol optical depth (AOD) with ground observations in Japan and developed a 1-km-resolution national-scale model between 2011 and 2016 to estimate daily PM<sub>2.5</sub> concentrations. A two-stage random forest model integrating MAIAC AOD with meteorological variables and land use data was applied to develop the model. The first-stage random forest model was used to impute the missing AOD values. The second-stage random forest model was then utilised to estimate ground PM<sub>2.5</sub> concentrations. Ten-fold cross-validation was performed to evaluate the model performance. There was good consistency between MAIAC AOD and ground truth in Japan (correlation coefficient = 0.82 and 74.62% of data falling within the expected error). For model training, the model showed a training coefficient of determination (<i>R</i><sup>2</sup>) of 0.98 and a root mean square error (RMSE) of 1.22 μg/m<sup>3</sup>. For the 10-fold cross-validation, the cross-validation <i>R</i><sup>2</sup> and RMSE of the model were 0.86 and 3.02 μg/m<sup>3</sup>, respectively. A subsite validation was used to validate the model at the grids overlapping with the AERONET sites, and the model performance was excellent at these sites with a validation <i>R</i><sup>2</sup> (RMSE) of 0.94 (1.78 μg/m<sup>3</sup>). Additionally, the model performance increased as increased AOD coverage. The top-ten important predictors for estimating ground PM<sub>2.5</sub> concentrations were day of the year, temperature, AOD, relative humidity, 10-m-height zonal wind, 10-m-height meridional wind, boundary layer height, precipitation, surface pressure, and population density. MAIAC AOD showed high retrieval accuracy in Japan. The performance of the satellite-based model was excellent, which showed that PM<sub>2.5</sub> estimates derived from the model were reliable and accurate. These estimates can be used to assess both the short-term and long-term effects of PM<sub>2.5</sub> on health outcomes in epidemiological studies.
|
|---|