Show simple item record

dc.contributor.authorFourrier, Marine
dc.contributor.authorCoppola, Laurent
dc.contributor.authorClaustre, Hervé
dc.contributor.authorD’Ortenzio, Fabrizio
dc.contributor.authorSauzède, Raphaëlle
dc.contributor.authorGattuso, Jean-Pierre
dc.coverage.spatialMediterranean Seaen_US
dc.identifier.citationFourrier, M.; Coppola, L.; Claustre, H.; D’Ortenzi, F.; Sauzède, R. and Gattuso, J-.P (2020) A Regional Neural Network Approach to Estimate Water-Column Nutrient Concentrations and Carbonate System Variables in the Mediterranean Sea: CANYON-MED. Frontiers in Marine Science, 7: 620, 20pp. DOI: 10.3389/fmars.2020.00620en_US
dc.description.abstractA regional neural network-based method, “CANYON-MED” is developed to estimate nutrients and carbonate system variables specifically in the Mediterranean Sea over the water column from pressure, temperature, salinity, and oxygen together with geolocation and date of sampling. Six neural network ensembles were developed, one for each variable (i.e., three macronutrients: nitrates (NO−3), phosphates (PO3−4) and silicates (SiOH4), and three carbonate system variables: pH on the total scale (pHT),total alkalinity (AT), and dissolved inorganic carbon or total carbon (CT), trained using a specific quality-controlled dataset of reference “bottle” data in the MediterraneanSea. This dataset is representative of the peculiar conditions of this semi-enclosed sea, as opposed to the global ocean. For each variable, the neural networks were trained on 80% of the data chosen randomly and validated using the remaining 20%.CANYON-MED retrieved the variables with good accuracies (Root Mean Squared Error):0.73μ−1for NO−3, 0.045μ−1for PO3−4and 0.70μ−1for Si(OH)4,0.016 units for pHT, 11μ−1forATand 10μ−1forCT. A second validationon the ANTARES independent time series confirmed the method’s applicability in the Mediterranean Sea. After comparison to other existing methods to estimate nutrients and carbonate system variables, CANYON-MED stood out as the most robust, using the aforementioned inputs. The application of CANYON-MED on the MediterraneanSea data from autonomous observing systems (integrated network of Biogeochemical-Argo floats, Eulerian moorings and ocean gliders measuring hydrological propertiestogether with oxygen concentration) could have a wide range of applications. These include data quality control or filling gaps in time series, as well as biogeochemical data assimilation and/or the initialization and validation of regional biogeochemical models still lacking crucial reference data. Matlab and R code are available at
dc.rightsAttribution 4.0 International*
dc.titleA Regional Neural Network Approach to Estimate Water-Column Nutrient Concentrations and Carbonate System Variables in the Mediterranean Sea: CANYON-MED.en_US
dc.typeJournal Contributionen_US
dc.subject.parameterDisciplineParameter Discipline::Chemical oceanography::Carbonate systemen_US
dc.bibliographicCitation.titleFrontiers in Marine Scienceen_US
dc.bibliographicCitation.issueArticle 620en_US
dc.description.eovInorganic carbonen_US
dc.description.maturitylevelTRL 8 Actual system completed and "mission qualified" through test and demonstration in an operational environment (ground or space)en_US
dc.description.bptypeBest Practiceen_US
dc.description.bptypeManual (incl. handbook, guide, cookbook etc)en_US Fourrier

Files in this item


This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's license is described as Attribution 4.0 International