@article{fdi:010075513,
  title = {{E}stimation of secondary phytoplankton pigments from satellite observations using {S}elf-{O}rganizing {M}aps ({SOM}s)},
  author = {{E}l {H}ourany, {R}. and {S}aab, {M}. {A}. {A}. and {F}aour, {G}. and {A}umont, {O}livier and {C}repon, {M}. and {T}hiria, {S}.},
  editor = {},
  language = {{ENG}},
  abstract = {{T}his study presents a method for estimating secondary phytoplankton pigments from satellite ocean color observations. {W}e first compiled a large training data set composed of 12,000 samples; each sample is composed of 10 in situ phytoplankton high-performance liquid chromatography ({HPLC})-measured pigment concentrations, {G}lob{C}olour products of chlorophyll-a concentration, and remote sensing reflectance ({R}rs()) data at different wavelengths, in addition to advanced very high resolution radiometer sea surface temperature measurements. {T}he resulting data set regroups a large variety of encountered situations between 1997 and 2014. {T}he nonlinear relationship between the in situ and satellite components was identified using a self-organizing map, which is a neural network classifier. {A}s a major result, the self-organizing map enabled reliable estimations of the concentration of chlorophyll-a and of nine different pigments from satellite observations. {A} cross-validation procedure showed that the estimations were robust for all pigments ({R}-2>0.75 and an average root-mean-square error=0.016mg/m(3)). {A} consistent association of several phytoplankton pigments indicating phytoplankton group specific dynamic was shown at a global scale. {W}e also showed the uncertainties for the estimation of each pigment. {P}lain {L}anguage {S}ummary {T}he knowledge of phytoplankton variability is essential to the understanding of the marine ecosystem dynamics and its response to environmental changes. {T}his paper presents a new approach to estimate phytoplankton pigment concentrations from satellite observations by using an artificial neural network, the so-called self-organizing map. {T}his neural network was calibrated using a large data set of in situ pigment observations from oceanic cruises along with ocean color satellite data provided by the {G}lobcolour project and advanced very high resolution radiometer sea surface temperature. {T}his approach allows an accurate estimation of phytoplankton pigment concentrations and their related uncertainties. {M}oreover, the method allows to reproduce the spatio-temporal variability of pigment concentration and the dynamics of phytoplankton groups. {A} particular attention is given to the {S}outhern {O}cean whose phytoplankton communities are specific.},
  keywords = {},
  booktitle = {},
  journal = {{J}ournal of {G}eophysical {R}esearch : {O}ceans},
  volume = {124},
  numero = {2},
  pages = {1357--1378},
  ISSN = {2169-9275},
  year = {2019},
  DOI = {10.1029/2018jc014450},
  URL = {https://www.documentation.ird.fr/hor/fdi:010075513},
}