Abstract
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, thanks to its ability to capture complex non-linear relationships, outperforms the SVR to capture satellite Chl spatial patterns (correlation of 0.75 vs. 0.65 on a global scale, respectively) along with its interannual variability and trend, 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.
Highlights
Phytoplankton—the microalgae that populates the upper sunlit layers of the ocean—fuels the oceanic food web and regulates oceanic and atmospheric carbon dioxide levels through photosynthetic carbon fixation ([1,2])
The multi-layer perceptron (MLP) trained on the same amount of data than the support vector regression (SVR) is more skillful than the SVR to reconstruct ChlOC-CCI (Figure 2, middle row)
ChlMLP still underestimates ChlOC-CCI, in the Pacific. Some of these differences may be related to changes in Chl, which may due for instance to photo acclimation (e.g., [50,51]) or by other components that are not Chl such as suspended particulate matter (SPM) or colored dissolved organic matter (CDOM; [52])
Summary
Phytoplankton—the microalgae that populates the upper sunlit layers of the ocean—fuels the oceanic food web and regulates oceanic and atmospheric carbon dioxide levels through photosynthetic carbon fixation ([1,2]). The unavailability of global scale observations over a continuous time-series longer than two decades led the scientific community to rely on coupled physical–biogeochemical ocean modeling to investigate phytoplankton biomass decadal variability. While models are able to resolve seasonal to interannual biogeochemical variability to an ever-improving degree (e.g., [5,6]), they diverge in reproducing decadal observations, in particular phytoplankton regime shifts [7,8,9]. It is still not possible on a global scale to clearly separate the phytoplankton long-term response to climate change from natural variability
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
