BibTeX
@ARTICLE{
         Li2020OIo,
       author = "Li, Lianfa",
       title = "Optimal Inversion of Conversion Parameters from Satellite {AOD} to Ground Aerosol
         Extinction Coefficient Using Automatic Differentiation",
       journal = "Remote Sensing",
       volume = "12",
       year = "2020",
       number = "492",
       url = "https://www.mdpi.com/2072-4292/12/3/492",
       issn = "2072-4292",
       abstract = "Satellite aerosol optical depth (AOD) plays an important role for high
         spatiotemporal-resolution estimation of fine particulate matter with diameters ≤2.5 μm
         (PM2.5). However, the MODIS sensors aboard the Terra and Aqua satellites mainly measure column
         (integrated) AOD using the aerosol (extinction) coefficient integrated over all altitudes in the
         atmosphere, and column AOD is less related to PM2.5 than low-level or ground-based aerosol
         (extinction) coefficient (GAC). With recent development of automatic differentiation (AD) that has
         been widely applied in deep learning, a method using AD to find optimal solution of conversion
         parameters from column AOD to the simulated GAC is presented. Based on the computational graph, AD
         has considerably improved the efficiency in applying gradient descent to find the optimal solution
         for complex problems involving multiple parameters and spatiotemporal factors. In a case study of
         the Jing-Jin-Ji region of China for the estimation of PM2.5 in 2015 using the Multiangle
         Implementation of Atmospheric Correction AOD, the optimal solution of the conversion parameters was
         obtained using AD and the loss function of mean square error. This solution fairly modestly improved
         the Pearson’s correlation between simulated GAC and PM2.5 up to 0.58 (test R2: 0.33), in
         comparison with three existing methods. In the downstream validation, the simulated GACs were used
         to reliably estimate PM2.5, considerably improving test R2 up to 0.90 and achieving consistent match
         for GAC and PM2.5 in their spatial distribution and seasonal variations. With the availability of
         the AD tool, the proposed method can be generalized to the inversion of other similar conversion
         parameters in remote sensing.",
       doi = "10.3390/Li2020OIo",
       ad_area = "Remote Sensing",
       ad_tools = "Tensorflow"
}