Estimating hourly PM2.5 concentrations in Beijing with satellite aerosol optical depth and a random forest approach

Assessing short-term exposure to PM2.5 requires the concentration distribution at a high spatiotemporal resolution. Abundant researches have derived the daily predictions of fine particles, but estimating hourly PM2.5 is still a challenge restrained by the input data. The recent aerosol optical depth (AOD) product from Himawari-8 provides hourly satellite observations informative to modelling. In this study, we developed separate random forest models with and without AOD and combined the estimates to obtain a full-coverage hourly PM2.5 distribution. 10-fold cross validation R-2 ranged from 0.92 to 0.95 and root mean square errors from 14.1 to 16.9 mu g/m(3), indicating the good model performance. Spatial convolutional layers of PM2.5 measurements and temporal accumulation effects of meteorological features were added into the model. They turned out to be of the most important predictors and improved the performance significantly. Finally, we mapped hourly PM2.5 at a 1-km resolution in Beijing during a pollution episode in 2019 and studied the pollution pattern. The study proposed a method to obtain 24-h full-coverage hourly PM2.5 estimates which are useful for acute exposure assessment in epidemiological researches. (C) 2020 Elsevier B.V. All rights reserved.

Automated summary

The study developed random forest models with and without AOD to obtain hourly PM2.5 distribution, achieving good model performance with 10-fold cross validation R-2 ranging from 0.92 to 0.95. Spatial convolutional layers and temporal accumulation effects were found to be important predictors that significantly improved the model performance.