TY - JOUR T1 - Neural Network Approaches to Reconstruct Phytoplankton Time-Series in the Global Ocean A1 - Martinez,Elodie A1 - Brini,Anouar A1 - Gorgues,Thomas A1 - Drumetz,Lucas A1 - Roussillon,Joana A1 - Tandeo,Pierre A1 - Maze,Guillaume A1 - Fablet,Ronan AD - Laboratoire d’Océanographie Physique et Spatiale (LOPS), IUEM, University Brest-CNRS-IRD-Ifremer, 29200 Brest, France AD - IMT Atlantique, Lab-STICC, UMR CNRS 6285, 29200 Brest, France AD - Laboratoire d’Océanographie Physique et Spatiale (LOPS), IUEM, University Brest-CNRS-IRD-Ifremer, 29200 Brest, France UR - https://archimer.ifremer.fr/doc/00667/77871/ DO - 10.3390/rs12244156 KW - phytoplankton time-series reconstruction KW - ocean color KW - neural networks KW - support vector regression KW - multi-layer perceptron KW - physical predictors N2 - 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. Y1 - 2020/12 PB - MDPI AG JF - Remote Sensing SN - 2072-4292 VL - 12 IS - 24 ID - 77871 ER -