@article{Zolfaghari-2022-Impact,
title = "Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment",
author = "Zolfaghari, Kiana and
Pahlevan, Nima and
Binding, Caren and
Gurlin, Daniela and
Simis, Stefan and
Verd{\'u}, Antonio Ruiz and
Li, Lin and
Crawford, Christopher J. and
Woude, Andrea Vander and
Errera, Reagan M. and
Zastepa, Arthur and
Duguay, Claude",
journal = "IEEE Transactions on Geoscience and Remote Sensing, Volume 60",
volume = "60",
year = "2022",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
url = "https://gwf-uwaterloo.github.io/gwf-publications/G22-68002",
doi = "10.1109/tgrs.2021.3114635",
pages = "1--20",
abstract = "Cyanobacterial harmful algal blooms are an increasing threat to coastal and inland waters. These blooms can be detected using optical radiometers due to the presence of phycocyanin (PC) pigments. The spectral resolution of best-available multispectral sensors limits their ability to diagnostically detect PC in the presence of other photosynthetic pigments. To assess the role of spectral resolution in the determination of PC, a large ( {\textless}inline-formula xmlns:mml=``http://www.w3.org/1998/Math/MathML'' xmlns:xlink=``http://www.w3.org/1999/xlink''{\textgreater} {\textless}tex-math notation=``LaTeX''{\textgreater}{\$}N =905{\$} {\textless}/tex-math{\textgreater}{\textless}/inline-formula{\textgreater} ) database of colocated {\textless}italic xmlns:mml=``http://www.w3.org/1998/Math/MathML'' xmlns:xlink=``http://www.w3.org/1999/xlink''{\textgreater}in situ{\textless}/i{\textgreater} radiometric spectra and PC are employed. We first examine the performance of selected widely used machine-learning (ML) models against that of benchmark algorithms for hyperspectral remote sensing reflectance ( {\textless}inline-formula xmlns:mml=``http://www.w3.org/1998/Math/MathML'' xmlns:xlink=``http://www.w3.org/1999/xlink''{\textgreater} {\textless}tex-math notation=``LaTeX''{\textgreater}{\$}R{\_}{{\textbackslash}mathrm {rs}}{\$} {\textless}/tex-math{\textgreater}{\textless}/inline-formula{\textgreater} ) spectra resampled to the spectral configuration of the Hyperspectral Imager for the Coastal Ocean (HICO) with a full-width at half-maximum (FWHM) of {\textless} 6 nm. Results show that the multilayer perceptron (MLP) neural network applied to HICO spectral configurations (median errors {\textless} 65{\%}) outperforms other ML models. This model is subsequently applied to {\textless}inline-formula xmlns:mml=``http://www.w3.org/1998/Math/MathML'' xmlns:xlink=``http://www.w3.org/1999/xlink''{\textgreater} {\textless}tex-math notation=``LaTeX''{\textgreater}{\$}R{\_}{{\textbackslash}mathrm {rs}}{\$} {\textless}/tex-math{\textgreater}{\textless}/inline-formula{\textgreater} spectra resampled to the band configuration of existing satellite instruments and of the one proposed for the next Landsat sensor. These results confirm that employing MLP models to estimate PC from hyperspectral data delivers tangible improvements compared with retrievals from multispectral data and benchmark algorithms (with median errors between {\textless}inline-formula xmlns:mml=``http://www.w3.org/1998/Math/MathML'' xmlns:xlink=``http://www.w3.org/1999/xlink''{\textgreater} {\textless}tex-math notation=``LaTeX''{\textgreater}{\$}{\textbackslash}sim 73{\$} {\textless}/tex-math{\textgreater}{\textless}/inline-formula{\textgreater} {\%} and 126{\%}) and shows promise for developing a globally applicable cyanobacteria measurement approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="Zolfaghari-2022-Impact">
<titleInfo>
<title>Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiana</namePart>
<namePart type="family">Zolfaghari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nima</namePart>
<namePart type="family">Pahlevan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caren</namePart>
<namePart type="family">Binding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Gurlin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Simis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Ruiz</namePart>
<namePart type="family">Verdú</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Crawford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="given">Vander</namePart>
<namePart type="family">Woude</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reagan</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Errera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Zastepa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claude</namePart>
<namePart type="family">Duguay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>IEEE Transactions on Geoscience and Remote Sensing, Volume 60</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>Institute of Electrical and Electronics Engineers (IEEE)</publisher>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Cyanobacterial harmful algal blooms are an increasing threat to coastal and inland waters. These blooms can be detected using optical radiometers due to the presence of phycocyanin (PC) pigments. The spectral resolution of best-available multispectral sensors limits their ability to diagnostically detect PC in the presence of other photosynthetic pigments. To assess the role of spectral resolution in the determination of PC, a large ( \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$N =905$ \textless/tex-math\textgreater\textless/inline-formula\textgreater ) database of colocated \textlessitalic xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreaterin situ\textless/i\textgreater radiometric spectra and PC are employed. We first examine the performance of selected widely used machine-learning (ML) models against that of benchmark algorithms for hyperspectral remote sensing reflectance ( \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$R_\textbackslashmathrm rs$ \textless/tex-math\textgreater\textless/inline-formula\textgreater ) spectra resampled to the spectral configuration of the Hyperspectral Imager for the Coastal Ocean (HICO) with a full-width at half-maximum (FWHM) of \textless 6 nm. Results show that the multilayer perceptron (MLP) neural network applied to HICO spectral configurations (median errors \textless 65%) outperforms other ML models. This model is subsequently applied to \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$R_\textbackslashmathrm rs$ \textless/tex-math\textgreater\textless/inline-formula\textgreater spectra resampled to the band configuration of existing satellite instruments and of the one proposed for the next Landsat sensor. These results confirm that employing MLP models to estimate PC from hyperspectral data delivers tangible improvements compared with retrievals from multispectral data and benchmark algorithms (with median errors between \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$\textbackslashsim 73$ \textless/tex-math\textgreater\textless/inline-formula\textgreater % and 126%) and shows promise for developing a globally applicable cyanobacteria measurement approach.</abstract>
<identifier type="citekey">Zolfaghari-2022-Impact</identifier>
<identifier type="doi">10.1109/tgrs.2021.3114635</identifier>
<location>
<url>https://gwf-uwaterloo.github.io/gwf-publications/G22-68002</url>
</location>
<part>
<date>2022</date>
<detail type="volume"><number>60</number></detail>
<extent unit="page">
<start>1</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment
%A Zolfaghari, Kiana
%A Pahlevan, Nima
%A Binding, Caren
%A Gurlin, Daniela
%A Simis, Stefan
%A Verdú, Antonio Ruiz
%A Li, Lin
%A Crawford, Christopher J.
%A Woude, Andrea Vander
%A Errera, Reagan M.
%A Zastepa, Arthur
%A Duguay, Claude
%J IEEE Transactions on Geoscience and Remote Sensing, Volume 60
%D 2022
%V 60
%I Institute of Electrical and Electronics Engineers (IEEE)
%F Zolfaghari-2022-Impact
%X Cyanobacterial harmful algal blooms are an increasing threat to coastal and inland waters. These blooms can be detected using optical radiometers due to the presence of phycocyanin (PC) pigments. The spectral resolution of best-available multispectral sensors limits their ability to diagnostically detect PC in the presence of other photosynthetic pigments. To assess the role of spectral resolution in the determination of PC, a large ( \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$N =905$ \textless/tex-math\textgreater\textless/inline-formula\textgreater ) database of colocated \textlessitalic xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreaterin situ\textless/i\textgreater radiometric spectra and PC are employed. We first examine the performance of selected widely used machine-learning (ML) models against that of benchmark algorithms for hyperspectral remote sensing reflectance ( \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$R_\textbackslashmathrm rs$ \textless/tex-math\textgreater\textless/inline-formula\textgreater ) spectra resampled to the spectral configuration of the Hyperspectral Imager for the Coastal Ocean (HICO) with a full-width at half-maximum (FWHM) of \textless 6 nm. Results show that the multilayer perceptron (MLP) neural network applied to HICO spectral configurations (median errors \textless 65%) outperforms other ML models. This model is subsequently applied to \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$R_\textbackslashmathrm rs$ \textless/tex-math\textgreater\textless/inline-formula\textgreater spectra resampled to the band configuration of existing satellite instruments and of the one proposed for the next Landsat sensor. These results confirm that employing MLP models to estimate PC from hyperspectral data delivers tangible improvements compared with retrievals from multispectral data and benchmark algorithms (with median errors between \textlessinline-formula xmlns:mml=“http://www.w3.org/1998/Math/MathML” xmlns:xlink=“http://www.w3.org/1999/xlink”\textgreater \textlesstex-math notation=“LaTeX”\textgreater$\textbackslashsim 73$ \textless/tex-math\textgreater\textless/inline-formula\textgreater % and 126%) and shows promise for developing a globally applicable cyanobacteria measurement approach.
%R 10.1109/tgrs.2021.3114635
%U https://gwf-uwaterloo.github.io/gwf-publications/G22-68002
%U https://doi.org/10.1109/tgrs.2021.3114635
%P 1-20
Markdown (Informal)
[Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment](https://gwf-uwaterloo.github.io/gwf-publications/G22-68002) (Zolfaghari et al., GWF 2022)
ACL
- Kiana Zolfaghari, Nima Pahlevan, Caren Binding, Daniela Gurlin, Stefan Simis, Antonio Ruiz Verdú, Lin Li, Christopher J. Crawford, Andrea Vander Woude, Reagan M. Errera, Arthur Zastepa, and Claude Duguay. 2022. Impact of Spectral Resolution on Quantifying Cyanobacteria in Lakes and Reservoirs: A Machine-Learning Assessment. IEEE Transactions on Geoscience and Remote Sensing, Volume 60, 60:1–20.
