Preprints
https://doi.org/10.5194/egusphere-2025-705
https://doi.org/10.5194/egusphere-2025-705
24 Feb 2025
 | 24 Feb 2025

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

Aina García-Espriu, Cristina González-Haro, and Fernando Aguilar-Gómez

Abstract. 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 buoys. 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 buoys. 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.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Share
Aina García-Espriu, Cristina González-Haro, and Fernando Aguilar-Gómez

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2025-705', Anonymous Referee #1, 05 Apr 2025
  • RC2: 'Comment on egusphere-2025-705', Anonymous Referee #2, 17 Apr 2025
Aina García-Espriu, Cristina González-Haro, and Fernando Aguilar-Gómez
Aina García-Espriu, Cristina González-Haro, and Fernando Aguilar-Gómez

Viewed

Total article views: 229 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
176 42 11 229 12 26
  • HTML: 176
  • PDF: 42
  • XML: 11
  • Total: 229
  • BibTeX: 12
  • EndNote: 26
Views and downloads (calculated since 24 Feb 2025)
Cumulative views and downloads (calculated since 24 Feb 2025)

Viewed (geographical distribution)

Total article views: 233 (including HTML, PDF, and XML) Thereof 233 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 19 Jul 2025
Download
Short summary
Ocean measurements currently rely on buoys for depth data and satellites for surface observations. We investigated combining these using data-driven approaches to reconstruct full 4D ocean profiles. Using an ocean model as ground truth, we simulated satellite surface data and ARGO profiles and then applied machine learning to predict complete temperature and salinity profiles. Results showed accurate predictions that matched simulation data and captured seasonal patterns.
Share