Preprints
https://doi.org/10.5194/gmd-2022-224
https://doi.org/10.5194/gmd-2022-224
Submitted as: development and technical paper
18 Nov 2022
Submitted as: development and technical paper | 18 Nov 2022
Status: this preprint is currently under review for the journal GMD.

Testing the reconstruction of modelled particulate organic carbon from surface ecosystem components using PlankTOM12 and Machine Learning

Anna Denvil-Sommer1, Erik T. Buitenhuis1, Rainer Kiko2,3, Fabien Lombard2,4, Lionel Guidi2, and Corinne Le Quéré1 Anna Denvil-Sommer et al.
  • 1School of Environmental Science, University of East Anglia, Norwich, UK
  • 2Sorbonne Université, Centre National de la Recherche Scientifique (CNRS), Laboratoire d’Océanographie de Villefranche (LOV), Villefranche-sur-Mer, France
  • 3GEOMAR Helmholtz Center for Ocean Research, Kiel, Germany
  • 4Institut Universitaire de France (IUF), Paris, France

Abstract. Understanding the relationship between surface marine ecosystems and the export of carbon to depth by sinking organic particles is key to represent 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 is 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.

Anna Denvil-Sommer et al.

Status: open (until 13 Jan 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2022-224', Anonymous Referee #1, 06 Dec 2022 reply

Anna Denvil-Sommer et al.

Anna Denvil-Sommer et al.

Viewed

Total article views: 186 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
149 33 4 186 3 2
  • HTML: 149
  • PDF: 33
  • XML: 4
  • Total: 186
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 18 Nov 2022)
Cumulative views and downloads (calculated since 18 Nov 2022)

Viewed (geographical distribution)

Total article views: 180 (including HTML, PDF, and XML) Thereof 180 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Dec 2022
Download
Short summary
Using outputs of global biogeochemical ocean model and Machine Learning methods we demonstrate that it will be possible to identify linkages between surface environmental and ecosystem structure and the export of carbon to depth by sinking organic particles using real observations. It will be possible to use this knowledge to improve both our understanding of ecosystem dynamics and of their functional representation within models.