Physical and deep learning retrieved fine mode fraction (Phy-DL FMF)

<p>Aerosol fine-mode fraction (FMF) is a key parameter for discriminating anthropogenic aerosols from natural ones, but it is highly uncertainty from satellite-based retrieval, especially over land.&nbsp; Here we integrated physical and deep learning (Phy-DL) methods to retrieval aerosol FMF in a global land scale based on MODIS data and produced&nbsp;the 20-year (2001-2020) Phy-DL FMF (500 nm) at daily temporal resolution and 1&deg; spatial resolution.</p> <p>The&nbsp;Phy-DL FMF is uploaded as Geotiff format,&nbsp;stretched from -89.5&deg; to 89.5&deg; latitude and from -179.5&deg;&nbsp;to&nbsp;179.5&deg;&nbsp;longitude. In some certain days Phy-DL FMF might be inavailable, due to the missing MODIS satellite data used for calculating&nbsp;Phy-DL FMF.&nbsp;</p>