| Autor: |
Sun, Jin1,2 (AUTHOR), Gong, Jianhua1,2,3 (AUTHOR), Zhou, Jieping1 (AUTHOR) zhoujp@aircas.ac.cn |
| Zdroj: |
Science of the Total Environment. Mar2021, Vol. 762, pN.PAG-N.PAG. 1p. 3 Charts. |
| Abstrakt: |
Assessing short-term exposure to PM 2.5 requires the concentration distribution at a high spatiotemporal resolution. Abundant researches have derived the daily predictions of fine particles, but estimating hourly PM 2.5 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 PM 2.5 distribution. 10-fold cross validation R2 ranged from 0.92 to 0.95 and root mean square errors from 14.1 to 16.9 μg/m3, indicating the good model performance. Spatial convolutional layers of PM 2.5 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 PM 2.5 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 PM 2.5 estimates which are useful for acute exposure assessment in epidemiological researches. Unlabelled Image • Separate random forest models were built with and without AOD to obtain full-coverage hourly PM 2.5 estimates. • The use of spatial autocorrelation and temporal accumulation improved the models significantly. • Himawari-8 AOD worked on the spatial trends explanation and was important to estimates in remote regions. [ABSTRACT FROM AUTHOR] |
| Databáze: |
GreenFILE |
| Externí odkaz: |
|
Full Text from ScienceDirect