Publications

Han, M; Jia, SQ; Zhang, CK (2022). Estimation of high-resolution PM2.5 concentrations based on gap-filling aerosol optical depth using gradient boosting model. AIR QUALITY ATMOSPHERE AND HEALTH, 15(4), 619-631.

Abstract
Air pollution caused by fine particulate matter (PM2.5) may affect people's health. At present, aerosol optical depth (AOD) products have been used to estimate PM2.5 concentrations. However, AOD always has a low coverage rate. High-resolution products cannot provide a wide range of data. The purpose of this study was to deal with the missing data problem using the interpolation technique and to estimate high-resolution PM2.5 concentrations by fitting the spatial and temporal variations of AOD and PM2.5. Firstly, we developed a gradient boosting model (XGBoost) to fill in the missing values. Secondly, we corrected the altitude and humidity of meteorological variables. We then used the mixed-effects model with the gap-filling AOD data to estimate the PM2.5 concentrations in this study area. Finally, we obtained the complete PM2.5 concentrations picture. The AOD coverage rate reached 100% after model estimation. Meanwhile, the estimation results of PM2.5 concentrations were also validated and the model worked well. The results indicate that it is necessary to fill in the missing values of AOD data for PM2.5 estimations. This study can provide complete AOD data, which makes the results of PM2.5 estimations more accurate and has some research value.

DOI:
10.1007/s11869-021-01149-w

ISSN:
1873-9326