Estimation of Hourly Ground-Level PM₂.₅ Concentration Based on Himawari-8 Apparent Reflectance

Satellite aerosol optical depth (AOD) is a quantitative parameter frequently used to estimate ground-level fine particulate matters (PM
_2.5
)at regional to global scales. In this article, Himawari-8 apparent reflectance (top-of-atmosphere reflectance) data were used to estimate the hourly ground-level PM
_2.5
concentrations (Ref-PM
_2.5
) using deep neural networks (DNNs), and comparison was conducted with the AOD-based PM
_2.5
estimation method (AOD-PM
_2.5
). In high-density site areas, the Ref-PM
_2.5
method was closer to the actual situation and more capable of PM
_2.5
estimation compared with the AOD-PM
_2.5
method. The PM
_2.5
samples used in the AOD-PM
_2.5
method were less than one-half of the Ref-PM
_2.5
method due to unavailability of AOD observations, which might be due to strict surface assumptions, cloud detection, and error in the aerosol scheme used in the AOD inversion method. This led to many missing values of AOD-derived PM
_2.5
in the spatial distribution map of a single day. Moreover, similar hourly variations in PM
_2.5
were observed for both the methods, and the highest concentration of PM
_2.5
appeared at the junction of Jiangsu, Anhui, and Shandong at 08:00, 09:00, and 10:00 in local time, which gradually decreased at 11:00 and reached to a minimum value at 16:00 and 18:00.