Abstract
Fine particulate matter (PM2.5) has a considerable impact on the environment, climate change, and human health. Herein, we introduce a deep neural network model for deriving ground-level, hourly PM2.5 concentrations by Himawari-8 aerosol optical depth, meteorological variables, and land cover information. A total of 151,726 records were collected from 313 ground-level PM2.5 monitoring stations (spread across the North China Plain) to calibrate and test the proposed model. The sample- and site-based cross-validation yielded satisfactory performance, with correlation coefficients > 0.8 (R = 0.86 and 0.83, respectively). Furthermore, the variation in mean ground-level hourly PM2.5 concentrations, using 2017 data, showed that the proposed method could be applied for spatiotemporal continuous PM2.5 monitoring. This study will serve as a reference for the application of geostationary meteorological satellite to perform ground-level PM2.5 estimation and the utilization in atmospheric monitoring.
Highlights
Fine particulate matter (PM2.5), which consists of particles with aerodynamic diameters \ 2.5 lm, has attracted considerable scientific attention (Pope & Dockery, 2006)
A total of 151,726 records were collected from 313 ground-level PM2.5 monitoring stations to calibrate and test the proposed model
The variation in mean ground-level hourly PM2.5 concentrations, using 2017 data, showed that the proposed method could be applied for spatiotemporal continuous PM2.5 monitoring
Summary
Fine particulate matter (PM2.5), which consists of particles with aerodynamic diameters \ 2.5 lm, has attracted considerable scientific attention (Pope & Dockery, 2006). Several studies were conducted for estimating PM2.5 concentrations from the aerosol optical depth (AOD), derived by satellite remote sensing, including multiple linear regression (Chu et al, 2016; Gupta & Christopher, 2008, 2009; Kacenelenbogen et al, 2006; Liu et al, 2005; Paciorek et al, 2008; Schaap et al, 2009; Wang, 2003; Yao et al 2018), mixed-effect models (Just et al 2015; Kloog et al 2011, 2012, 2014; Lee et al 2012; Zheng et al 2016), geographically weighted regressions (Bai et al, 2016; Guo et al, 2017; He & Huang, 2018a, b; Hu, 2009; Ma et al, 2014; You et al, 2015; Zou et al, 2016), and chemical transport models (Crouse et al., Journal of the Indian Society of Remote Sensing (August 2021) 49(8):1839–1852. Random forests (Chen et al, 2018; Hu et al, 2017), deep belief networks (DBNs) (Li et al, 2018; Liu et al, 2018), deep neural networks (DNNs) (Wang & Sun, 2019), and machine learning models with high-dimensional expansion (Xue et al, 2019) have been used, and they have delivered superior prediction accuracy and applicability
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
