Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 1
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

On the global reconstruction of ocean interior variables: a feasibility data-driven study with simulated surface and water column observations

  • García Espriu, Aina
  • González-Haro, Cristina
  • Aguilar, Fernando
The Argo profilers dataset (Argo, 2025) from which we derive the observed points are available through the SEANOE webpage (https://doi.org/10.17882/42182) or all the alternative access to data options provided there. Mixed Layer Depth climatology dataset (de Boyer Montégut, 2023) can be downloaded from the Seanoe webpage https://doi.org/10.17882/91774., The code used in this study is publicly available at GitHub (https://github.com/ainagarciaes/SSS-SST-4D-Reconstruction/tree/v1, last access: 15 October 2025) under a GNU General Public License and has been archived on Zenodo (DOI: https://doi.org/10.5281/zenodo.11487678, García-Espriu, 2024)., This work uses data-driven approaches to study the feasibility of reconstructing ocean interior variables (temperature and salinity) from surface observations provided by satellites and interior observations provided by Argo floats. The feasibility of the approach is based on an Observing System Simulation Experiment (OSSE) in which we use the outputs from an ocean numerical model as the ground truth, and simulate a real observing system of the ocean, taking the surface of the model as a simulation of satellite observations, and vertical profiles in the same locations as the real Argo floats. We implemented different models based on Random Forest Regressors and Long-Short Term Memory networks, which were trained with the simulated observations and validated against the complete numerical model results. We obtain high spatial and temporal correlation using both technologies and an accurate description of the annual variability of the data, accompanied by small biases, This work was supported by the Ministerio de Ciencia e Innovación through the EO4TIP project (grant PID2023-149659OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF/EU; the European Maritime, Fisheries and Aquaculture Fund (EMFAF); and the EU HORIZON EUROPE Reforming and enhancing the European Research and Innovation system (grant no. 10105859)., This work also acknowledges the “Severo Ochoa Centre of Excellence” accreditation (grant CEX2019-000928-S), The article processing charges for this open-access publication were covered by the CSIC Open Access Publication Support Initiative through its Unit of Information Resources for Research (URICI)., Peer reviewed