@article{fdi:010075731,
  title = {{F}actors structuring phytoplankton community in a large tropical river : case study in the {R}ed {R}iver ({V}ietnam)},
  author = {{D}uong, {T}. {T}. and {H}oang, {T}. {T}. {H}. and {N}guyen, {T}. {K}. and {L}e, {T}. {P}. {Q}. and {L}e, {N}. {D}. and {D}ang, {D}. {K}. and {L}u, {X}. {X}. and {B}ui, {M}. {H}. and {T}rinh, {Q}. {H}. and {D}inh, {T}. {H}. {V}. and {P}ham, {T}. {D}. and {R}ochelle-{N}ewall, {E}mma},
  editor = {},
  language = {{ENG}},
  abstract = {{A}lgal assemblages have been widely used as an ecological indicator of aquatic ecosystem health conditions because of their specific sensitivity to a wide variety of environmental conditions. {I}n turbid rivers, as in other aquatic systems, phytoplankton structure plays an important role in structuring aquatic food webs. {W}orldwide, phytoplankton is less studied in turbid, large tropical rivers compared to temperate river systems. {T}he present study aimed to describe the phytoplankton diversity and abundance in a turbid tropical river (the {R}ed {R}iver, northern part of {V}ietnam from 20 degrees 00 to 25 degrees 30 {N}orth; from 100 degrees 00 to 107 degrees 10 {E}ast) and to determine the importance of a series of environmental variables in controlling the phytoplankton community composition. {P}hytoplankton community was composed of 169 phytoplankton taxa from six algal groups including {B}acillariophyceae, {C}hlorophyceae, {C}ryptophyceae, {E}uglenophyceae, {D}inophyceae and {C}yanobacteria. {C}ommunity composition varied both spatially and with season. {S}ixteen measurement environmental variables were used as input variables for a three-layer backpropagation neural network that was developed to predict the phytoplankton abundance. {P}hytoplankton abundance was successfully predicted using the tagsig transfer function and the {L}evenberg-{M}arquardt backpropagation algorithm. {T}he network was trained to provide a good overall linear fit to the total data set with a slope ({R}) and mean square error ({MSE}) of 0.808 and 0.0107, respectively. {T}he sensitivity analysis and neutral interpretation diagram revealed that total phosphorus ({TP}), flow discharge, water temperature and {P}-{PO}43- were the significant variables. {T}he results showed that the developed {ANN} model was able to simulate phytoplankton abundance in the {R}ed {R}iver. {T}hese findings can help for gaining insight into and the relationship between phytoplankton and environmental factors in this complex, turbid, tropical river.},
  keywords = {{P}hytoplankton community ; {T}hree-layer backpropagation neural network ; {T}he {R}ed {R}iver ; {T}urbidity ; {V}ietnam ; {VIET} {NAM} ; {FLEUVE} {ROUGE}},
  booktitle = {},
  journal = {{L}imnologica},
  volume = {76},
  numero = {},
  pages = {82--93},
  ISSN = {0075-9511},
  year = {2019},
  DOI = {10.1016/j.limno.2019.04.003},
  URL = {https://www.documentation.ird.fr/hor/fdi:010075731},
}