![]() ![]() ![]() Beyond improving performance reconstruction, we show that the different modes appear regionally consistent with the ocean dynamics and that they may help to get new insights into physical-biogeochemical processes controlling phytoplankton spatio-temporal variability at global scale. Each mode is associated with a CNN submodel, standing for a mode-specific response of phytoplankton biomass to the physical forcing. Here, we propose to use a multi-mode Convolutional Neural Network (CNN), which can spatially learn and combine different modes, to globally account for interregional variabilities. ![]() ![]() The time-evolving nature of those provinces prevents imposing a priori spatially-fixed boundary constraints to restrict the learning phase. Indeed, the global ocean is commonly partitioned into biogeochemical provinces (BGCPs) into which phytoplankton growth is supposed to be governed by regionally-”homogeneous” processes. Nevertheless, the relationships between phytoplankton and its physical surrounding environment were implicitly considered homogeneous in space, and training such models on a global scale does not allow one to consider known regional mechanisms. Machine learning models such as Support Vector Regression (SVR) or Multi-Layer Perceptron (MLP) have recently proven to be an alternative approach to mechanistic ones to reconstruct Chl synoptic past time-series before the satellite era from physical predictors. Time series of satellite-derived chlorophyll-a concentration (Chl, a proxy of phytoplankton biomass), continuously generated since 1997, are still too short to investigate the low-frequency variability of phytoplankton biomass (e.g. 2IMT Atlantique, UMR CNRS LabSTICC, Technopole Brest Iroise, Brest, France.1Laboratoire d’Océanographie Physique et Spatiale, CNRS/IFREMER/IRD/UBO, Institut Universitaire Européen de la Mer, Plouzané, France.Joana Roussillon 1*, Ronan Fablet 2, Thomas Gorgues 1, Lucas Drumetz 2, Jean Littaye 1 and Elodie Martinez 1 ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |