@article{fdi:010089748,
  title = {{L}inking satellites to genes with machine learning to estimate phytoplankton community structure from space},
  author = {{E}l {H}ourany, {R}. and {K}arlusich, {J}. {P}. and {Z}inger, {L}. and {L}oisel, {H}. and {L}evy, {M}arina and {B}owler, {C}.},
  editor = {},
  language = {{ENG}},
  abstract = {{O}cean color remote sensing has been used for more than 2 decades to estimate primary productivity. {A}pproaches have also been developed to disentangle phytoplankton community structure based on spectral data from space, in particular when combined with in situ measurements of photosynthetic pigments. {H}ere, we propose a new ocean color algorithm to derive the relative cell abundance of seven phytoplankton groups, as well as their contribution to total chlorophyll a ({C}hl a ) at the global scale. {O}ur algorithm is based on machine learning and has been trained using remotely sensed parameters (reflectance, backscattering, and attenuation coefficients at different wavelengths, plus temperature and {C}hl a ) combined with an omics-based biomarker developed using {T}ara {O}ceans data representing a single-copy gene encoding a component of the photosynthetic machinery that is present across all phytoplankton, including both prokaryotes and eukaryotes. {I}t differs from previous methods which rely on diagnostic pigments to derive phytoplankton groups. {O}ur methodology provides robust estimates of the phytoplankton community structure in terms of relative cell abundance and contribution to total {C}hl a concentration. {T}he newly generated datasets yield complementary information about different aspects of phytoplankton that are valuable for assessing the contributions of different phytoplankton groups to primary productivity and inferring community assembly processes. {T}his makes remote sensing observations excellent tools to collect essential biodiversity variables ({EBV}s) and provide a foundation for developing marine biodiversity forecasts.},
  keywords = {{MONDE}},
  booktitle = {},
  journal = {{O}cean {S}cience},
  volume = {20},
  numero = {1},
  pages = {217--239},
  ISSN = {1812-0784},
  year = {2024},
  DOI = {10.5194/os-20-217-2024},
  URL = {https://www.documentation.ird.fr/hor/fdi:010089748},
}