Back to Search Start Over

Capturing synoptic-scale variations in surface aerosol pollution using deep learning with meteorological data.

Authors :
Feng, Jin
Li, Yanjie
Qiu, Yulu
Zhu, Fuxin
Source :
Atmospheric Chemistry & Physics; 2023, Vol. 23 Issue 1, p375-388, 14p
Publication Year :
2023

Abstract

The estimation of daily variations in aerosol concentrations using meteorological data is meaningful and challenging, given the need for accurate air quality forecasts and assessments. In this study, a 3×50 -layer spatiotemporal deep learning (DL) model is proposed to link synoptic variations in aerosol concentrations and meteorology, thereby building a "deep" Weather Index for Aerosols (deepWIA). The model was trained and validated using 7 years of data and tested in January–April 2022. The index successfully reproduced the variation in daily PM 2.5 observations in China. The coefficient of determination between PM 2.5 concentrations calculated from the index and observation was 0.72, with a root mean square error (RMSE) of 16.5 µ g m -3. The DeepWIA performed better than Weather Forecast and Research (WRF)-Chem simulations for eight aerosol-polluted cities in China. The simulating power of the model also outperformed commonly used PM 2.5 concentration retrieval models based on random forest (RF), extreme gradient boost (XGB), and multilayer perceptron (MLP). The index and the DL model can be used as robust tools for estimating daily variations in aerosol concentrations. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
16807316
Volume :
23
Issue :
1
Database :
Complementary Index
Journal :
Atmospheric Chemistry & Physics
Publication Type :
Academic Journal
Accession number :
161359295
Full Text :
https://doi.org/10.5194/acp-23-375-2023