El Hourany R., Saab M. A. A., Faour G., Aumont Olivier, Crepon M., Thiria S. (2019). Estimation of secondary phytoplankton pigments from satellite observations using Self-Organizing Maps (SOMs). Journal of Geophysical Research : Oceans, 124 (2), p. 1357-1378. ISSN 2169-9275.
Titre du document
Estimation of secondary phytoplankton pigments from satellite observations using Self-Organizing Maps (SOMs)
El Hourany R., Saab M. A. A., Faour G., Aumont Olivier, Crepon M., Thiria S.
Source
Journal of Geophysical Research : Oceans, 2019,
124 (2), p. 1357-1378 ISSN 2169-9275
This study presents a method for estimating secondary phytoplankton pigments from satellite ocean color observations. We first compiled a large training data set composed of 12,000 samples; each sample is composed of 10 in situ phytoplankton high-performance liquid chromatography (HPLC)-measured pigment concentrations, GlobColour products of chlorophyll-a concentration, and remote sensing reflectance (Rrs()) data at different wavelengths, in addition to advanced very high resolution radiometer sea surface temperature measurements. The resulting data set regroups a large variety of encountered situations between 1997 and 2014. The nonlinear relationship between the in situ and satellite components was identified using a self-organizing map, which is a neural network classifier. As a major result, the self-organizing map enabled reliable estimations of the concentration of chlorophyll-a and of nine different pigments from satellite observations. A cross-validation procedure showed that the estimations were robust for all pigments (R-2>0.75 and an average root-mean-square error=0.016mg/m(3)). A consistent association of several phytoplankton pigments indicating phytoplankton group specific dynamic was shown at a global scale. We also showed the uncertainties for the estimation of each pigment. Plain Language Summary The knowledge of phytoplankton variability is essential to the understanding of the marine ecosystem dynamics and its response to environmental changes. This paper presents a new approach to estimate phytoplankton pigment concentrations from satellite observations by using an artificial neural network, the so-called self-organizing map. This neural network was calibrated using a large data set of in situ pigment observations from oceanic cruises along with ocean color satellite data provided by the Globcolour project and advanced very high resolution radiometer sea surface temperature. This approach allows an accurate estimation of phytoplankton pigment concentrations and their related uncertainties. Moreover, the method allows to reproduce the spatio-temporal variability of pigment concentration and the dynamics of phytoplankton groups. A particular attention is given to the Southern Ocean whose phytoplankton communities are specific.
