A231-02
OC-SMART: A Machine Learning Platform for Satellite Ocean Color data Analysis
Wednesday, 16 December 2020: 05:39
Virtual
Knut H Stamnes1, Yongzhen Fan1, Wei Li1, Nan Chen2, Jae-Hyun Ahn3, Young-Je Park3, Susanne Kratzer4, Thomas Schroeder5,6 and Joji Ishizaka7, (1)Stevens Institute of Technology, Hoboken, NJ, United States, (2)Stevens Institute of Technology, Union City, NJ, United States, (3)KIOST Korea Institute of Ocean Science and Technology, Korea Ocean Satellite Center, Busan, South Korea, (4)Stockholm University, Department of Ecology, Environment and Plant Sciences (DEEP), Stockholm, Sweden, (5)CSIRO Marine and Atmospheric Research, Hobart, Australia, (6)CSIRO Ocean & Atmosphere, Brisbane, Australia, (7)Nagoya University, Nagoya, Japan
Abstract:
We present a powerful new tool: Ocean Color - Simultaneous Marine and Aerosol Retrieval Tool (OC-SMART), for analysis of data obtained by satellite ocean color sensors. OC-SMART is a multi-sensor data analysis platform which supports heritage, current, and possible future multi-spectral and hyper-spectral sensors from US, EU, Korea, Japan, and China, including SeaWiFS, Aqua/MODIS, SNPP/VIIRS, ISS/HICO, Landsat8/OLI, DSCOVR/EPIC, Sentinel-2/MSI, Sentinel-3/OLCI, COMS/GOCI, GCOM-C/SGLI, and FengYun-3D/MERSI2. The products provided by OC-SMART include spectral remote sensing reflectances, chlorophyll-a
concentrations, and spectral ocean inherent optical properties (IOPs) including absorption coefficients due to phytoplankton and gelbstoff and backscattering coefficients due to particulates. Spectral aerosol optical depths, cloud mask results, and uncertainty estimates are also provided by OC-SMART.
OC-SMART retrieves high-quality global ocean color products, especially under complex environmental conditions, such as coastal/inland turbid water areas and heavy aerosol loadings. The atmospheric correction (AC) and ocean IOP algorithms in OC-SMART are driven by extensive coupled atmosphere-ocean radiative transfer simulations in conjunction with powerful machine learning techniques. For each sensor, we have created huge and comprehensive training datasets to support the development of the machine learning AC and ocean IOP algorithms. OC-SMART completely resolves the negative water-leaving radiance problem that has plagued heritage AC algorithms. The comprehensive training datasets created using multiple atmosphere, aerosol, and ocean IOP models ensure global applicability of OC-SMART.
The use of machine learning algorithms makes OC-SMART roughly 10 times faster than NASA's SeaDAS platform. OC-SMART also includes an advanced cloud screening algorithm and is resilient to the contamination by sunglint and cloud edges. It is therefore capable of recovering large amounts of data that are discarded by other algorithms (such as those implemented in NASA's SeaDAS package), especially in coastal areas. OC-SMART is currently available as a standalone Python package or as a plugin that can be installed in ESA's Sentinel Application Platform (SNAP).
