Search

Several studies have attempted to predict ground PM2.5 concentrations using satellite aerosol optical depth (AOD) retrieval. However, over 70%–90% of aerosol retrievals are non-random missing, which limits and biases the estimation. To the best of our knowledge, this issue has not been well resolved to date. The aim of this study was to develop an interpolation technique to handle the missing data retrieval problem and to estimate the daily PM2.5 for a high coverage dataset with 3-km resolution in China by fitting the complex temporal and spatial variations. We developed a two-step interpolation method (i.e., the mixed-effect model and inverse distance weighting technology) to replace the missing values in AOD. Next, the extreme gradient boosting (XGBoost) technique that includes a non-linear exposure-lag-response model (NELRM) was proposed and validated to estimate the daily levels of PM2.5 across China during 2014–2015. After two steps of interpolation, the missing value rate of daily AOD data was reduced from 87.91% to 13.83%. The cross-validation (CV) R-square, root mean square error (RMSE) and mean absolute percentage prediction error (MAPE) of the interpolation were 0.76, 0.10 and 21.41%, respectively. The cross-validation for the prediction of daily PM2.5 resulted in R2 = 0.86, RMSE = 14.98, and MAPE = 23.72%. The results of this study indicate that the two-step interpolation method can largely resolve the non-random missing data problem and that the combined XGBoost methods have a good ability to estimate fine particulate matter concentrations.

Background The accurate measurement of particulate matter (PM) provides a crucial basis for health impact assessment and pollution management and control. However, monitoring stations of air pollution are limited worldwide. Recently, some researchers have attempted to estimate the levels of PM based on remote sensing data, but the methods still need to be validated and further improved. Objectives This study aimed to develop a new model, to estimate daily ground-level PM2.5 concentrations using the fused aerosol optical depth (AOD) retrieved by the Moderate Resolution Imaging Spectro radiometer and meteorological information. Methods We combined generalized additive mixed-effects model with the log-linked Gaussian error distribution and non-linear exposure-lag-response model for AOD and meteorological measures, to estimate daily ground-level PM2.5 concentrations in 2014–2015 in Guangzhou, China. Results The PM2.5 concentration was significantly associated with AOD and meteorological measures. Compared to the log-linear model, the non-linear exposure-lag-response model had better model performance with a higher temporal (spatial) cross-validation R–square (0.81 (0.81) vs 0.67 (0.67)), and a smaller mean absolute percentage error (17.65% (16.90%) vs 21.22% (21.01%)). AOD explained about 15% variations of PM2.5 in the mixed-effect model. The planetary-boundary -layer-height-revised AOD and relative-humidity-revised PM2.5 did not significantly improve the model performance. Conclusion Considering the non-linear exposure-lag-response association between PM2.5 and AOD and meteorological factors can significantly increase the modelling ability to estimate PM2.5 concentrations.