Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation
Ocean color remote sensing tracks water quality globally, but multispectral ocean color sensors often struggle with complex coastal and inland waters. Traditional models have difficulty capturing detailed relationships between remote sensing reflectance (Rrs), biogeochemical properties (BPs), and in...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Remote Sensing |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frsen.2025.1488565/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832539913878241280 |
|---|---|
| author | Sundarabalan V. Balasubramanian Ryan E. O’Shea Ryan E. O’Shea Arun M. Saranathan Arun M. Saranathan Christopher C. Begeman Christopher C. Begeman Daniela Gurlin Caren Binding Claudia Giardino Michelle C. Tomlinson Krista Alikas Kersti Kangro Moritz K. Lehmann Moritz K. Lehmann Lisa Reed |
| author_facet | Sundarabalan V. Balasubramanian Ryan E. O’Shea Ryan E. O’Shea Arun M. Saranathan Arun M. Saranathan Christopher C. Begeman Christopher C. Begeman Daniela Gurlin Caren Binding Claudia Giardino Michelle C. Tomlinson Krista Alikas Kersti Kangro Moritz K. Lehmann Moritz K. Lehmann Lisa Reed |
| author_sort | Sundarabalan V. Balasubramanian |
| collection | DOAJ |
| description | Ocean color remote sensing tracks water quality globally, but multispectral ocean color sensors often struggle with complex coastal and inland waters. Traditional models have difficulty capturing detailed relationships between remote sensing reflectance (Rrs), biogeochemical properties (BPs), and inherent optical properties (IOPs) in these complex water bodies. 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 measurements. Our model is validated on satellite match-ups corresponding to the SeaWiFS Bio-optical 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. TSS was the parameter with the highest MdSR for all three sensors (MODIS, VIIRS, and MERIS). 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. We found that the MDN model is sensitive to the instrument noise and uncertainties from atmospheric correction present in multispectral satellite-derived Rrs. The overall performance of the MDN model presented here was also analyzed qualitatively for near-simultaneous images of MODIS/A and VIIRS as well as MODIS/T and MERIS to understand and demonstrate the product resemblance and discrepancies in retrieved variables. 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). |
| format | Article |
| id | doaj-art-930375043fd1491c80b8b2982aa44680 |
| institution | Kabale University |
| issn | 2673-6187 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Remote Sensing |
| spelling | doaj-art-930375043fd1491c80b8b2982aa446802025-02-05T07:32:54ZengFrontiers Media S.A.Frontiers in Remote Sensing2673-61872025-02-01610.3389/frsen.2025.14885651488565Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validationSundarabalan V. Balasubramanian0Ryan E. O’Shea1Ryan E. O’Shea2Arun M. Saranathan3Arun M. Saranathan4Christopher C. Begeman5Christopher C. Begeman6Daniela Gurlin7Caren Binding8Claudia Giardino9Michelle C. Tomlinson10Krista Alikas11Kersti Kangro12Moritz K. Lehmann13Moritz K. Lehmann14Lisa Reed15Geosensing and Imaging Consultancy, Trivandrum, Kerala, IndiaNASA Goddard Spaceflight Center, Greenbelt, MD, United StatesScience Systems and Applications, Inc., Lanham, MD, United StatesNASA Goddard Spaceflight Center, Greenbelt, MD, United StatesScience Systems and Applications, Inc., Lanham, MD, United StatesScience Systems and Applications, Inc., Lanham, MD, United StatesBAE Systems, Boulder, CO, United StatesWisconsin Department of Natural Resources, Madison, WI, United StatesEnvironment and Climate Change Canada, Burlington, ON, CanadaInstitute of Electromagnetic Sensing of the Environment, National Research Council (CNR-IREA), Milano, ItalyNOAA National Ocean Service, National Centers for Coastal Ocean Science, Silver Spring, MD, United StatesDepartment of Remote Sensing, Tartu Observatory, University of Tartu, Tartu, EstoniaDepartment of Remote Sensing, Tartu Observatory, University of Tartu, Tartu, Estonia0Starboard Maritime Intelligence, Wellington, New Zealand1School of Science, University of Waikato, Hamilton, New Zealand1School of Science, University of Waikato, Hamilton, New ZealandOcean color remote sensing tracks water quality globally, but multispectral ocean color sensors often struggle with complex coastal and inland waters. Traditional models have difficulty capturing detailed relationships between remote sensing reflectance (Rrs), biogeochemical properties (BPs), and inherent optical properties (IOPs) in these complex water bodies. 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 measurements. Our model is validated on satellite match-ups corresponding to the SeaWiFS Bio-optical 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. TSS was the parameter with the highest MdSR for all three sensors (MODIS, VIIRS, and MERIS). 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. We found that the MDN model is sensitive to the instrument noise and uncertainties from atmospheric correction present in multispectral satellite-derived Rrs. The overall performance of the MDN model presented here was also analyzed qualitatively for near-simultaneous images of MODIS/A and VIIRS as well as MODIS/T and MERIS to understand and demonstrate the product resemblance and discrepancies in retrieved variables. 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).https://www.frontiersin.org/articles/10.3389/frsen.2025.1488565/fullaquatic remote sensingneural networksmultispectralbiogeochemical parametersinland and coastal watersMODIS |
| spellingShingle | Sundarabalan V. Balasubramanian Ryan E. O’Shea Ryan E. O’Shea Arun M. Saranathan Arun M. Saranathan Christopher C. Begeman Christopher C. Begeman Daniela Gurlin Caren Binding Claudia Giardino Michelle C. Tomlinson Krista Alikas Kersti Kangro Moritz K. Lehmann Moritz K. Lehmann Lisa Reed Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation Frontiers in Remote Sensing aquatic remote sensing neural networks multispectral biogeochemical parameters inland and coastal waters MODIS |
| title | Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation |
| title_full | Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation |
| title_fullStr | Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation |
| title_full_unstemmed | Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation |
| title_short | Mixture density networks for re-constructing historical ocean-color products over inland and coastal waters: demonstration and validation |
| title_sort | mixture density networks for re constructing historical ocean color products over inland and coastal waters demonstration and validation |
| topic | aquatic remote sensing neural networks multispectral biogeochemical parameters inland and coastal waters MODIS |
| url | https://www.frontiersin.org/articles/10.3389/frsen.2025.1488565/full |
| work_keys_str_mv | AT sundarabalanvbalasubramanian mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT ryaneoshea mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT ryaneoshea mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT arunmsaranathan mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT arunmsaranathan mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT christophercbegeman mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT christophercbegeman mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT danielagurlin mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT carenbinding mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT claudiagiardino mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT michellectomlinson mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT kristaalikas mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT kerstikangro mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT moritzklehmann mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT moritzklehmann mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation AT lisareed mixturedensitynetworksforreconstructinghistoricaloceancolorproductsoverinlandandcoastalwatersdemonstrationandvalidation |