Articles | Volume 20, issue 3
https://doi.org/10.5194/tc-20-1841-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-20-1841-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
30 Mar 2026
Research article |
| 30 Mar 2026
| 30 Mar 2026
Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperature
Nils Bochow
CORRESPONDING AUTHOR
Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research, Potsdam, Germany
Potsdam Institute for Climate Impact Research, Potsdam, Germany
Department of Mathematics and Statistics, Faculty of Science and Technology, UiT The Arctic University of Norway, Tromsø, Norway
Philipp Hess
Potsdam Institute for Climate Impact Research, Potsdam, Germany
Munich Climate Center and Earth System Modelling Group, Department of Aerospace and Geodesy, TUM School of Engineering and Design, Technical University of Munich, Munich, Germany
Alexander Robinson
Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research, Potsdam, Germany
Related authors
Nils Bochow, Jonathan Krönke, Julius Garbe, and Nico Wunderling
EGUsphere, https://doi.org/10.5194/egusphere-2026-614, https://doi.org/10.5194/egusphere-2026-614, 2026
Short summary
Short summary
We provide a simple, updateable tool that turns comprehensive simulations into fast dynamical models for the three major tipping elements; the Greenland Ice Sheet, the West Antarctic Ice Sheet, and the Atlantic Meridional Overturning circulation. By fitting our framework to existing comprehensive simulations, it matches both short-term change and long-term stable states. This helps produce more consistent, policy-ready risk estimates as new simulations arrive.
Anna Poltronieri, Nils Bochow, and Martin Rypdal
EGUsphere, https://doi.org/10.5194/egusphere-2025-1134, https://doi.org/10.5194/egusphere-2025-1134, 2025
Preprint archived
Short summary
Short summary
As Arctic sea ice shrinks, new shipping routes become more accessible. This study compares the effects of two main Arctic pathways: the Northern and the Transpolar Sea routes. Using a high-complexity climate model, we simulate black carbon emissions from ships. When deposited on sea ice, black carbon increases solar absorption, enhancing melt. We analyze absorbed solar radiation, sea ice extent, and air temperature, finding that the Transpolar Sea Route has a greater effect on Arctic sea ice.
Nils Bochow, Anna Poltronieri, and Niklas Boers
The Cryosphere, 18, 5825–5863, https://doi.org/10.5194/tc-18-5825-2024, https://doi.org/10.5194/tc-18-5825-2024, 2024
Short summary
Short summary
Using the latest climate models, we update the understanding of how the Greenland ice sheet responds to climate changes. We found that precipitation and temperature changes in Greenland vary across different regions. Our findings suggest that using uniform estimates for temperature and precipitation for modelling the response of the ice sheet can overestimate ice loss in Greenland. Therefore, this study highlights the need for spatially resolved data in predicting the ice sheet's future.
Sergio Pérez-Montero, Jorge Alvarez-Solas, Jan Swierczek-Jereczek, Daniel Moreno-Parada, Alexander Robinson, and Marisa Montoya
Clim. Past, 22, 625–646, https://doi.org/10.5194/cp-22-625-2026, https://doi.org/10.5194/cp-22-625-2026, 2026
Short summary
Short summary
Almost 3 million years ago, the planet began to experience a succession of cold and warm periods every 40,000 years. However, about 1 million years ago, they began to occur every 100,000 years. In this paper we explore how the change in the basal velocity of the ice sheets could have produced this change in behavior. On the other hand, we also see that in our model, decreasing in time the sensitivity of snowfall to temperature is also an effective mechanism with which to reproduce the records.
Antonio Juarez-Martinez, Alexander Robinson, Jan Swierczek-Jereczek, Javier Blasco, Jorge Alvarez-Solas, and Marisa Montoya
EGUsphere, https://doi.org/10.5194/egusphere-2026-248, https://doi.org/10.5194/egusphere-2026-248, 2026
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Short summary
Tidal-water intrusions can cause warm ocean water to extend beneath grounded Antarctic ice, increasing submarine melting beyond the grounding line. Here, a new parameterization representing this effect is introduced and tested in the Yelmo ice-sheet model, revealing that tides could amplify ice loss and sea-level rise. This new parameterization shows good agreement with inferred grounding zones.
Michael Aich, Philipp Hess, Baoxiang Pan, Sebastian Bathiany, Yu Huang, and Niklas Boers
Geosci. Model Dev., 19, 1791–1808, https://doi.org/10.5194/gmd-19-1791-2026, https://doi.org/10.5194/gmd-19-1791-2026, 2026
Short summary
Short summary
Accurately simulating rainfall is essential to understand the impacts of climate change, especially extreme events such as floods and droughts. Climate models simulate the atmosphere at a coarse resolution and often misrepresent precipitation, leading to biased and overly smooth fields. We improve the precipitation using a machine learning model that is data-efficient, preserves key climate signals such as trends and variability, and significantly improves the representation of extreme events.
Nils Bochow, Jonathan Krönke, Julius Garbe, and Nico Wunderling
EGUsphere, https://doi.org/10.5194/egusphere-2026-614, https://doi.org/10.5194/egusphere-2026-614, 2026
Short summary
Short summary
We provide a simple, updateable tool that turns comprehensive simulations into fast dynamical models for the three major tipping elements; the Greenland Ice Sheet, the West Antarctic Ice Sheet, and the Atlantic Meridional Overturning circulation. By fitting our framework to existing comprehensive simulations, it matches both short-term change and long-term stable states. This helps produce more consistent, policy-ready risk estimates as new simulations arrive.
Lucía Gutiérrez-González, Alexander Robinson, Jorge Alvarez-Solas, Ilaria Tabone, Jan Swierczek-Jereczek, Daniel Moreno-Parada, and Marisa Montoya
The Cryosphere, 20, 1139–1162, https://doi.org/10.5194/tc-20-1139-2026, https://doi.org/10.5194/tc-20-1139-2026, 2026
Short summary
Short summary
The Greenland ice sheet is considered a tipping element: if temperatures exceed its threshold, it would transition to a virtually ice-free state and the ice losses could be irreversible on very long timescales. We study its stability across the full range of glacial-interglacial temperatures, as well as those expected in coming centuries. We find a future critical threshold between 1.5-2ºC of global warming, another under colder climates, and persistent hysteresis across the full range of study.
Jan Swierczek-Jereczek, Jorge Alvarez-Solas, Alexander Robinson, Lucía Gutiérrez-González, and Marisa Montoya
EGUsphere, https://doi.org/10.5194/egusphere-2025-6566, https://doi.org/10.5194/egusphere-2025-6566, 2026
Short summary
Short summary
The Antarctic Ice Sheet is subject to hysteresis, i.e. if ice is lost due to warming, a comparatively larger cooling is needed to recover the original state. Here, we show that this effect might be larger than previously assumed, with volume differences of as much as 35 metres of sea-level equivalent between retreat and regrowth. Due to the large population density along the coasts, this stresses the importance of mitigating future sea-level rise, since adapting to it will likely be much harder.
Johanna Beckmann, Ronja Reese, Felicity S. McCormack, Sue Cook, Lawrence Bird, Dawid Gwyther, Daniel Richards, Matthias Scheiter, Yu Wang, Hélène Seroussi, Ayako Abe‐Ouchi, Torsten Albrecht, Jorge Alvarez‐Solas, Xylar S. Asay‐Davis, Jean‐Baptiste Barre, Constantijn J. Berends, Jorge Bernales, Javier Blasco, Justine Caillet, David M. Chandler, Violaine Coulon, Richard Cullather, Christophe Dumas, Benjamin K. Galton‐Fenzi, Julius Garbe, Fabien Gillet‐Chaulet, Rupert Gladstone, Heiko Goelzer, Nicholas R. Golledge, Ralf Greve, G. Hilmar Gudmundsson, Holly Kyeore Han, Trevor R. Hillebrand, Matthew J. Hoffman, Philippe Huybrechts, Nicolas C. Jourdain, Ann Kristin Klose, Petra M. Langebroek, Gunter R. Leguy, William H. Lipscomb, Daniel P. Lowry, Pierre Mathiot, Marisa Montoya, Mathieu Morlighem, Sophie Nowicki, Frank Pattyn, Antony J. Payne, Tyler Pelle, Aurélien Quiquet, Alexander Robinson, Leopekka Saraste, Erika G. Simon, Sainan Sun, Jake P. Twarog, Luke D. Trusel, Benoit Urruty, Jonas Van Breedam, Roderik S. W. van de Wal, Chen Zhao, and Thomas Zwinger
EGUsphere, https://doi.org/10.5194/egusphere-2025-4069, https://doi.org/10.5194/egusphere-2025-4069, 2025
Short summary
Short summary
Antarctica holds enough ice to raise sea levels by many meters, but its future is uncertain. Warm ocean water melts ice shelves from below, letting inland ice flow faster into the sea. By 2300, Antarctica could add 0.6–4.4 m to sea levels. Our study identifies two key factors—how strongly shelves melt and how the ice responds. These explain much of the range, and refining them in models may improve future predictions.
Kolja Kypke, Marisa Montoya, Alexander Robinson, Jorge Alvarez-Solas, Jan Swierczek-Jereczek, and Peter Ditlevsen
EGUsphere, https://doi.org/10.5194/egusphere-2025-4116, https://doi.org/10.5194/egusphere-2025-4116, 2025
Short summary
Short summary
Using a state-of-the-art ice sheet model, simulations of the future evolution of the Greenland ice sheet under moderate warming display chaotic variability, with the resulting large-scale loss of the ice sheet (also known as ’tipping’) being delayed by hundreds of thousands of years in some instances. The source of this variability is two nearby ice streams which oscillate in a build-up and surge pattern. This is the first study of such chaos in the Greenland ice sheet.
Daniel Moreno-Parada, Alexander Robinson, Marisa Montoya, and Jorge Alvarez-Solas
Geosci. Model Dev., 18, 3895–3919, https://doi.org/10.5194/gmd-18-3895-2025, https://doi.org/10.5194/gmd-18-3895-2025, 2025
Short summary
Short summary
We introduce Nix, an ice-sheet model designed for understanding how large masses of ice behave. Nix is a computer programme that simulates the movement and temperature evolution in ice sheets. It helps us study how ice sheets respond to changes in the atmosphere and ocean. We found that ice temperatures play an essential role in determining the motion and stability of ice sheets. Nix is a useful tool for learning how climate change affects polar ice sheets.
Sergio Pérez-Montero, Jorge Alvarez-Solas, Jan Swierczek-Jereczek, Daniel Moreno-Parada, Alexander Robinson, and Marisa Montoya
Earth Syst. Dynam., 16, 915–937, https://doi.org/10.5194/esd-16-915-2025, https://doi.org/10.5194/esd-16-915-2025, 2025
Short summary
Short summary
The climate of the last 3 Myr has varied between cold and warm periods. Numerous independent mechanisms have been proposed to explain this; however, no effort has been made to study their competing effects. Here we present a simple but physically motivated model that includes these mechanisms in a modular way. We identify ice-sheet dynamics and lithosphere displacement as main triggers, but reproducing the climate records additionally requires the natural darkening of ice.
Ricarda Winkelmann, Donovan P. Dennis, Jonathan F. Donges, Sina Loriani, Ann Kristin Klose, Jesse F. Abrams, Jorge Alvarez-Solas, Torsten Albrecht, David Armstrong McKay, Sebastian Bathiany, Javier Blasco Navarro, Victor Brovkin, Eleanor Burke, Gokhan Danabasoglu, Reik V. Donner, Markus Drüke, Goran Georgievski, Heiko Goelzer, Anna B. Harper, Gabriele Hegerl, Marina Hirota, Aixue Hu, Laura C. Jackson, Colin Jones, Hyungjun Kim, Torben Koenigk, Peter Lawrence, Timothy M. Lenton, Hannah Liddy, José Licón-Saláiz, Maxence Menthon, Marisa Montoya, Jan Nitzbon, Sophie Nowicki, Bette Otto-Bliesner, Francesco Pausata, Stefan Rahmstorf, Karoline Ramin, Alexander Robinson, Johan Rockström, Anastasia Romanou, Boris Sakschewski, Christina Schädel, Steven Sherwood, Robin S. Smith, Norman J. Steinert, Didier Swingedouw, Matteo Willeit, Wilbert Weijer, Richard Wood, Klaus Wyser, and Shuting Yang
EGUsphere, https://doi.org/10.5194/egusphere-2025-1899, https://doi.org/10.5194/egusphere-2025-1899, 2025
Short summary
Short summary
The Tipping Points Modelling Intercomparison Project (TIPMIP) is an international collaborative effort to systematically assess tipping point risks in the Earth system using state-of-the-art coupled and stand-alone domain models. TIPMIP will provide a first global atlas of potential tipping dynamics, respective critical thresholds and key uncertainties, generating an important building block towards a comprehensive scientific basis for policy- and decision-making.
Anna Poltronieri, Nils Bochow, and Martin Rypdal
EGUsphere, https://doi.org/10.5194/egusphere-2025-1134, https://doi.org/10.5194/egusphere-2025-1134, 2025
Preprint archived
Short summary
Short summary
As Arctic sea ice shrinks, new shipping routes become more accessible. This study compares the effects of two main Arctic pathways: the Northern and the Transpolar Sea routes. Using a high-complexity climate model, we simulate black carbon emissions from ships. When deposited on sea ice, black carbon increases solar absorption, enhancing melt. We analyze absorbed solar radiation, sea ice extent, and air temperature, finding that the Transpolar Sea Route has a greater effect on Arctic sea ice.
Nils Bochow, Anna Poltronieri, and Niklas Boers
The Cryosphere, 18, 5825–5863, https://doi.org/10.5194/tc-18-5825-2024, https://doi.org/10.5194/tc-18-5825-2024, 2024
Short summary
Short summary
Using the latest climate models, we update the understanding of how the Greenland ice sheet responds to climate changes. We found that precipitation and temperature changes in Greenland vary across different regions. Our findings suggest that using uniform estimates for temperature and precipitation for modelling the response of the ice sheet can overestimate ice loss in Greenland. Therefore, this study highlights the need for spatially resolved data in predicting the ice sheet's future.
Therese Rieckh, Andreas Born, Alexander Robinson, Robert Law, and Gerrit Gülle
Geosci. Model Dev., 17, 6987–7000, https://doi.org/10.5194/gmd-17-6987-2024, https://doi.org/10.5194/gmd-17-6987-2024, 2024
Short summary
Short summary
We present the open-source model ELSA, which simulates the internal age structure of large ice sheets. It creates layers of snow accumulation at fixed times during the simulation, which are used to model the internal stratification of the ice sheet. Together with reconstructed isochrones from radiostratigraphy data, ELSA can be used to assess ice sheet models and to improve their parameterization. ELSA can be used coupled to an ice sheet model or forced with its output.
Antonio Juarez-Martinez, Javier Blasco, Alexander Robinson, Marisa Montoya, and Jorge Alvarez-Solas
The Cryosphere, 18, 4257–4283, https://doi.org/10.5194/tc-18-4257-2024, https://doi.org/10.5194/tc-18-4257-2024, 2024
Short summary
Short summary
We present sea level projections for Antarctica in the context of ISMIP6-2300 with several forcings but extend the simulations to 2500, showing that more than 3 m of sea level contribution could be reached. We also test the sensitivity on a basal melting parameter and determine the timing of the loss of ice in the west region. All the simulations were carried out with the ice sheet model Yelmo.
Daniel Moreno-Parada, Alexander Robinson, Marisa Montoya, and Jorge Alvarez-Solas
The Cryosphere, 18, 4215–4232, https://doi.org/10.5194/tc-18-4215-2024, https://doi.org/10.5194/tc-18-4215-2024, 2024
Short summary
Short summary
Our study tries to understand how the ice temperature evolves in a large mass as in the case of Antarctica. We found a relation that tells us the ice temperature at any point. These results are important because they also determine how the ice moves. In general, ice moves due to slow deformation (as if pouring honey from a jar). Nevertheless, in some regions the ice base warms enough and melts. The liquid water then serves as lubricant and the ice slides and its velocity increases rapidly.
Javier Blasco, Ilaria Tabone, Daniel Moreno-Parada, Alexander Robinson, Jorge Alvarez-Solas, Frank Pattyn, and Marisa Montoya
Clim. Past, 20, 1919–1938, https://doi.org/10.5194/cp-20-1919-2024, https://doi.org/10.5194/cp-20-1919-2024, 2024
Short summary
Short summary
In this study, we assess Antarctic tipping points which may had been crossed during the mid-Pliocene Warm Period. For this, we use data from the PlioMIP2 ensemble. Additionally, we investigate various sources of uncertainty, like ice dynamics and bedrock configuration. Our research significantly enhances our comprehension of Antarctica's response to a warming climate, shedding light on potential future tipping points that may be surpassed.
Jan Swierczek-Jereczek, Marisa Montoya, Konstantin Latychev, Alexander Robinson, Jorge Alvarez-Solas, and Jerry Mitrovica
Geosci. Model Dev., 17, 5263–5290, https://doi.org/10.5194/gmd-17-5263-2024, https://doi.org/10.5194/gmd-17-5263-2024, 2024
Short summary
Short summary
Ice sheets present a thickness of a few kilometres, leading to a vertical deformation of the crust of up to a kilometre. This process depends on properties of the solid Earth, which can be regionally very different. We propose a model that accounts for this often-ignored heterogeneity and run 100 000 simulation years in minutes. Thus, the evolution of ice sheets is modeled with better accuracy, which is critical for a good mitigation of climate change and, in particular, sea-level rise.
Daniel Moreno-Parada, Jorge Alvarez-Solas, Javier Blasco, Marisa Montoya, and Alexander Robinson
The Cryosphere, 17, 2139–2156, https://doi.org/10.5194/tc-17-2139-2023, https://doi.org/10.5194/tc-17-2139-2023, 2023
Short summary
Short summary
We have reconstructed the Laurentide Ice Sheet, located in North America during the Last Glacial Maximum (21 000 years ago). The absence of direct measurements raises a number of uncertainties. Here we study the impact of different physical laws that describe the friction as the ice slides over its base. We found that the Laurentide Ice Sheet is closest to prior reconstructions when the basal friction takes into account whether the base is frozen or thawed during its motion.
Matteo Willeit, Andrey Ganopolski, Alexander Robinson, and Neil R. Edwards
Geosci. Model Dev., 15, 5905–5948, https://doi.org/10.5194/gmd-15-5905-2022, https://doi.org/10.5194/gmd-15-5905-2022, 2022
Short summary
Short summary
In this paper we present the climate component of the newly developed fast Earth system model CLIMBER-X. It has a horizontal resolution of 5°x5° and is designed to simulate the evolution of the Earth system on temporal scales ranging from decades to >100 000 years. CLIMBER-X is available as open-source code and is expected to be a useful tool for studying past climate changes and for the investigation of the long-term future evolution of the climate.
Alexander Robinson, Daniel Goldberg, and William H. Lipscomb
The Cryosphere, 16, 689–709, https://doi.org/10.5194/tc-16-689-2022, https://doi.org/10.5194/tc-16-689-2022, 2022
Short summary
Short summary
Here we investigate the numerical stability of several commonly used methods in order to determine which of them are capable of resolving the complex physics of the ice flow and are also computationally efficient. We find that the so-called DIVA solver outperforms the others. Its representation of the physics is consistent with more complex methods, while it remains computationally efficient at high resolution.
Andreas Born and Alexander Robinson
The Cryosphere, 15, 4539–4556, https://doi.org/10.5194/tc-15-4539-2021, https://doi.org/10.5194/tc-15-4539-2021, 2021
Short summary
Short summary
Ice penetrating radar reflections from the Greenland ice sheet are the best available record of past accumulation and how these layers have been deformed over time by the flow of ice. Direct simulations of this archive hold great promise for improving our models and for uncovering details of ice sheet dynamics that neither models nor data could achieve alone. We present the first three-dimensional ice sheet model that explicitly simulates individual layers of accumulation and how they deform.
Cited articles
Aich, M., Hess, P., Pan, B., Bathiany, S., Huang, Y., and Boers, N.: Conditional diffusion models for downscaling & bias correction of Earth system model precipitation, arXiv [preprint], https://doi.org/10.48550/arXiv.2404.14416, 2024. a
Aich, M., Bathiany, S., Hess, P., Huang, Y., and Boers, N.: Diffusion models for probabilistic precipitation generation from atmospheric variables, arXiv [preprint], https://doi.org/10.48550/arXiv.2504.00307, 2025. a
Arjovsky, M. and Bottou, L.: Towards Principled Methods for Training Generative Adversarial Networks, arXiv [preprint], https://doi.org/10.48550/arXiv.1701.04862, 2017. a
Aschwanden, A., Fahnestock, M. A., Truffer, M., Brinkerhoff, D. J., Hock, R., Khroulev, C., Mottram, R., and Khan, S. A.: Contribution of the Greenland Ice Sheet to sea level over the next millennium, Science Advances, 5, eaav9396, https://doi.org/10.1126/sciadv.aav9396, 2019. a
Beckmann, J. and Winkelmann, R.: Effects of extreme melt events on ice flow and sea level rise of the Greenland Ice Sheet, The Cryosphere, 17, 3083–3099, https://doi.org/10.5194/tc-17-3083-2023, 2023. a
Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., and Tian, Q.: Accurate medium-range global weather forecasting with 3D neural networks, Nature, 619, 533–538, https://doi.org/10.1038/s41586-023-06185-3, 2023. a
Bischoff, T. and Deck, K.: Unpaired Downscaling of Fluid Flows with Diffusion Bridges, Artificial Intelligence for the Earth Systems, 3, https://doi.org/10.1175/AIES-D-23-0039.1, 2024. a
Bochow, N. and Hess, P.: NilsBochow/greenland_downscaling: GrIS_downscaling (v1.0), Zenodo [code], https://doi.org/10.5281/zenodo.19220315, 2026. a
Bochow, N., Poltronieri, A., Robinson, A., Montoya, M., Rypdal, M., and Boers, N.: Overshooting the critical threshold for the Greenland ice sheet, Nature, 622, 528–536, https://doi.org/10.1038/s41586-023-06503-9, 2023. a
Bochow, N., Poltronieri, A., and Boers, N.: Projections of precipitation and temperatures in Greenland and the impact of spatially uniform anomalies on the evolution of the ice sheet, The Cryosphere, 18, 5825–5863, https://doi.org/10.5194/tc-18-5825-2024, 2024. a
Bochow, N., Poltronieri, A., Rypdal, M., and Boers, N.: Reconstructing historical climate fields with deep learning, Science Advances, 11, eadp0558, https://doi.org/10.1126/sciadv.adp0558, 2025. a
Bochow, N., Robinson, A., and Hess, P.: Supplementary Data: Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperature, Zenodo [data set], https://doi.org/10.5281/zenodo.18241574, 2026. a
Bolibar, J., Rabatel, A., Gouttevin, I., Galiez, C., Condom, T., and Sauquet, E.: Deep learning applied to glacier evolution modelling, The Cryosphere, 14, 565–584, https://doi.org/10.5194/tc-14-565-2020, 2020. a
Bourgault, P., Huard, D., Smith, T. J., Logan, T., Aoun, A., Lavoie, J., Dupuis, E., Rondeau-Genesse, G., Alegre, R., Barnes, C., Laperrière, A. B., Biner, S., Caron, D., Ehbrecht, C., Fyke, J., Keel, T., Labonté, M.-P., Lierhammer, L., Low, J.-F., Quinn, J., Roy, P., Squire, D., Stephens, A., Tanguy, M., and Whelan, C.: xclim: xarray-based climate data analytics, Journal of Open Source Software, 8, 5415, https://doi.org/10.21105/joss.05415, 2023. a
Calov, R. and Greve, R.: A semi-analytical solution for the positive degree-day model with stochastic temperature variations, J. Glaciol., 51, 173–175, https://doi.org/10.3189/172756505781829601, 2005. a
Cannon, A. J., Sobie, S. R., and Murdock, T. Q.: Bias Correction of GCM Precipitation by Quantile Mapping: How Well Do Methods Preserve Changes in Quantiles and Extremes?, J. Climate, 28, 6938–6959, https://doi.org/10.1175/JCLI-D-14-00754.1, 2015. a, b
Choi, Y., Morlighem, M., Rignot, E., and Wood, M.: Ice dynamics will remain a primary driver of Greenland ice sheet mass loss over the next century, Communications Earth and Environment, 2, 1–9, https://doi.org/10.1038/s43247-021-00092-z, 2021. a, b
Crameri, F., Shephard, G. E., and Heron, P. J.: The misuse of colour in science communication, Nat. Commun., 11, 5444, https://doi.org/10.1038/s41467-020-19160-7, 2020. a
Danabasoglu, G., Lamarque, J.-F., Bacmeister, J., Bailey, D. A., DuVivier, A. K., Edwards, J., Emmons, L. K., Fasullo, J., Garcia, R., Gettelman, A., Hannay, C., Holland, M. M., Large, W. G., Lauritzen, P. H., Lawrence, D. M., Lenaerts, J. T. M., Lindsay, K., Lipscomb, W. H., Mills, M. J., Neale, R., Oleson, K. W., Otto-Bliesner, B., Phillips, A. S., Sacks, W., Tilmes, S., van Kampenhout, L., Vertenstein, M., Bertini, A., Dennis, J., Deser, C., Fischer, C., Fox-Kemper, B., Kay, J. E., Kinnison, D., Kushner, P. J., Larson, V. E., Long, M. C., Mickelson, S., Moore, J. K., Nienhouse, E., Polvani, L., Rasch, P. J., and Strand, W. G.: The Community Earth System Model Version 2 (CESM2), J. Adv. Model. Earth Sy., 12, e2019MS001916, https://doi.org/10.1029/2019MS001916, 2020. a
Delhasse, A., Beckmann, J., Kittel, C., and Fettweis, X.: Coupling MAR (Modèle Atmosphérique Régional) with PISM (Parallel Ice Sheet Model) mitigates the positive melt–elevation feedback, The Cryosphere, 18, 633–651, https://doi.org/10.5194/tc-18-633-2024, 2024. a
Fettweis, X., Franco, B., Tedesco, M., van Angelen, J. H., Lenaerts, J. T. M., van den Broeke, M. R., and Gallée, H.: Estimating the Greenland ice sheet surface mass balance contribution to future sea level rise using the regional atmospheric climate model MAR, The Cryosphere, 7, 469–489, https://doi.org/10.5194/tc-7-469-2013, 2013. a, b, c
Fettweis, X., Box, J. E., Agosta, C., Amory, C., Kittel, C., Lang, C., van As, D., Machguth, H., and Gallée, H.: Reconstructions of the 1900–2015 Greenland ice sheet surface mass balance using the regional climate MAR model, The Cryosphere, 11, 1015–1033, https://doi.org/10.5194/tc-11-1015-2017, 2017. a, b, c
Garbe, J., Albrecht, T., Levermann, A., Donges, J. F., and Winkelmann, R.: The hysteresis of the Antarctic Ice Sheet, Nature, 585, 538–544, https://doi.org/10.1038/s41586-020-2727-5, 2020. a
Gettelman, A., Mills, M. J., Kinnison, D. E., Garcia, R. R., Smith, A. K., Marsh, D. R., Tilmes, S., Vitt, F., Bardeen, C. G., McInerny, J., Liu, H.-L., Solomon, S. C., Polvani, L. M., Emmons, L. K., Lamarque, J.-F., Richter, J. H., Glanville, A. S., Bacmeister, J. T., Phillips, A. S., Neale, R. B., Simpson, I. R., DuVivier, A. K., Hodzic, A., and Randel, W. J.: The Whole Atmosphere Community Climate Model Version 6 (WACCM6), J. Geophys. Res.-Atmos., 124, 12380–12403, https://doi.org/10.1029/2019JD030943, 2019. a
Glaude, Q., Noel, B., Olesen, M., Van den Broeke, M., van de Berg, W. J., Mottram, R., Hansen, N., Delhasse, A., Amory, C., Kittel, C., Goelzer, H., and Fettweis, X.: A Factor Two Difference in 21st-Century Greenland Ice Sheet Surface Mass Balance Projections From Three Regional Climate Models Under a Strong Warming Scenario (SSP5-8.5), Geophys. Res. Lett., 51, e2024GL111902, https://doi.org/10.1029/2024GL111902, 2024. a
Goelzer, H., Nowicki, S., Payne, A., Larour, E., Seroussi, H., Lipscomb, W. H., Gregory, J., Abe-Ouchi, A., Shepherd, A., Simon, E., Agosta, C., Alexander, P., Aschwanden, A., Barthel, A., Calov, R., Chambers, C., Choi, Y., Cuzzone, J., Dumas, C., Edwards, T., Felikson, D., Fettweis, X., Golledge, N. R., Greve, R., Humbert, A., Huybrechts, P., Le clec'h, S., Lee, V., Leguy, G., Little, C., Lowry, D. P., Morlighem, M., Nias, I., Quiquet, A., Rückamp, M., Schlegel, N.-J., Slater, D. A., Smith, R. S., Straneo, F., Tarasov, L., van de Wal, R., and van den Broeke, M.: The future sea-level contribution of the Greenland ice sheet: a multi-model ensemble study of ISMIP6, The Cryosphere, 14, 3071–3096, https://doi.org/10.5194/tc-14-3071-2020, 2020. a, b, c
Harris, L., McRae, A. T. T., Chantry, M., Dueben, P. D., and Palmer, T. N.: A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts, J. Adv. Model. Earth Sy., 14, e2022MS003120, https://doi.org/10.1029/2022MS003120, 2022. a
Hartmann, D. L.: Global Physical Climatology, Academic Press, San Diego, ISBN 978-0-12-328531-7, https://doi.org/10.1016/C2009-0-00030-0, 1994. a
Hess, P., Lange, S., Schötz, C., and Boers, N.: Deep Learning for Bias-Correcting CMIP6-Class Earth System Models, Earth's Future, 11, e2023EF004002, https://doi.org/10.1029/2023EF004002, 2023. a, b
Hess, P., Aich, M., Pan, B., and Boers, N.: Fast, Scale-Adaptive, and Uncertainty-Aware Downscaling of Earth System Model Fields with Generative Machine Learning, Code Ocean capsule 9094997, version 1, https://doi.org/10.24433/CO.2150269.v1, 2026. a
Ho, J., Jain, A., and Abbeel, P.: Denoising Diffusion Probabilistic Models, arXiv [preprint], https://doi.org/10.48550/arXiv.2006.11239, 2020. a
Jouvet, G. and Cordonnier, G.: Ice-flow model emulator based on physics-informed deep learning, J. Glaciol., 69, 1941–1955, https://doi.org/10.1017/jog.2023.73, 2023. a
Jouvet, G., Cordonnier, G., Kim, B., Lüthi, M., Vieli, A., and Aschwanden, A.: Deep learning speeds up ice flow modelling by several orders of magnitude, J. Glaciol., 68, 651–664, https://doi.org/10.1017/jog.2021.120, 2022. a
Kochkov, D., Yuval, J., Langmore, I., Norgaard, P., Smith, J., Mooers, G., Klöwer, M., Lottes, J., Rasp, S., Düben, P., Hatfield, S., Battaglia, P., Sanchez-Gonzalez, A., Willson, M., Brenner, M. P., and Hoyer, S.: Neural general circulation models for weather and climate, Nature, 632, 1060–1066, https://doi.org/10.1038/s41586-024-07744-y, 2024. a
Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., and Battaglia, P.: Learning skillful medium-range global weather forecasting, Science, 382, 1416–1421, https://doi.org/10.1126/science.adi2336, 2023. a
Lucas-Picher, P., Wulff-Nielsen, M., Christensen, J. H., Aðalgeirsdóttir, G., Mottram, R., and Simonsen, S. B.: Very high resolution regional climate model simulations over Greenland: Identifying added value, J. Geophys. Res.-Atmos., 117, https://doi.org/10.1029/2011JD016267, 2012. a
Morlighem, M., Williams, C. N., Rignot, E., An, L., Arndt, J. E., Bamber, J. L., Catania, G., Chauché, N., Dowdeswell, J. A., Dorschel, B., Fenty, I., Hogan, K., Howat, I., Hubbard, A., Jakobsson, M., Jordan, T. M., Kjeldsen, K. K., Millan, R., Mayer, L., Mouginot, J., Noël, B. P. Y., O'Cofaigh, C., Palmer, S., Rysgaard, S., Seroussi, H., Siegert, M. J., Slabon, P., Straneo, F., van den Broeke, M. R., Weinrebe, W., Wood, M., and Zinglersen, K. B.: BedMachine v3: Complete Bed Topography and Ocean Bathymetry Mapping of Greenland From Multibeam Echo Sounding Combined With Mass Conservation, Geophys. Res. Lett., 44, 11051–11061, https://doi.org/10.1002/2017GL074954, 2017. a
Mottram, R., Boberg, F., Langen, P., Yang, S., Rodehacke, C., Christensen, J. H., and Madsen, M. S.: Surface mass balance of the Greenland ice sheet in the regional climate model HIRHAM5: Present state and future prospects, Low Temperature Science, 75, 105–115, https://doi.org/10.14943/lowtemsci.75.105, 2017. a
Noël, B., van de Berg, W. J., Machguth, H., Lhermitte, S., Howat, I., Fettweis, X., and van den Broeke, M. R.: A daily, 1 km resolution data set of downscaled Greenland ice sheet surface mass balance (1958–2015), The Cryosphere, 10, 2361–2377, https://doi.org/10.5194/tc-10-2361-2016, 2016. a
Nowicki, S., Goelzer, H., Seroussi, H., Payne, A. J., Lipscomb, W. H., Abe-Ouchi, A., Agosta, C., Alexander, P., Asay-Davis, X. S., Barthel, A., Bracegirdle, T. J., Cullather, R., Felikson, D., Fettweis, X., Gregory, J. M., Hattermann, T., Jourdain, N. C., Kuipers Munneke, P., Larour, E., Little, C. M., Morlighem, M., Nias, I., Shepherd, A., Simon, E., Slater, D., Smith, R. S., Straneo, F., Trusel, L. D., van den Broeke, M. R., and van de Wal, R.: Experimental protocol for sea level projections from ISMIP6 stand-alone ice sheet models, The Cryosphere, 14, 2331–2368, https://doi.org/10.5194/tc-14-2331-2020, 2020. a, b
Paice, C. M., Fettweis, X., and Huybrechts, P.: Positive feedbacks drive the Greenland ice sheet evolution in millennial-length MAR–GISM simulations under a high-end warming scenario, The Cryosphere, 20, 309–332, https://doi.org/10.5194/tc-20-309-2026, 2026. a
Payne, A. J., Nowicki, S., Abe-Ouchi, A., Agosta, C., Alexander, P., Albrecht, T., Asay-Davis, X., Aschwanden, A., Barthel, A., Bracegirdle, T. J., Calov, R., Chambers, C., Choi, Y., Cullather, R., Cuzzone, J., Dumas, C., Edwards, T. L., Felikson, D., Fettweis, X., Galton-Fenzi, B. K., Goelzer, H., Gladstone, R., Golledge, N. R., Gregory, J. M., Greve, R., Hattermann, T., Hoffman, M. J., Humbert, A., Huybrechts, P., Jourdain, N. C., Kleiner, T., Munneke, P. K., Larour, E., Le clec'h, S., Lee, V., Leguy, G., Lipscomb, W. H., Little, C. M., Lowry, D. P., Morlighem, M., Nias, I., Pattyn, F., Pelle, T., Price, S. F., Quiquet, A., Reese, R., Rückamp, M., Schlegel, N.-J., Seroussi, H., Shepherd, A., Simon, E., Slater, D., Smith, R. S., Straneo, F., Sun, S., Tarasov, L., Trusel, L. D., Van Breedam, J., van de Wal, R., van den Broeke, M., Winkelmann, R., Zhao, C., Zhang, T., and Zwinger, T.: Future Sea Level Change Under Coupled Model Intercomparison Project Phase 5 and Phase 6 Scenarios From the Greenland and Antarctic Ice Sheets, Geophys. Res. Lett., 48, e2020GL091741, https://doi.org/10.1029/2020GL091741, 2021. a
Price, I., Sanchez-Gonzalez, A., Alet, F., Andersson, T. R., El-Kadi, A., Masters, D., Ewalds, T., Stott, J., Mohamed, S., Battaglia, P., Lam, R., and Willson, M.: Probabilistic weather forecasting with machine learning, Nature, 637, 84–90, https://doi.org/10.1038/s41586-024-08252-9, 2025. a
Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P., Fitzsimons, M., Athanassiadou, M., Kashem, S., Madge, S., Prudden, R., Mandhane, A., Clark, A., Brock, A., Simonyan, K., Hadsell, R., Robinson, N., Clancy, E., Arribas, A., and Mohamed, S.: Skilful precipitation nowcasting using deep generative models of radar, Nature, 597, 672–677, https://doi.org/10.1038/s41586-021-03854-z, 2021. a
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, arXiv [preprint], https://doi.org/10.48550/arXiv.1505.04597, 2015. a, b
Rosier, S. H. R., Bull, C. Y. S., Woo, W. L., and Gudmundsson, G. H.: Predicting ocean-induced ice-shelf melt rates using deep learning, The Cryosphere, 17, 499–518, https://doi.org/10.5194/tc-17-499-2023, 2023. a
Seguinot, J.: Spatial and seasonal effects of temperature variability in a positive degree-day glacier surface mass-balance model, J. Glaciol., 59, 1202–1204, https://doi.org/10.3189/2013JoG13J081, 2013. a, b
Seguinot, J.: PyPDD: a positive degree day model for glacier surface mass balance, Zenodo [code], https://doi.org/10.5281/zenodo.3467639, 2019. a
Seland, Ø., Bentsen, M., Olivié, D., Toniazzo, T., Gjermundsen, A., Graff, L. S., Debernard, J. B., Gupta, A. K., He, Y.-C., Kirkevåg, A., Schwinger, J., Tjiputra, J., Aas, K. S., Bethke, I., Fan, Y., Griesfeller, J., Grini, A., Guo, C., Ilicak, M., Karset, I. H. H., Landgren, O., Liakka, J., Moseid, K. O., Nummelin, A., Spensberger, C., Tang, H., Zhang, Z., Heinze, C., Iversen, T., and Schulz, M.: Overview of the Norwegian Earth System Model (NorESM2) and key climate response of CMIP6 DECK, historical, and scenario simulations, Geosci. Model Dev., 13, 6165–6200, https://doi.org/10.5194/gmd-13-6165-2020, 2020. a, b, c
Sellevold, R., van Kampenhout, L., Lenaerts, J. T. M., Noël, B., Lipscomb, W. H., and Vizcaino, M.: Surface mass balance downscaling through elevation classes in an Earth system model: application to the Greenland ice sheet, The Cryosphere, 13, 3193–3208, https://doi.org/10.5194/tc-13-3193-2019, 2019. a
Seroussi, H., Nowicki, S., Payne, A. J., Goelzer, H., Lipscomb, W. H., Abe-Ouchi, A., Agosta, C., Albrecht, T., Asay-Davis, X., Barthel, A., Calov, R., Cullather, R., Dumas, C., Galton-Fenzi, B. K., Gladstone, R., Golledge, N. R., Gregory, J. M., Greve, R., Hattermann, T., Hoffman, M. J., Humbert, A., Huybrechts, P., Jourdain, N. C., Kleiner, T., Larour, E., Leguy, G. R., Lowry, D. P., Little, C. M., Morlighem, M., Pattyn, F., Pelle, T., Price, S. F., Quiquet, A., Reese, R., Schlegel, N.-J., Shepherd, A., Simon, E., Smith, R. S., Straneo, F., Sun, S., Trusel, L. D., Van Breedam, J., van de Wal, R. S. W., Winkelmann, R., Zhao, C., Zhang, T., and Zwinger, T.: ISMIP6 Antarctica: a multi-model ensemble of the Antarctic ice sheet evolution over the 21st century, The Cryosphere, 14, 3033–3070, https://doi.org/10.5194/tc-14-3033-2020, 2020. a, b
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., and Poole, B.: Score-Based Generative Modeling through Stochastic Differential Equations, arXiv [preprint], https://doi.org/10.48550/arXiv.2011.13456, 2021. a, b
Steidl, V., Bamber, J. L., and Zhu, X. X.: Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard, The Cryosphere, 19, 645–661, https://doi.org/10.5194/tc-19-645-2025, 2025. a
Tedesco, M., Colosio, P., Fettweis, X., and Cervone, G.: A computationally efficient statistically downscaled 100 m resolution Greenland product from the regional climate model MAR, The Cryosphere, 17, 5061–5074, https://doi.org/10.5194/tc-17-5061-2023, 2023. a, b, c
Trusel, L. D., Das, S. B., Osman, M. B., Evans, M. J., Smith, B. E., Fettweis, X., McConnell, J. R., Noël, B. P. Y., and van den Broeke, M. R.: Nonlinear rise in Greenland runoff in response to post-industrial Arctic warming, Nature, 564, 104–108, https://doi.org/10.1038/s41586-018-0752-4, 2018. a
van Dalum, C. T., van de Berg, W. J., Gadde, S. N., van Tiggelen, M., van der Drift, T., van Meijgaard, E., van Ulft, L. H., and van den Broeke, M. R.: First results of the polar regional climate model RACMO2.4, The Cryosphere, 18, 4065–4088, https://doi.org/10.5194/tc-18-4065-2024, 2024. a, b
van den Broeke, M. R., Enderlin, E. M., Howat, I. M., Kuipers Munneke, P., Noël, B. P. Y., van de Berg, W. J., van Meijgaard, E., and Wouters, B.: On the recent contribution of the Greenland ice sheet to sea level change, The Cryosphere, 10, 1933–1946, https://doi.org/10.5194/tc-10-1933-2016, 2016. a
van der Meer, M., de Roda Husman, S., and Lhermitte, S.: Deep Learning Regional Climate Model Emulators: A Comparison of Two Downscaling Training Frameworks, J. Adv. Model. Earth Sy., 15, e2022MS003593, https://doi.org/10.1029/2022MS003593, 2023. a
van der Meer, M., Zekollari, H., Huss, M., Bolibar, J., Sjursen, K. H., and Farinotti, D.: A minimal machine-learning glacier mass balance model, The Cryosphere, 19, 805–826, https://doi.org/10.5194/tc-19-805-2025, 2025. a
Verjans, V. and Robel, A.: Accelerating Subglacial Hydrology for Ice Sheet Models With Deep Learning Methods, Geophys. Res. Lett., 51, e2023GL105281, https://doi.org/10.1029/2023GL105281, 2024. a
Wang, Y., Lai, C.-Y., Prior, D. J., and Cowen-Breen, C.: Deep learning the flow law of Antarctic ice shelves, Science, 387, 1219–1224, https://doi.org/10.1126/science.adp3300, 2025. a
Watt-Meyer, O., Henn, B., McGibbon, J., Clark, S. K., Kwa, A., Perkins, W. A., Wu, E., Harris, L., and Bretherton, C. S.: ACE2: accurately learning subseasonal to decadal atmospheric variability and forced responses, NPJ Climate and Atmospheric Science, 8, 205, https://doi.org/10.1038/s41612-025-01090-0, 2025. a
Zeitz, M., Reese, R., Beckmann, J., Krebs-Kanzow, U., and Winkelmann, R.: Impact of the melt–albedo feedback on the future evolution of the Greenland Ice Sheet with PISM-dEBM-simple, The Cryosphere, 15, 5739–5764, https://doi.org/10.5194/tc-15-5739-2021, 2021. a
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., and Wang, O.: The Unreasonable Effectiveness of Deep Features as a Perceptual Metric, arXiv [preprint], https://doi.org/10.48550/arXiv.1801.03924, 2018. a
Short summary
This study presents a fast, physics-guided machine-learning method that downscales coarse climate fields to fine resolution while enforcing conservation of large-scale totals. Trained on regional climate simulations and driven by Earth system model output, it handles extremes and outperforms linear interpolation, providing realistic, high-resolution forcing for ice-sheet models and improving projections of Greenland’s sea-level contribution.
This study presents a fast, physics-guided machine-learning method that downscales coarse...
