@Article{PahlevanSAABBBCGGFJKLLMHOPSVVR:2022:SiReSe,
author = "Pahlevan, Nima and Smith, Brandon and Alikas, Krista and Anstee,
Janet and Barbosa, Cl{\'a}udio Clemente Faria and Binding, Caren
and Bresciani, Mariano and Cremelha, Bruno and Giardino, Claudia
and Gurlin, Daniela and Fernandez, Virginia and Jamet, C{\'e}dric
and Kangro, Kersti and Lehmann, Moritz K. and Loisel, Hubert and
Matshushita, Bunkei and H{\`a}, Nguy{\^e}n and Olmanson, Leif
and Potvin, Genevi{\`e}ve and Simis, Stefan G. H. and
VanderWoude, Andrea and Vantrepotte, Vincent and Ruiz-Verdù,
Antonio",
affiliation = "{NASA Goddard Space Flight Center} and {NASA Goddard Space Flight
Center} and {University of Tartu} and {Commonwealth Scientific and
Industrial Research Organization (CSIRO)} and {Instituto Nacional
de Pesquisas Espaciais (INPE)} and {Environment and Climate Change
Canada} and {National Research Council of Italy} and {University
of Sherbrooke} and {National Research Council of Italy} and
{Wisconsin Department of Natural Resources} and {Universidad la
Republica} and {Univ. Littoral C{\^o}te d’Opale} and {University
of Tartu} and {Xerra Earth Observation Institute and the
University of Waikato} and {Univ. Littoral C{\^o}te d’Opale} and
{University of Tsukuba} and {Vietnam National University} and
{University of Minnesota} and {University of Sherbrooke} and
{Plymouth Marine Laboratory} and {National Oceanic and Atmospheric
Administration} and {Univ. Littoral C{\^o}te d’Opale} and
{University of Valencia}",
title = "Simultaneous retrieval of selected optical water quality
indicators from Landsat-8, Sentinel-2, and Sentinel-3",
journal = "Remote Sensing of Environment",
year = "2022",
volume = "270",
pages = "e112860",
month = "Mar.",
keywords = "Inland and coastal waters, Machine learning, MSI, OLCI, OLI, Water
quality.",
abstract = "Constructing multi-source satellite-derived water quality (WQ)
products in inland and nearshore coastal waters from the past,
present, and future missions is a long-standing challenge. Despite
inherent differences in sensors spectral capability, spatial
sampling, and radiometric performance, research efforts focused on
formulating, implementing, and validating universal WQ algorithms
continue to evolve. This research extends a recently developed
machine-learning (ML) model, i.e., Mixture Density Networks (MDNs)
(Pahlevan et al., 2020; Smith et al., 2021), to the inverse
problem of simultaneously retrieving WQ indicators, including
chlorophyll-a (Chla), Total Suspended Solids (TSS), and the
absorption by Colored Dissolved Organic Matter at 440 nm
(acdom(440)), across a wide array of aquatic ecosystems. We use a
database of in situ measurements to train and optimize MDN models
developed for the relevant spectral measurements (400800 nm) of
the Operational Land Imager (OLI), MultiSpectral Instrument (MSI),
and Ocean and Land Color Instrument (OLCI) aboard the Landsat-8,
Sentinel-2, and Sentinel-3 missions, respectively. Our two
performance assessment approaches, namely hold-out and
leave-one-out, suggest significant, albeit varying degrees of
improvements with respect to second-best algorithms, depending on
the sensor and WQ indicator (e.g., 68%, 75%, 117% improvements
based on the hold-out method for Chla, TSS, and acdom(440),
respectively from MSI-like spectra). Using these two assessment
methods, we provide theoretical upper and lower bounds on model
performance when evaluating similar and/or out-of-sample datasets.
To evaluate multi-mission product consistency across broad spatial
scales, map products are demonstrated for three near-concurrent
OLI, MSI, and OLCI acquisitions. Overall, estimated TSS and
acdom(440) from these three missions are consistent within the
uncertainty of the model, but Chla maps from MSI and OLCI achieve
greater accuracy than those from OLI. By applying two different
atmospheric correction processors to OLI and MSI images, we also
conduct matchup analyses to quantify the sensitivity of the MDN
model and best-practice algorithms to uncertainties in reflectance
products. Our model is less or equally sensitive to these
uncertainties compared to other algorithms. Recognizing their
uncertainties, MDN models can be applied as a global algorithm to
enable harmonized retrievals of Chla, TSS, and acdom(440) in
various aquatic ecosystems from multi-source satellite imagery.
Local and/or regional ML models tuned with an apt data
distribution (e.g., a subset of our dataset) should nevertheless
be expected to outperform our global model.",
doi = "10.1016/j.rse.2021.112860",
url = "http://dx.doi.org/10.1016/j.rse.2021.112860",
issn = "0034-4257",
language = "en",
targetfile = "pahlevan_2022.pdf",
urlaccessdate = "29 jun. 2024"
}