Sundarabalan V Balasubramanian ^1* Ryan O'Shea ^2,3 Arun M Saranathan ^2,3 Christopher C Begeman ^3,4 Daniela Gurlin ⁵ Caren Binding ⁶ Claudia Giardino ⁷ Michelle Christine Tomlinson ⁸ Krista Alikas ⁹ Kersti Kangro ⁹ Moritz K Lehmann ^10,11 Lisa Reed ¹¹ Nima Pahlevan ¹²

• ¹ Geo-Sensing and Imaging Consultancy, Trivandrum, India
• ² Goddard Space Flight Center, National Aeronautics and Space Administration, Greenbelt, Maryland, United States
• ³ Science Systems and Applications, Inc., Lanham, Maryland, United States
• ⁴ BAE Systems, Boulder, CO 80301, United States
• ⁵ Wisconsin Department of Natural Resources, Wisconsin, United States
• ⁶ Environment and Climate Change Canada (ECCC), Burlington, Ontario, Canada
• ⁷ Institute of Electromagnetic Sensing of the Environment, National Research Council (CNR-IREA),, Milano 20133, Italy
• ⁸ National Ocean Service, National Centers for Coastal Ocean Science, National Ocean Service (NOAA), Silver Spring, Maryland, United States
• ⁹ Tartu Observatory of the University of Tartu, Tartumaa, 61602, Estonia
• ¹⁰ Starboard Maritime Intelligence, 6 Johnsonville Road, Wellington, 6037, New Zealand
• ¹¹ School of Science, University of Waikato, Private Bag 3105, Hamilton, 3240, New Zealand
• ¹² National Aeronautics and Space Administration (NASA) Headquarters, 300 Hidden Figures Way SW, Washington D.C. 20546, United States

Ocean color remote sensing tracks water quality globally, but multispectral ocean color sensors often struggle with complex coastal and inland waters. We developed a robust Mixture Density Network (MDN) model to retrieve 10 relevant biogeochemical and optical variables from heritage multispectral ocean color missions. These variables include chlorophyll-a (Chla) and total suspended solids (TSS), as well as the absorbing components of IOPs at their reference wavelengths. The heritage missions include the Moderate Resolution Imaging Spectroradiometer (MODIS) aboard Aqua and Terra, the Environmental Satellite (Envisat) Medium Resolution Imaging Spectrometer (MERIS), and the Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (Suomi NPP). Our model is trained and tested on all available in situ spectra from an augmented version of the GLObal Reflectance community dataset for Imaging and Optical sensing of Aquatic environments (GLORIA) (N=9,956) after having added globally distributed in situ IOP This is a provisional file, not the final typeset measurements. Our model is validated on satellite match-ups corresponding to the SeaWiFS Biooptical Archive and Storage System (SeaBASS) database. For both training and validation, the hyperspectral in situ radiometric and absorption datasets were resampled via the relative spectral response functions of MODIS, MERIS, and VIIRS to simulate the response of each multispectral ocean color mission. Using hold-out (80-20 split) and leave-one-out testing methods, the retrieved parameters exhibited variable uncertainty represented by the Median Symmetric Residual (MdSR) for each parameter and sensor combination. The median MdSR over all 10 variables for the hold-out testing method was 25.9%, 24.5%, and 28.9% for MODIS, MERIS, and VIIRS, respectively. The developed MDN was applied to satellite-derived Rrs products to practically validate their quality via the SeaBASS dataset. The median MdSR from all estimated variables for each sensor from the matchup analysis is 63.21% for MODIS/A, 63.15% for MODIS/T, 60.45% for MERIS, and 75.19% for VIIRS. The developed MDN is shown to be capable of robustly retrieving 10 water quality variables for monitoring coastal and inland waters from multiple multispectral satellite sensors (MODIS, MERIS, and VIIRS).