Development of a Deep Learning-Based Atmospheric Correction Algorithm for Oligotrophic Oceans

Although the 5% mission goal for National Aeronautics and Space Administrations (NASA’s) standard atmospheric correction (AC) algorithm (i.e., the near-infrared (NIR) algorithm) for oligotrophic oceans has been met, this algorithm applies only to blue bands and is highly sensitive to contamination from cloud straylight and sunglint. Here, we developed an AC algorithm for clear waters based on deep learning (namely, DLAC). The algorithm was trained using 3.6 million pairs of moderate resolution imaging spectroradiometer (MODIS)-Aqua high-quality
${R} _{\mathrm {rs}}$
from the NIR algorithm and Rayleigh-corrected reflectances selected across the global oceans and from all seasons. Validations using in situ data and a chlorophyll (Chl) constraint-based approach showed that the uncertainties in the
${R} _{\mathrm {rs}}$
retrievals for DLAC are lower than those for the NIR algorithm, especially for the green and red bands. More importantly, the DLAC algorithm is more tolerant to cloud adjacency effects and moderate sunglint. As a result, the number of valid observations increased by
$\sim 50$
%, and the coverage of monthly global Level-
$3~{R} _{\mathrm {rs}}$
composites increased by up to 20%. More spatially and temporally consistent patterns were also found for the Level-
$3~{R} _{\mathrm {rs}}$
and Chl products, and large changes in their magnitudes (up to 20% for
${R} _{\mathrm {rs}}$
and 30% for Chl) were detected in some oceanic regions. With these improvements in the quality and quantity of data, our DLAC algorithm may be valuable as another option for processing global data.