Estimating Regional Ground‐Level PM2.5 Directly From Satellite Top‐Of‐Atmosphere Reflectance Using Deep Belief Networks

Almost all remote sensing atmospheric PM2.5 estimation methods need satellite aerosol optical depth (AOD) products, which are often retrieved from top‐of‐atmosphere (TOA) reflectance via an atmospheric radiative transfer model. Then, is it possible to estimate ground‐level PM2.5 directly from satellite TOA reflectance without a physical model? In this study, this challenging work was achieved based on a machine learning model. Specifically, we established the relationship between PM2.5, satellite TOA reflectance, observation angles, and meteorological factors in a deep learning architecture (denoted as Ref‐PM modeling). This relationship was trained with station PM2.5 measurements, and then the PM2.5 values of those locations without stations could be retrieved. Taking the Wuhan Urban Agglomeration as a case study, the results demonstrate that, compared with AOD‐PM modeling, the Ref‐PM modeling obtains a competitive performance, with sample‐based cross‐validated R2 and root‐mean‐square error values of 0.87 and 9.89 μg/m3, respectively. Also, the TOA‐reflectance‐derived PM2.5 has a finer resolution and a larger spatial coverage than the AOD‐derived PM2.5. This work provides an alternative technique to estimate ground‐level PM2.5, and may have the potential to promote the application in atmospheric environmental monitoring.