Ocean Science
Ocean Science
OS
Articles | Volume 20, issue 3
Articles | Volume 20, issue 3
https://doi.org/10.5194/os-20-689-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/os-20-689-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 20, issue 3
Research article
 | 
27 May 2024
Research article |  | 27 May 2024

Combining neural networks and data assimilation to enhance the spatial impact of Argo floats in the Copernicus Mediterranean biogeochemical model

Carolina Amadio, Anna Teruzzi, Gloria Pietropolli, Luca Manzoni, Gianluca Coidessa, and Gianpiero Cossarini

Data sets

Mediterranean Quality checked BGC-Argo 2013-2022 dataset C. Amadio et al. https://doi.org/10.5281/zenodo.10391759

Argo float data and metadata from Global Data Assembly Centre (Argo GDAC) Argo https://doi.org/10.17882/42182

Model code and software

ogstm (4.1) Giorgio Bolzon et al. https://doi.org/10.5281/zenodo.8283447

bit.sea (1.7) Giorgio Bolzon et al. https://doi.org/10.5281/zenodo.8283692

BFM (5.0). Paolo Lazzari et al. https://doi.org/10.5281/zenodo.8283629

3DVarBio (3.3) Anna Teruzzi et al. https://doi.org/10.5281/zenodo.8283275

Download
Short summary
Forecasting of marine biogeochemistry can be improved via the assimilation of observations. Floating buoys provide multivariate information about the status of the ocean interior. Information on the ocean interior can be expanded/augmented by machine learning. In this work, we show the enhanced impact of assimilating new in situ variables (oxygen) and reconstructed variables (nitrate) in the operational forecast system (MedBFM) model of the Mediterranean Sea.
Read more
Special issue
Special Issue for the 54th International Liège Colloquium...