@article{fdi:010084411,
  title = {{U}nsupervised optical classification of the seabed color in shallow oligotrophic waters from {S}entinel-2 images : a case study in the {V}oh-{K}one-{P}ouembout {L}agoon ({N}ew {C}aledonia)},
  author = {{W}attelez, {G}. and {D}upouy, {C}{\'e}cile and {J}uillot, {F}arid},
  editor = {},
  language = {{ENG}},
  abstract = {{M}onitoring chlorophyll-a concentration or turbidity is crucial for understanding and managing oligo- to mesotrophic coastal waters quality. {H}owever, mapping bio-optical components from space in such shallow settings remains challenging because of the strong interference of the complex bathymetry and various seabed colors. {C}orrecting the total satellite reflectance signal from the seabed reflectance in ocean color with high resolution sensors is promising. {T}his article shows how unsupervised clustering approaches can be applied to {S}entinel-2 images to classify seabed colors in shallow waters of a tropical oligotrophic lagoon in {N}ew {C}aledonia. {D}ata processing included {L}yzenga correction for estimating the water column reflectance, optical spectra standardization for attenuating water absorption effects and clustering using the unsupervised k-means method. {T}his methodological approach was applied on the 497, 560, 664 and 704 nm optical bands of the selected {S}entinel-2 image. {W}hen applied on non-standardized data, our unsupervised classification retrieved three seafloor clusters, whereas five seafloor clusters could be retrieved using standardized data. {F}or each of these two trials, the computed membership values explained more than 75% of the inertia in each {S}entinel-2 wavelength band used for the clustering. {H}owever, the accuracy of the method was slightly improved when applied on standardized data. {C}onfusion index mapping of the unsupervised clustering retrieved from these data emphasized the relevance and robustness of our methodological approach. {S}uch an approach for seabed colors classification in optically complex shallow settings will be particularly helpful to improve remote sensing of biogeochemical indicators such as chlorophyll-a concentration and turbidity in fragile coastal environments.},
  keywords = {{DONNEES} {SATELLITE} ; {CARTOGRAPHIE} ; {FOND} {MARIN} ; {TURBIDITE} ; {LAGON} ; {ZONE} {TROPICALE} ; seabed mapping ; clustering ; machine learning ; k-means ; tropical lagoon ; {S}entinel-2 ; {N}ew {C}aledonia ; {NOUVELLE} {CALEDONIE} {PROVINCE} {NORD} ; {VOH} ; {KONE} ; {POUEMBOUT}},
  booktitle = {},
  journal = {{R}emote {S}ensing},
  volume = {14},
  numero = {4},
  pages = {836 [16 ]},
  ISSN = {2072-4292},
  year = {2022},
  DOI = {10.3390/rs14040836},
  URL = {https://www.documentation.ird.fr/hor/fdi:010084411},
}