A new approach to estimate the aerosol scattering ratios for the atmospheric correction of satellite remote sensing data in coastal regions

Aerosol scattering reflectance is the most uncertain term to be determined in the atmospheric correction of satellite remote sensing data. The values in the visible bands depend on the aerosol scattering ratios (the epsilon spectrum). The epsilon value in the Near-infrared (NIR) band is estimated on the dark pixel assumption of the water-leaving reflectance in the two NIR bands and then the epsilon spectrum is determined from the aerosol models. This assumption usually becomes invalid for turbid coastal waters, leading to lost regions in the satellite imagery masked by the failure of the atmospheric correction. A new approach was developed to accurately estimate epsilon from turbid coastal waters. This method is based on the idea that the aerosol scattering reflectance and the epsilon values can be obtained from the known water-leaving reflectance of in situ measurements. The water-leaving reflectance is determined from the choice of a look-up table of the water-leaving reflectance based on the Angstrom law of the candidate aerosol scattering reflectance using the best non-linear least squares fit function. In this approach, the entire epsilon spectra can be obtained and used to determine the two closest aerosol models which are used to interpolate the actual epsilon values. It is demonstrated that the results from matching the entire spectra are more robust than that obtained from using only one epsilon value. The performance of the approach was evaluated using the simulated reflectance at the top of the atmosphere, the Sea-viewing Wide Field-of-view Sensor (SeaWiFS) imagery, and in situ measured aerosol optical thickness. This approach is based on the assumption of the aerosol scattering reflectance following the Angstrom law instead of the standard dark pixel assumption, named as the ENLF model. This new assumption is valid for both Case I and Case 2 waters, even over terrestrial regions. Therefore, the ENLF model provides a potential approach for a universal algorithm of the atmospheric correction of satellite remote sensing data. (C) 2013 Elsevier Inc. All rights reserved.