DOE OSTI · 3374888
Machine Learning Eliminates Reanalysis Warm Bias and Reveals Weaker Winter Surface Cooling Over Arctic Sea Ice
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.
Keep this discovery
Explore connections, maps & timelines
Hossain, Akil [Alfred Wegener Institute for Polar and Marine Research, Bremerhaven (Germany)] (ORCID:0000000183403056), Keil, Paul [Helmholtz Centre Hereon, Geesthacht (Germany); Helmholtz AI, Munich (Germany); Deutsches Klimarechenzentrum GmbH (DKRZ), Hamburg (Germany)] (ORCID:0000000265024148), Grover, Harsh [Helmholtz Centre Hereon, Geesthacht (Germany); Helmholtz AI, Munich (Germany); Deutsches Klimarechenzentrum GmbH (DKRZ), Hamburg (Germany)], Brooks, Ian M. [University of Leeds (United Kingdom)] (ORCID:0000000250511322), Cox, Christopher J. [National Oceanic and Atmospheric Administration (NOAA), Boulder, CO (United States). NOAA Physical Sciences Laboratory (PSL)] (ORCID:0000000322037173), Gallagher, Michael R. [National Oceanic and Atmospheric Administration (NOAA), Boulder, CO (United States). NOAA Physical Sciences Laboratory (PSL); University of Colorado, Boulder, CO (United States). Cooperative Institute for Research in Environmental Sciences (CIRES)], Granskog, Mats A. [Norwegian Polar Institute (NPI), Tromso (Norway). Fram Centre] (ORCID:0000000250354347), Guy, Heather [University of Leeds (United Kingdom)] (ORCID:0000000335250766), Hudson, Stephen R. [Norwegian Polar Institute (NPI), Tromso (Norway). Fram Centre] (ORCID:0000000264989167), Persson, P. Ola G. [National Oceanic and Atmospheric Administration (NOAA), Boulder, CO (United States). NOAA Physical Sciences Laboratory (PSL); University of Colorado, Boulder, CO (United States). Cooperative Institute for Research in Environmental Sciences (CIRES)], Shupe, Matthew D. [National Oceanic and Atmospheric Administration (NOAA), Boulder, CO (United States). NOAA Physical Sciences Laboratory (PSL); University of Colorado, Boulder, CO (United States). Cooperative Institute for Research in Environmental Sciences (CIRES)] (ORCID:0000000209739982), Tjernström, Michael [Stockholm University (Sweden)] (ORCID:0000000269087410), Vüllers, Jutta [Karlsruhe Institute of Technology (KIT) (Germany)], Walden, Von P. [Washington State University, Pullman, WA (United States)] (ORCID:0000000338574416), Pithan, Felix [Alfred Wegener Institute for Polar and Marine Research, Bremerhaven (Germany); University of Bremen (Germany)] (ORCID:0000000343823077). 2026-06-19. Machine Learning Eliminates Reanalysis Warm Bias and Reveals Weaker Winter Surface Cooling Over Arctic Sea Ice. https://doi.org/10.1029/2025gl121289
Cite the original work for its findings. Save a collection to share your selection of sources.