Machine Learning Eliminates Reanalysis Warm Bias and Reveals Weaker Winter Surface Cooling Over Arctic Sea Ice
Open Access
- 19 June 2026
- journal article
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 53 (12)
Abstract
The surface energy budget governs Arctic sea‐ice growth/melt, yet observations are sparse, and reanalysis data sets suffer from systematic biases. Here, we train a neural network with observational data to bias‐correct hourly ERA5 fluxes over Arctic ice‐covered regions (≥70°N; sea‐ice concentration >80%) for 1994–2024. Training data cover two full seasonal cycles and different sea‐ice regimes. The neural network reduces RMSE for net shortwave radiation by ∼40%, downward longwave radiation by ∼16% and the total surface energy budget by ∼55%, eliminating the wintertime warm bias of ∼4 K in ERA5. Wintertime surface cooling is reduced by ∼50%, yielding thermodynamic ice‐growth estimates of ∼80–120 cm, consistent with SMOS–CryoSat satellite thickness increases and in contrast to the 150–200 cm growth implied by ERA5. Our bias‐corrected data capture the observed clear/cloudy states of the winter boundary layer and can be used to study Arctic climatology, evaluate climate models and drive sea‐ice‐ocean models.Keywords
All Related Versions
Funding Information
- Global Ocean Monitoring and Observing Program
- Polarforskningssekretariatet (2016.0024)
This publication has 31 references indexed in Scilit:
- The Two Arctic Wintertime Boundary Layer States: Disentangling the Role of Cloud and Wind Regimes in Reanalysis and Observations During MOSAiCAtmospheric Science Letters, 2025
- The ERA5 global reanalysisQuarterly Journal of the Royal Meteorological Society, 2020
- Use and impact of Arctic observations in the ECMWF Numerical Weather Prediction systemQuarterly Journal of the Royal Meteorological Society, 2019
- Atmosphere‐Ice‐Ocean‐Ecosystem Processes in a Thinner Arctic Sea Ice Regime: The Norwegian Young Sea ICE (N‐ICE2015) ExpeditionJournal of Geophysical Research: Oceans, 2018
- Atmospheric components of the surface energy budget over young sea ice: Results from the N‐ICE2015 campaignJournal of Geophysical Research: Atmospheres, 2017
- Meteorological conditions in a thinner Arctic sea ice regime from winter to summer during the Norwegian Young Sea Ice expedition (N‐ICE2015)Journal of Geophysical Research: Atmospheres, 2017
- A comparison of the two Arctic atmospheric winter states observed during N‐ICE2015 and SHEBAJournal of Geophysical Research: Atmospheres, 2017
- Direct determination of the air‐sea CO2 gas transfer velocity in Arctic sea ice regionsGeophysical Research Letters, 2017
- Select strengths and biases of models in representing the Arctic winter boundary layer over sea ice: the Larcform 1 single column model intercomparisonJournal of Advances in Modeling Earth Systems, 2016
- Why is it so difficult to represent stably stratified conditions in numerical weather prediction (NWP) models?Journal of Advances in Modeling Earth Systems, 2013