FN Archimer Export Format
PT J
TI Neural Network Approaches to Reconstruct Phytoplankton Time-Series in the Global Ocean
BT 
AF Martinez, Elodie
   Brini, Anouar
   Gorgues, Thomas
   Drumetz, Lucas
   Roussillon, Joana
   Tandeo, Pierre
   Maze, Guillaume
   Fablet, Ronan
AS 1:3;2:3;3:3;4:2;5:3;6:2;7:1;8:2;
FF 1:;2:;3:;4:;5:;6:;7:PDG-ODE-LOPS-OH;8:;
C1 Laboratoire d’Océanographie Physique et Spatiale (LOPS), IUEM, University Brest-CNRS-IRD-Ifremer, 29200 Brest, France
   IMT Atlantique, Lab-STICC, UMR CNRS 6285, 29200 Brest, France
   Laboratoire d’Océanographie Physique et Spatiale (LOPS), IUEM, University Brest-CNRS-IRD-Ifremer, 29200 Brest, France
C2 IFREMER, FRANCE
   IMT ATLANTIQUE, FRANCE
   IRD, FRANCE
SI BREST
SE PDG-ODE-LOPS-OH
UM LOPS
IN WOS Ifremer UMR
   WOS Cotutelle UMR
   DOAJ
   copubli-france
   copubli-p187
IF 2.1
TC 5
UR https://archimer.ifremer.fr/doc/00667/77871/80017.pdf
   https://archimer.ifremer.fr/doc/00667/77871/80018.pdf
   https://archimer.ifremer.fr/doc/00667/77871/97543.pdf
LA English
DT Article
DE ;phytoplankton time-series reconstruction;ocean color;neural networks;support vector regression;multi-layer perceptron;physical predictors
AB Phytoplankton plays a key role in the carbon cycle and supports the oceanic food web. While its seasonal and interannual cycles are rather well characterized owing to the modern satellite ocean color era, its longer time variability remains largely unknown due to the short time-period covered by observations on a global scale. With the aim of reconstructing this longer-term phytoplankton variability, a support vector regression (SVR) approach was recently considered to derive surface Chlorophyll-a concentration (Chl, a proxy of phytoplankton biomass) from physical oceanic model outputs and atmospheric reanalysis. However, those early efforts relied on one particular algorithm, putting aside the question of whether different algorithms may have specific behaviors. Here, we show that this approach can also be applied on satellite observations and can even be further improved by testing performances of different machine learning algorithms, the SVR and a neural network with dense layers (a multi-layer perceptron, MLP). The MLP outperforms the SVR to capture satellite Chl (correlation of 0.6 vs. 0.17 on a global scale, respectively) along with its seasonal and interannual variability, despite an underestimated amplitude. Among deep learning algorithms, neural network such as MLP models appear to be promising tools to investigate phytoplankton long-term time-series. 
PY 2020
PD DEC
SO Remote Sensing
SN 2072-4292
PU MDPI AG
VL 12
IS 24
UT 000603329000001
DI 10.3390/rs12244156
ID 77871
ER

EF