Preprints
https://doi.org/10.5194/gmd-2024-185
https://doi.org/10.5194/gmd-2024-185
Submitted as: development and technical paper
 | 
21 Oct 2024
Submitted as: development and technical paper |  | 21 Oct 2024
Status: this preprint is currently under review for the journal GMD.

Correction of Air-Sea Heat Fluxes in the NEMO Ocean General Circulation Model Using Neural Networks

Andrea Storto, Sergey Frolov, Laura Slivinski, and Chunxue Yang

Abstract. The atmospheric forcing and the heat exchanges between the ocean and the atmosphere represent one of the major sources of uncertainty for numerical ocean reconstructions and predictions. Air-sea heat fluxes may suffer from inaccuracies in meteorological fields, sea surface variables, and bulk formulations, which have a strongly non-linear dependence on the ocean state. Here, state-dependent errors of the heat fluxes are learned by artificial neural networks (ANN) from a dataset of heat flux correction terms, derived in turn from previous sea surface temperature nudging experiments. The pre-trained model predictors include stationary fields, atmospheric forcing data, ocean state, and stratification indices. Variable importance scores emphasize the dependence of the air-sea heat flux errors on the wind forcing. The pre-trained model of heat flux correction is then used to adaptively correct the fluxes online, in a series of global ocean experiments performed with the NEMO (Nucleus for European Modelling of the Ocean) ocean general circulation model, augmented with ANN inference capabilities. Results indicate the positive impact of the correction procedure, beyond the training period, e.g., in independent observation-poor and -rich periods, leading to the same dynamical and subsurface signature as in nudging experiments. Prediction experiments also indicate the method's potential for operational forecast applications. The method may also be adopted in coupled long-term reanalyses, long-range predictions, and projections.

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.
Andrea Storto, Sergey Frolov, Laura Slivinski, and Chunxue Yang

Status: open (until 08 Jan 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2024-185', Anonymous Referee #1, 20 Nov 2024 reply
  • CEC1: 'Comment on gmd-2024-185 - No compliance with the policy of the journal', Juan Antonio Añel, 28 Nov 2024 reply
    • AC1: 'Reply on CEC1', Andrea Storto, 28 Nov 2024 reply
Andrea Storto, Sergey Frolov, Laura Slivinski, and Chunxue Yang

Data sets

Material for the manuscript Andrea Storto https://doi.org/10.5281/zenodo.13380698

Model code and software

NEMO 4.0.7 Andrea Storto https://baltig.cnr.it/nemo_ismar-rm/nemo_4.0.7/-/tree/3.0?ref_type=tags

Andrea Storto, Sergey Frolov, Laura Slivinski, and Chunxue Yang

Viewed

Total article views: 292 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
219 62 11 292 1 2
  • HTML: 219
  • PDF: 62
  • XML: 11
  • Total: 292
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 21 Oct 2024)
Cumulative views and downloads (calculated since 21 Oct 2024)

Viewed (geographical distribution)

Total article views: 281 (including HTML, PDF, and XML) Thereof 281 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 07 Dec 2024
Download
Short summary
Inaccuracies in air-sea heat fluxes severely downgrade the accuracy of ocean numerical simulations. Here, we use artificial neural networks to correct the air-sea heat fluxes as a function of oceanic and atmospheric state predictors. The correction successfully improves surface and subsurface ocean temperatures beyond the training period and in prediction experiments.