Abstract
The immense problem of missing satellite aerosol retrievals (Aerosol Optical Depth, (AOD)) detrimentally affects the prediction ability of ground-level PM2.5 concentrations and may lead to unavoidable biases. An appropriate missing-imputation method has not been well developed to date. This study developed a two-stage approach (AOD-imputation stage and PM2.5-prediction stage) to predict short-term PM2.5 exposure in mainland China from 2013–2018. At the AOD-imputation stage, geostatistical methods and machine learning (ML) algorithms were examined to interpolate 1 km satellite aerosol retrievals. At the PM2.5-prediction stage, the daily levels of PM2.5 were predicted at a resolution of 1 km, based on interpolated AOD and meteorological data. The statistical performances of the different interpolation methods were comprehensively compared at each stage. The original coverage of retrieved AOD was 15.46% on average. For the AOD-imputation stage, ML methods produced a higher coverage (98.64%) of AOD than geostatistical methods (21.43–87.31%). Among ML algorithms, random forest (RF) or extreme gradient boosted (XG-interpolated) AOD produced better interpolated quality (CV R2 = 0.89 and 0.85) than other algorithms (0.49–0.78), but XGBoost required only 15% of the computing time of RF. For the PM2.5 predicted stage, neither RF-AOD nor XG-AOD could guarantee higher accuracy in PM2.5 estimations (CV R2 = 0.88 (RF or XG-AOD) compared to 0.85 (original)), or more stable spatial and temporal extrapolation (spatial, (temporal) CV R2 = 0.83 (0.83), 0.82 (0.82), and 0.65 (0.61) for RF, XG, and original). For the AOD-imputation stage, the missing-filled efficiency depended more on external information, while the missing-filled accuracy relied more on model structure. For the PM2.5 predicted stage, efficient AOD interpolation (or the ability to eliminate the missing data) was a precondition for the stable spatial and temporal extrapolation, while the quality of interpolated AOD showed less significant improvements. It was found that XG-AOD is a better choice to estimate daily PM2.5 exposure in health assessments.
Highlights
Since 1998, in China and India, industrialization, economic development, and a substantially increasing energy demand has led to over five times and triple growth in China’s and India’s coal-fired power, respectively [1]
From 2013 to 2018, the daily coverage of Multiangle Implementation of Atmospheric Correction (MAIAC) aerosol optical depth (AOD) in China generally remained at an average of approximately 15–16% (Figure 2)
From 2014 to 2018, the median PM2.5 concentrations reported by the monitoring sites gradually decreased from 45.60 μg/m3(IQR = 43.89) to 32.14 μg/m3 (IQR = 30.34)
Summary
Since 1998, in China and India, industrialization, economic development, and a substantially increasing energy demand has led to over five times and triple growth in China’s and India’s coal-fired power, respectively [1]. Many previous epidemiological studies around the world have linked short-term PM2.5 exposure to emergency hospital admissions and even deaths from acute or chronic illnesses such as asthma and stoke [3,4,5,6,7]. Despite such severe air pollution conditions and widely publicized concerns, there are sparse PM monitoring stations, and this is a significant hurdle for assessing pollution exposure. This is because of the high cost of building and maintaining monitoring sites
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call