Abstract
Accurate estimation of fine particulate matter with diameter ≤2.5 μm (PM2.5) at a high spatiotemporal resolution is crucial for the evaluation of its health effects. Previous studies face multiple challenges including limited ground measurements and availability of spatiotemporal covariates. Although the multiangle implementation of atmospheric correction (MAIAC) retrieves satellite aerosol optical depth (AOD) at a high spatiotemporal resolution, massive non-random missingness considerably limits its application in PM2.5 estimation. Here, a deep learning approach, i.e., bootstrap aggregating (bagging) of autoencoder-based residual deep networks, was developed to make robust imputation of MAIAC AOD and further estimate PM2.5 at a high spatial (1 km) and temporal (daily) resolution. The base model consisted of autoencoder-based residual networks where residual connections were introduced to improve learning performance. Bagging of residual networks was used to generate ensemble predictions for better accuracy and uncertainty estimates. As a case study, the proposed approach was applied to impute daily satellite AOD and subsequently estimate daily PM2.5 in the Jing-Jin-Ji metropolitan region of China in 2015. The presented approach achieved competitive performance in AOD imputation (mean test R2: 0.96; mean test RMSE: 0.06) and PM2.5 estimation (test R2: 0.90; test RMSE: 22.3 μg/m3). In the additional independent tests using ground AERONET AOD and PM2.5 measurements at the monitoring station of the U.S. Embassy in Beijing, this approach achieved high R2 (0.82–0.97). Compared with the state-of-the-art machine learning method, XGBoost, the proposed approach generated more reasonable spatial variation for predicted PM2.5 surfaces. Publically available covariates used included meteorology, MERRA2 PBLH and AOD, coordinates, and elevation. Other covariates such as cloud fractions or land-use were not used due to unavailability. The results of validation and independent testing demonstrate the usefulness of the proposed approach in exposure assessment of PM2.5 using satellite AOD having massive missing values.
Highlights
Fine particulate matter with a diameter < 2.5 μm (PM2.5) has been associated with adverse health effects, ranging from acute, short-term to chronic health outcomes [1,2,3], including increased respiratory symptoms [4,5,6], worsened asthma [7,8], increased cardiovascular diseases [9,10], decreased lung function [11], and increased premature death from heart or lung diseases [12,13]
This paper presents a novel approach, i.e., bagging of residual networks for robust imputation of multiangle implementation of atmospheric correction (MAIAC) aerosol optical depth (AOD) and estimation of PM2.5 at a high spatiotemporal resolution
For the challenges of massive missing satellite AOD, limited data of PM2.5 and publicly available covariates, and local variation of concentration probably caused by more traffic emissions than previously, compared with other existing methods, this proposed approach achieved PM2.5 prediction with complete spatial coverage, a high spatiotemporal resolution, and cutting-edge performance
Summary
Fine particulate matter with a diameter < 2.5 μm (PM2.5) has been associated with adverse health effects, ranging from acute, short-term to chronic health outcomes [1,2,3], including increased respiratory symptoms [4,5,6], worsened asthma [7,8], increased cardiovascular diseases [9,10], decreased lung function [11], and increased premature death from heart or lung diseases [12,13]. PM2.5 ground monitoring stations are usually limitedly distributed worldwide, e.g., there were 102 PM2.5 monitoring stations in 2015 for the large Jing-Jin-Ji metropolitan area of China (64,022 km). PM2.5 ground monitoring stations are usually limitedly distributed worldwide, e.g., there were 102 PM2.5 monitoring stations in 2015 for the large Jing-Jin-Ji metropolitan area of China (64,022 km2) These limited measurements create a challenge in spatiotemporal PM2.5 estimation at a high resolution using traditional modeling methods such as nearest neighbor [24,25], land-use regression [26,27], generalized additive model (GAM) and kriging [28]
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
