Testing the reconstruction of modelled particulate organic carbon from surface ecosystem components using PlankTOM12 and Machine Learning
| Type | : | ACL |
|---|---|---|
| Nature | : | Production scientifique |
| Au bénéfice du Laboratoire | : | Oui |
| Statut de publication | : | En révision |
| Année de publication | : | 2022 |
| Auteurs (6) | : | DENVIL-SOMMER A BUITENHUIS E,t KIKO Rainer LOMBARD Fabien GUIDI Lionel LE QUÉRÉ C |
| Revue scientifique | : | Geoscientific Model Development Discussions |
| Volume | : | 2022 |
| Fascicule | : | |
| Pages | : | |
| DOI | : | 10.5194/gmd-2022-224 |
| URL | : | https://gmd.copernicus.org/preprints/gmd-2022-224/ |
| 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. |
| Mots-clés | : | - |
| Commentaire | : | - |
| Tags | : | - |
| Fichier attaché | : | - |
| Citation | : |
Denvil-Sommer A, Buitenhuis ET, Kiko R, Lombard F, Guidi L, Le Quéré C (2022) Testing the reconstruction of modelled particulate organic carbon from surface ecosystem components using PlankTOM12 and Machine Learning. Geosci Model Dev Discuss 2022 | doi: 10.5194/gmd-2022-224
|