FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366579056> ?p ?o ?g. }

• W4366579056 abstract "<strong class=journal-contentHeaderColor>Abstract.</strong> 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 (POC<span class=inline-formula>_S</span>) and large (POC<span class=inline-formula>_L</span>) 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 POC<span class=inline-formula>_S</span> and by 22 % for POC<span class=inline-formula>_L</span>. Results were less robust over the equatorial Pacific and some parts of the high latitudes. For POC<span class=inline-formula>_S</span> reconstruction, the most important drivers were the depth level, temperature, microzooplankton and PO<span class=inline-formula>₄</span>, while for POC<span class=inline-formula>_L</span> it was the depth level, temperature, mixed-layer depth, microzooplankton, phaeocystis, PO<span class=inline-formula>₄</span> and chlorophyll <span class=inline-formula><i>a</i></span> 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." @default.
• W4366579056 created "2023-04-23" @default.
• W4366579056 creator A5090386033 @default.
• W4366579056 date "2023-04-19" @default.
• W4366579056 modified "2023-09-29" @default.
• W4366579056 title "Reply on RC2" @default.
• W4366579056 doi "https://doi.org/10.5194/gmd-2022-224-ac2" @default.
• W4366579056 hasPublicationYear "2023" @default.
• W4366579056 type Work @default.
• W4366579056 citedByCount "0" @default.
• W4366579056 crossrefType "peer-review" @default.
• W4366579056 hasAuthorship W4366579056A5090386033 @default.
• W4366579056 hasBestOaLocation W43665790561 @default.
• W4366579056 hasConcept C108469399 @default.
• W4366579056 hasConcept C110872660 @default.
• W4366579056 hasConcept C119857082 @default.
• W4366579056 hasConcept C127313418 @default.
• W4366579056 hasConcept C127413603 @default.
• W4366579056 hasConcept C142796444 @default.
• W4366579056 hasConcept C146978453 @default.
• W4366579056 hasConcept C158787203 @default.
• W4366579056 hasConcept C169258074 @default.
• W4366579056 hasConcept C18903297 @default.
• W4366579056 hasConcept C19269812 @default.
• W4366579056 hasConcept C24245907 @default.
• W4366579056 hasConcept C2776939893 @default.
• W4366579056 hasConcept C2780892065 @default.
• W4366579056 hasConcept C2993636123 @default.
• W4366579056 hasConcept C39432304 @default.
• W4366579056 hasConcept C41008148 @default.
• W4366579056 hasConcept C6939412 @default.
• W4366579056 hasConcept C71915725 @default.
• W4366579056 hasConcept C86803240 @default.
• W4366579056 hasConcept C91586092 @default.
• W4366579056 hasConceptScore W4366579056C108469399 @default.
• W4366579056 hasConceptScore W4366579056C110872660 @default.
• W4366579056 hasConceptScore W4366579056C119857082 @default.
• W4366579056 hasConceptScore W4366579056C127313418 @default.
• W4366579056 hasConceptScore W4366579056C127413603 @default.
• W4366579056 hasConceptScore W4366579056C142796444 @default.
• W4366579056 hasConceptScore W4366579056C146978453 @default.
• W4366579056 hasConceptScore W4366579056C158787203 @default.
• W4366579056 hasConceptScore W4366579056C169258074 @default.
• W4366579056 hasConceptScore W4366579056C18903297 @default.
• W4366579056 hasConceptScore W4366579056C19269812 @default.
• W4366579056 hasConceptScore W4366579056C24245907 @default.
• W4366579056 hasConceptScore W4366579056C2776939893 @default.
• W4366579056 hasConceptScore W4366579056C2780892065 @default.
• W4366579056 hasConceptScore W4366579056C2993636123 @default.
• W4366579056 hasConceptScore W4366579056C39432304 @default.
• W4366579056 hasConceptScore W4366579056C41008148 @default.
• W4366579056 hasConceptScore W4366579056C6939412 @default.
• W4366579056 hasConceptScore W4366579056C71915725 @default.
• W4366579056 hasConceptScore W4366579056C86803240 @default.
• W4366579056 hasConceptScore W4366579056C91586092 @default.
• W4366579056 hasLocation W43665790561 @default.
• W4366579056 hasOpenAccess W4366579056 @default.
• W4366579056 hasPrimaryLocation W43665790561 @default.
• W4366579056 hasRelatedWork W1668895673 @default.
• W4366579056 hasRelatedWork W2047281433 @default.
• W4366579056 hasRelatedWork W2133398059 @default.
• W4366579056 hasRelatedWork W2370229557 @default.
• W4366579056 hasRelatedWork W2807127889 @default.
• W4366579056 hasRelatedWork W3149493843 @default.
• W4366579056 hasRelatedWork W3150541146 @default.
• W4366579056 hasRelatedWork W3187877654 @default.
• W4366579056 hasRelatedWork W4284879993 @default.
• W4366579056 hasRelatedWork W4297182566 @default.
• W4366579056 isParatext "false" @default.
• W4366579056 isRetracted "false" @default.
• W4366579056 workType "peer-review" @default.