Comparison of Satellite-based PM2.5 Estimation from Aerosol Optical Depth and Top-of-atmosphere Reflectance

Abstract

Aerosol optical depth (AOD) and top-of-atmosphere (TOA) reflectance are two useful sources of satellite data for estimating surface PM2.5 concentrations. Comparison of PM2.5 estimates between these two approaches remains to be explored. In this study, satellite observations of TOA reflectance and AOD from the Advanced Himawari Imager (AHI) onboard the Himawari-8 geostationary satellite in 2016 over Yangtze River Delta (YRD) and meteorological data are used to estimate hourly PM2.5 based on four different machine learning algorithms (i.e., random forest, extreme gradient boosting, gradient boosting regression, and support vector regression). For both reflectance-based and AOD-based approaches, our cross validated results show that random forest algorithm achieves the best performance, with a coefficient of determination (R 2) of 0.75 and root-mean-square error (RMSE) of 18.71 μg m-3 for the former and R 2 = 0.65 and RMSE = 15.69 μg m-3 for the later. Additionally, we find a large discrepancy in PM2.5 estimates between reflectance-based and AOD-based approaches in terms of annual mean and their spatial distribution, which is mainly due to the sampling difference, especially over northern YRD in winter. Overall, reflectance-based approach can provide robust PM2.5 estimates for both annual mean values and probability density function of hourly PM2.5. Our results further show that almost all population lives in non-attainment areas in YRD using annual mean PM2.5 from reflectance-based approach. This study suggests that reflectance-based approach is a valuable way for providing robust PM2.5 estimates and further for constraining health impact assessments.

Influence of Spatial Resolution on Satellite-Based PM2.5 Estimation: Implications for Health Assessment

“…Input predictors for the RF model are the same as the LUR model. We carried out a grid search approach to find the optimized hyperparameters [15]. For the RF model at 1, 3, 5 and 10 km resolution, the optimized values of max_features (n_estimators) are 9 (900), 10 (800), 13 (700) and 11 (300), respectively.…”

“…Zhang et al [14] created monthly PM 2.5 estimates in China by using a land-use regression model and MODIS AOD product. Numerous studies have also used satellite AOD data to retrieve PM 2.5 concentrations at a regional scale, such as the Yangtze River Delta (YRD) [15][16][17][18][19][20].…”

Estimation of Atmospheric PM10 Concentration in China Using an Interpretable Deep Learning Model and Top‐of‐the‐Atmosphere Reflectance Data From China’s New Generation Geostationary Meteorological Satellite, FY‐4A

“…The coverage of satellite top‐of‐the‐atmosphere reflectance (TOAR) was higher than that of AOD, so TOAR was used to directly obtain the particle concentration (L. Yang et al., 2020). Using the TOAR of Himawari‐8 and the random forest model, the PM 2.5 , of the Yangtze River Delta (YRD) in 2016 was obtained, and the 10‐fold cross validation ( R 2 ) was 0.75 (Bai et al., 2021). Using the TOAR of the Himawari‐8 and LightGBM models, the R 2 of the PM 2.5 model was 0.86 (Yin et al., 2021).…”

Spatiotemporal Distribution Characteristics and Driving Forces of PM2.5 in Three Urban Agglomerations of the Yangtze River Economic Belt

“…At present, studies on PM2.5 mainly rely on data acquisition and assessment of the spatiotemporal distribution characteristics and driving factors. Data sources are mainly derived from environmental monitoring sites [ 12 ] and aerosol optical depth (AOD) production from remote sensing [ 13 , 14 , 15 , 16 , 17 ]. However, different data collection methods have also led to obvious discrepancies between the two data sets.…”