Testing the reconstruction of modelled particulate organic carbon from surface ecosystem components using PlankTOM12 and machine learning

• Published in: Geoscientific Model Development 2023-05, Vol.16 (10), p.2995-3012
• Main Authors: Denvil-Sommer, Anna, Buitenhuis, Erik T, Kiko, Rainer, Lombard, Fabien, Guidi, Lionel, Le Quéré, Corinne
• Format: Article
• Language: English
• Subjects: Analysis; Biogeochemistry; Biomass; Carbon; Carbon content; Carbon cycle; Carbon cycle (Biogeochemistry); Chlorophyll; Chlorophyll a; Climate models; Dynamics; Ecosystem components; Ecosystem dynamics; Ecosystem structure; Ecosystems; Environmental aspects; Hypotheses; Learning algorithms; Machine learning; Marine ecosystems; Mixed layer depth; Model accuracy; Model testing; Modelling; Oceans; Organic carbon; Particle size; Particulate organic carbon; Plankton; Reconstruction; Synthetic data; Temperature; Zooplankton
• ISSN: 1991-9603; 1991-959X; 1991-962X; 1991-9603; 1991-962X
• DOI: 10.5194/gmd-16-2995-2023

Understanding the relationship between surface marine ecosystems and the export of carbon to depth by sinking organic particles is key to representing the effect of ecosystem dynamics and diversity, and their evolution under multiple stressors, on the carbon cycle and climate in models. Recent observational technologies have greatly increased the amount of data available, both for the abundance of diverse plankton groups and for the concentration and properties of particulate organic carbon in the ocean interior. Here we use synthetic model data to test the potential of using machine learning (ML) to reproduce concentrations of particulate organic carbon within the ocean interior based on surface ecosystem and environmental data. We test two machine learning methods that differ in their approaches to data-fitting, the random forest and XGBoost methods. The synthetic data are sampled from the PlankTOM12 global biogeochemical model using the time and coordinates of existing observations. We test 27 different combinations of possible drivers to reconstruct small (POCS) and large (POCL) particulate organic carbon concentrations. We show that ML can successfully be used to reproduce modelled particulate organic carbon over most of the ocean based on ecosystem and modelled environmental drivers. XGBoost showed better results compared to random forest thanks to its gradient boosting trees' architecture. The inclusion of plankton functional types (PFTs) in driver sets improved the accuracy of the model reconstruction by 58 % on average for POCS and by 22 % for POCL. Results were less robust over the equatorial Pacific and some parts of the high latitudes. For POCS reconstruction, the most important drivers were the depth level, temperature, microzooplankton and PO4, while for POCL it was the depth level, temperature, mixed-layer depth, microzooplankton, phaeocystis, PO4 and chlorophyll a averaged over the mixed-layer depth. These results suggest that it will be possible to identify linkages between surface environmental and ecosystem structure and particulate organic carbon distribution within the ocean interior using real observations and to use this knowledge to improve both our understanding of ecosystem dynamics and of their functional representation within models.