Articles | Volume 18, issue 15
https://doi.org/10.5194/gmd-18-4789-2025
https://doi.org/10.5194/gmd-18-4789-2025
Development and technical paper
 | 
04 Aug 2025
Development and technical paper |  | 04 Aug 2025

Correction of sea surface biases in the NEMO ocean general circulation model using neural networks

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

Data sets

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

ERA5 hourly data on single levels from 1940 to present H. Hersbach et al. https://doi.org/10.24381/cds.adbb2d47

Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century (https://www.metoffice.gov.uk/hadobs/hadisst) N. A. Rayner et al. https://doi.org/10.1029/2002JD002670

Improvements of the Daily Optimum Interpolation Sea Surface Temperature (DOISST) Version 2.1 (https://psl.noaa.gov/data/gridded/data.noaa.oisst.v2.highres.html) B. Huang et al. https://doi.org/10.1175/JCLI-D-20-0166.1

EN4: Quality controlled ocean temperature and salinity profiles and monthly objective analyses with uncertainty estimates (https://www.metoffice.gov.uk/hadobs/en4/download-en4-2-2.html) S. A. Good et al. https://doi.org/10.1002/2013JC009067

Download
Short summary

Inaccuracies in air–sea heat fluxes severely degrade the accuracy of ocean numerical simulations. Here, we use artificial neural networks to correct 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.

Share