@Article{LimaGiBrBaFaPeBe:2023:CoSeMa,
author = "Lima, Thainara Munhoz Alexandre de and Giardino, Claudia and
Bresciani, Mariano and Barbosa, Cl{\'a}udio Clemente Faria and
Fabbretto, Alice and Pellegrino, Andrea and Begliomini, Felipe
Nincao",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {National
Research Council of Italy} and {National Research Council of
Italy} and {Instituto Nacional de Pesquisas Espaciais (INPE)} and
{National Research Council of Italy} and {National Research
Council of Italy} and {University of Cambridge}",
title = "Assessment of estimated phycocyanin and chlorophyll-a
concentration from PRISMA and OLCI in Brazilian inland waters: a
comparison between semi-analytical and machine learning
algorithms",
journal = "Remote Sensing",
year = "2023",
volume = "15",
number = "5",
pages = "e1299",
month = "Mar.",
keywords = "aquatic remote sensing, cyanobacteria, hyperspectral, machine
learning, phycocyanin, semi-analytical model.",
abstract = "The aim of this work is to test the state-of-the-art of water
constituent retrieval algorithms for phycocyanin (PC) and
chlorophyll-a (chl-a) concentrations in Brazilian reservoirs from
hyperspectral PRISMA images and concurrent in situ data. One
near-coincident Sentinel-3 OLCI dataset has also been considered
for PC mapping as its high revisit time is a relevant element for
mapping cyanobacterial blooms. The testing was first performed on
remote sensing reflectance ((Formula presented.)), as derived by
applying two atmospheric correction methods (6SV, ACOLITE) to
Level 1 data and as provided in the corresponding Level 2 products
(PRISMA L2C and OLCI L2-WFR). Since PRISMA images were affected by
sun glint, the testing of three de-glint models was also
performed. The applicability of Semi-Analytical (SA) and Mixture
Density Network (MDN) algorithms in enabling PC and chl-a
concentration retrieval was then tested over three PRISMA scenes;
in the case of PC concentration estimation, a Random Forest (RF)
algorithm was further applied. Regarding OLCI, the SA algorithm
was tested for PC estimation; notably, only SA was calibrated with
site-specific data from the reservoir. The algorithms were applied
to the (Formula presented.) spectra provided by PRISMA L2C
productsand those derived with ACOLITE, in the case of OLCIas
these data showed better agreement with in situ measurements. The
SA model provided low median absolute error (MdAE) for
PRISMA-derived (MdAE = 3.06 mg.m\−3) and OLCI-derived (MdAE
= 3.93 mg.m\−3) PC concentrations, while it overestimated
PRISMA-derived chl-a (MdAE = 42.11 mg.m\−3). The RF model
for PC applied to PRISMA performed slightly worse than SA (MdAE =
5.21 mg.m\−3). The MDN showed a rather different
performance, with higher errors for PC (MdAE = 40.94
mg.m\−3) and lower error for chl-a (MdAE = 23.21
mg.m\−3). The results overall suggest that the model
calibrated with site-specific measurements performed better and
indicates that SA could be applied to PRISMA and OLCI for remote
sensing of PC in Brazilian reservoirs.",
doi = "10.3390/rs15051299",
url = "http://dx.doi.org/10.3390/rs15051299",
issn = "2072-4292",
language = "en",
targetfile = "remotesensing-15-01299-v2.pdf",
urlaccessdate = "03 maio 2024"
}