Articles | Volume 20, issue 7
https://doi.org/10.5194/tc-20-4235-2026
© 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-20-4235-2026
© 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 Jul 2026
Research article |
| 30 Jul 2026
| 30 Jul 2026
The Modèle Atmosphérique Régional – Intelligence Artificielle (MAR-IA): surface meltwater over Greenland
Marco Tedesco
CORRESPONDING AUTHOR
Lamont-Doherty Earth Observatory, Columbia Climate School, Columbia University, New York, USA
Racheet Matai
Lamont-Doherty Earth Observatory, Columbia Climate School, Columbia University, New York, USA
Xavier Fettweis
University of Liege, Liege, Belgium
Related authors
Raf Antwerpen, Marco Tedesco, Pierre Gentine, Willem Jan van de Berg, and Xavier Fettweis
The Cryosphere, 20, 3131–3149, https://doi.org/10.5194/tc-20-3131-2026, https://doi.org/10.5194/tc-20-3131-2026, 2026
Short summary
Short summary
We study why Greenland ice melts faster by improving how ice brightness is represented. This is important because it controls how much sunlight is absorbed by the ice. Using satellite data and a new transparent machine learning method trained with climate model information, we capture how the shape of the ice sheet, temperature, and meltwater change ice brightness. Our approach outperforms existing climate models and can reduce uncertainty in future sea level rise projections.
Jonathon R. Preece, Patrick Alexander, Thomas L. Mote, Gabriel J. Kooperman, Xavier Fettweis, and Marco Tedesco
The Cryosphere, 20, 2871–2894, https://doi.org/10.5194/tc-20-2871-2026, https://doi.org/10.5194/tc-20-2871-2026, 2026
Short summary
Short summary
Surface melt of the Greenland Ice Sheet has increased dramatically since the turn of the century, aided by an increase in persistent atmospheric circulation patterns that promote anomalously warm conditions. Through modeling experiments, this study shows that surface mass loss would have been reduced by 62% relative to historical conditions if this shift in atmospheric circulation would have occurred under the lower average temperatures of a preindustrial climate.
Wenwen Li, Chia-Yu Hsu, and Marco Tedesco
EGUsphere, https://doi.org/10.5194/egusphere-2023-2831, https://doi.org/10.5194/egusphere-2023-2831, 2024
Preprint withdrawn
Short summary
Short summary
This review paper fills a knowledge gap in comprehensive literature review at the junction of AI-Arctic sea ice research. We provide a fine-grained review of AI applications in a variety of sea ice research domains. Based on these analyses, we point out exciting opportunities where the Arctic sea ice community can continue benefiting from cutting-edge AI. These future research directions will foster the continuous growth of the Arctic sea ice–AI research community.
Marco Tedesco, Paolo Colosio, Xavier Fettweis, and Guido Cervone
The Cryosphere, 17, 5061–5074, https://doi.org/10.5194/tc-17-5061-2023, https://doi.org/10.5194/tc-17-5061-2023, 2023
Short summary
Short summary
We developed a technique to improve the outputs of a model that calculates the gain and loss of Greenland and consequently its contribution to sea level rise. Our technique generates “sharper” images of the maps generated by the model to better understand and quantify where losses occur. This has implications for improving models, understanding what drives the contributions of Greenland to sea level rise, and more.
Benjamin E. Smith, Brooke Medley, Xavier Fettweis, Tyler Sutterley, Patrick Alexander, David Porter, and Marco Tedesco
The Cryosphere, 17, 789–808, https://doi.org/10.5194/tc-17-789-2023, https://doi.org/10.5194/tc-17-789-2023, 2023
Short summary
Short summary
We use repeated satellite measurements of the height of the Greenland ice sheet to learn about how three computational models of snowfall, melt, and snow compaction represent actual changes in the ice sheet. We find that the models do a good job of estimating how the parts of the ice sheet near the coast have changed but that two of the models have trouble representing surface melt for the highest part of the ice sheet. This work provides suggestions for how to better model snowmelt.
Raf M. Antwerpen, Marco Tedesco, Xavier Fettweis, Patrick Alexander, and Willem Jan van de Berg
The Cryosphere, 16, 4185–4199, https://doi.org/10.5194/tc-16-4185-2022, https://doi.org/10.5194/tc-16-4185-2022, 2022
Short summary
Short summary
The ice on Greenland has been melting more rapidly over the last few years. Most of this melt comes from the exposure of ice when the overlying snow melts. This ice is darker than snow and absorbs more sunlight, leading to more melt. It remains challenging to accurately simulate the brightness of the ice. We show that the color of ice simulated by Modèle Atmosphérique Régional (MAR) is too bright. We then show that this means that MAR may underestimate how fast the Greenland ice is melting.
Guillaume Timmermans, Brice Noël, Christoph Kittel, Thomas Dethinne, Nicolas Ghilain, and Xavier Fettweis
EGUsphere, https://doi.org/10.5194/egusphere-2026-2341, https://doi.org/10.5194/egusphere-2026-2341, 2026
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Short summary
We assess how well a regional climate model reproduces changes in the mass of the Greenland Ice Sheet due to surface processes, an important driver of sea level rise. By comparing model results with observations, we show that high-resolution simulations closely match reality. Coarser simulations are less detailed near the edges but remain reliable overall. A resolution of 10 kilometers provides a good balance between accuracy and computing cost for long-term projections.
Ian Simpson, Edward Hanna, Ryan S. Williams, Linh Luu, Andrew Orr, Julie Jones, Xavier Fettweis, Jose Abraham Torres Alavez, Ole Bøssing Christensen, Ella Gilbert, Sid Gumber, Christoph Kittel, Sihan Li, Damien Maure, Ruth Mottram, Tony Phillips, Willem Jan van de Berg, and Kristiina Verro
EGUsphere, https://doi.org/10.5194/egusphere-2026-2270, https://doi.org/10.5194/egusphere-2026-2270, 2026
Short summary
Short summary
The warming trend in global temperatures has potential to result in accelerated break up of the Antarctic ice shelves, which would contribute to rising sea levels. Here we present a novel database of Antarctic extreme weather events over a selection of the Antarctic ice shelves. We examine air temperature, precipitation, wind and surface pressure. In addition, we examine trends in the frequency of extreme events and the links with weather patterns around Antarctica.
Raf Antwerpen, Marco Tedesco, Pierre Gentine, Willem Jan van de Berg, and Xavier Fettweis
The Cryosphere, 20, 3131–3149, https://doi.org/10.5194/tc-20-3131-2026, https://doi.org/10.5194/tc-20-3131-2026, 2026
Short summary
Short summary
We study why Greenland ice melts faster by improving how ice brightness is represented. This is important because it controls how much sunlight is absorbed by the ice. Using satellite data and a new transparent machine learning method trained with climate model information, we capture how the shape of the ice sheet, temperature, and meltwater change ice brightness. Our approach outperforms existing climate models and can reduce uncertainty in future sea level rise projections.
Ian Castellanos, Martin Ménégoz, Juliette Blanchet, Julien Beaumet, Hubert Gallée, Eduardo Moreno-Chamarro, Chantal Staquet, and Xavier Fettweis
Earth Syst. Dynam., 17, 581–605, https://doi.org/10.5194/esd-17-581-2026, https://doi.org/10.5194/esd-17-581-2026, 2026
Short summary
Short summary
The Alps host glaciers, distinct ecosystems, socio-economic interests and water resources that are being impacted by climate change. In this study, we aim at understanding how warming occurs in the Alps in projected scenarios and what physical processes drive it. We find under these scenarios that elevations around the snowline will warm faster than elsewhere, because snow retreats to higher elevations. Indeed, snow slows down warming due to its high albedo and the energy consumed to melt it.
Fredrik Boberg, Xavier Fettweis, Nicolaj Hansen, Ruth Mottram, and Michiel R. van den Broeke
The Cryosphere, 20, 2947–2960, https://doi.org/10.5194/tc-20-2947-2026, https://doi.org/10.5194/tc-20-2947-2026, 2026
Short summary
Short summary
An ensemble of regional climate model simulations is used to estimate the 21st century change in precipitation on the Greenland ice sheet. For the end of the century, the change is in the range 40 to 170 Gt per year, depending on the emission scenario. Using annual values of 2 m air temperature and precipitation, we estimate an increase in precipitation of 35 Gt per year for every degree of warming.
Jonathon R. Preece, Patrick Alexander, Thomas L. Mote, Gabriel J. Kooperman, Xavier Fettweis, and Marco Tedesco
The Cryosphere, 20, 2871–2894, https://doi.org/10.5194/tc-20-2871-2026, https://doi.org/10.5194/tc-20-2871-2026, 2026
Short summary
Short summary
Surface melt of the Greenland Ice Sheet has increased dramatically since the turn of the century, aided by an increase in persistent atmospheric circulation patterns that promote anomalously warm conditions. Through modeling experiments, this study shows that surface mass loss would have been reduced by 62% relative to historical conditions if this shift in atmospheric circulation would have occurred under the lower average temperatures of a preindustrial climate.
Ella Gilbert, José Abraham Torres-Alavez, Marte G. Hofsteenge, Willem Jan van de Berg, Fredrik Boberg, Ole Bøssing Christensen, Christiaan Timo van Dalum, Xavier Fettweis, Siddharth Gumber, Nicolaj Hansen, Christoph Kittel, Clara Lambin, Damien Maure, Ruth Mottram, Martin Olesen, Andrew Orr, Tony Phillips, Maurice van Tiggelen, Kristiina Verro, and Priscilla A. Mooney
The Cryosphere, 20, 2629–2658, https://doi.org/10.5194/tc-20-2629-2026, https://doi.org/10.5194/tc-20-2629-2026, 2026
Short summary
Short summary
Here we present a new dataset – the PolarRES ensemble – of four state-of-the-art regional climate models, which capture the full complexity of Antarctica's climate. The ensemble out-performs other available tools, advancing our ability to explore Antarctic climate. While it still has limitations, the PolarRES ensemble offers a novel and exciting way of evaluating climate processes and features, and we encourage researchers to use the data, which are freely available.
Audrey Goutard, Marion Réveillet, Fanny Brun, Delphine Six, Kevin Fourteau, Charles Amory, Xavier Fettweis, Mathieu Fructus, Arbindra Khadka, and Matthieu Lafaysse
The Cryosphere, 20, 2393–2416, https://doi.org/10.5194/tc-20-2393-2026, https://doi.org/10.5194/tc-20-2393-2026, 2026
Short summary
Short summary
A new scheme has been developed in a snowpack model (SURFEX/ISBA-Crocus), to consider the impact of liquid water dynamics on bare ice, including albedo feedback and refreezing. When applied to the Mera Glacier in Nepal, the model reveals strong seasonal effects on the energy and mass balance, with increased melting in dry seasons and significant refreezing during the monsoon. This development improves mass balance modeling under increasing rainfall and bare ice exposure due to climate warming.
Benjamin Heurgue, Charles Amory, Christoph Kittel, Fredrik Boberg, Gaël Durand, Vincent Favier, Xavier Fettweis, Quentin Glaude, Heiko Goelzer, Nicolaj Hansen, Nicolas C. Jourdain, Ruth Mottram, Martin Olesen, Willem Jan Van de Berg, Michiel R. Van den Broeke, and René R. Wijngaard
EGUsphere, https://doi.org/10.5194/egusphere-2026-624, https://doi.org/10.5194/egusphere-2026-624, 2026
Short summary
Short summary
We studied how the Antarctic ice sheet surface mass balance may change by 2100 using three high-resolution climate models forced by the same future climate scenario. While the models agree for present-day conditions, they project very different futures, especially over floating ice shelves. These differences mainly come from how melting, refreezing, and temperature are represented. Our results show that future sea level projections strongly depend on how well models simulate today’s climate.
Horst Machguth, Andrew Tedstone, Peter Kuipers Munneke, Max Brils, Brice Noël, Nicole Clerx, Nicolas Jullien, Xavier Fettweis, and Michiel van den Broeke
The Cryosphere, 20, 427–452, https://doi.org/10.5194/tc-20-427-2026, https://doi.org/10.5194/tc-20-427-2026, 2026
Short summary
Short summary
Due to increasing air temperatures, surface melt expands to higher elevations on the Greenland ice sheet. This is visible on satellite imagery in the form of rivers of meltwater running across the surface of the ice sheet. We compare model results of meltwater at high elevations on the ice sheet to satellite observations. We find that each of the models shows strengths and weaknesses. A detailed look into the model results reveals potential reasons for the differences between models.
Chloë Marie Paice, Xavier Fettweis, and Philippe Huybrechts
The Cryosphere, 20, 309–332, https://doi.org/10.5194/tc-20-309-2026, https://doi.org/10.5194/tc-20-309-2026, 2026
Short summary
Short summary
To study Greenland ice sheet–atmosphere interactions, we coupled an ice sheet model to a regional climate model and performed simulations of differing coupling complexity over 1000 years under a high-warming climate scenario. They reveal that at first melt at the ice sheet margin is reduced by changing wind patterns. But over time, as the ice sheet melts and its surface lowers, precipitation patterns and cloudiness also change and amplify ice mass loss over the entire ice sheet.
Heiko Goelzer, Constantijn J. Berends, Fredrik Boberg, Gael Durand, Tamsin L. Edwards, Xavier Fettweis, Fabien Gillet-Chaulet, Quentin Glaude, Philippe Huybrechts, Sébastien Le clec'h, Ruth Mottram, Brice Noël, Martin Olesen, Charlotte Rahlves, Jeremy Rohmer, Michiel van den Broeke, and Roderik S. W. van de Wal
The Cryosphere, 19, 6887–6906, https://doi.org/10.5194/tc-19-6887-2025, https://doi.org/10.5194/tc-19-6887-2025, 2025
Short summary
Short summary
We present an ensemble of ice sheet model projections for the Greenland ice sheet. The focus is on providing projections that improve our understanding of the range future sea-level rise and the inherent uncertainties over the next 100 to 300 years. Compared to earlier work we more fully account for some of the uncertainties in sea-level projections. We include a wider range of climate model output, more climate change scenarios and we extend projections schematically up to year 2300.
Thomas Dethinne, Nicolas Ghilain, Christoph Kittel, Benjamin Lecart, Xavier Fettweis, and François Jonard
EGUsphere, https://doi.org/10.5194/egusphere-2025-3907, https://doi.org/10.5194/egusphere-2025-3907, 2025
Short summary
Short summary
This study replace standard vegetation input of a regional climate model with a satellite-based vegetation dataset to assess how vegetation influences climate during extreme events and to test the sensitivity of the model. The results show a non-linear sensitivity to vegetation, and using an observation-based vegetation input allows for a better representation of the extreme events, highlight the need for an advanced representation of vegetation in climate model to improve climate predictions.
Kristiina Verro, Cecilia Äijälä, Roberta Pirazzini, Ruzica Dadic, Damien Maure, Willem Jan van de Berg, Giacomo Traversa, Christiaan T. van Dalum, Petteri Uotila, Xavier Fettweis, Biagio Di Mauro, and Milla Johansson
The Cryosphere, 19, 4409–4436, https://doi.org/10.5194/tc-19-4409-2025, https://doi.org/10.5194/tc-19-4409-2025, 2025
Short summary
Short summary
Accurately representing Antarctic sea ice is essential for reliable climate and ocean model predictions. We evaluated how different models simulate the sea ice's sunlight reflectivity (called albedo) using field and satellite data. Models with simple albedo schemes performed well in limited cases but missed key processes. The advanced scheme in the MetROMS-UHel ocean model provided the most accurate results, including observed day–night albedo changes observed during a field campaign.
Zhengwen Yan, Jiangjun Ran, Pavel Ditmar, C. K. Shum, Roland Klees, Patrick Smith, and Xavier Fettweis
Earth Syst. Sci. Data, 17, 4253–4275, https://doi.org/10.5194/essd-17-4253-2025, https://doi.org/10.5194/essd-17-4253-2025, 2025
Short summary
Short summary
The Gravity Recovery And Climate Experiment (GRACE) mission has greatly improved our understanding of changes in Earth's gravity field over time. A novel mass concentration (mascon) dataset, GCL-Mascon2024, was determined by leveraging the short-arc approach, advanced spatial constraints, a frequency-dependent noise processing strategy, and parameterization-integrating natural boundaries, aiming to enhance accuracy for monitoring mass transportation on Earth.
Weiran Li, Stef Lhermitte, Bert Wouters, Cornelis Slobbe, Max Brils, and Xavier Fettweis
The Cryosphere, 19, 3419–3442, https://doi.org/10.5194/tc-19-3419-2025, https://doi.org/10.5194/tc-19-3419-2025, 2025
Short summary
Short summary
Due to recurrent melt and refreezing events in recent decades, the snow conditions over Greenland have changed. To observe this, we use a parameter (leading edge width; LeW) derived from satellite altimetry and analyse its spatial and temporal variations. By comparing the LeW variations with modelled firn parameters, we concluded that the 2012 melt event and the recent and increasingly frequent melt events have a long-lasting impact on the volume scattering of Greenland firn.
Jean-François Grailet, Robin J. Hogan, Nicolas Ghilain, David Bolsée, Xavier Fettweis, and Marilaure Grégoire
Geosci. Model Dev., 18, 1965–1988, https://doi.org/10.5194/gmd-18-1965-2025, https://doi.org/10.5194/gmd-18-1965-2025, 2025
Short summary
Short summary
The MAR (Modèle Régional Atmosphérique) is a regional climate model used for weather forecasting and studying the climate over various regions. This paper presents an update of MAR thanks to which it can precisely decompose solar radiation, in particular in the UV (ultraviolet) and photosynthesis ranges, both being critical to human health and ecosystems. As a first application of this new capability, this paper presents a method for predicting UV indices with MAR.
Ny Riana Randresihaja, Olivier Gourgue, Lauranne Alaerts, Xavier Fettweis, Jonathan Lambrechts, Miguel De Le Court, Marilaure Grégoire, and Emmanuel Hanert
EGUsphere, https://doi.org/10.5194/egusphere-2025-634, https://doi.org/10.5194/egusphere-2025-634, 2025
Preprint archived
Short summary
Short summary
Coastal areas face rising flood threats as storms intensifies with climate change. With an advanced model of the Scheldt Estuary-North Sea, we studied how detailed atmospheric data must be to predict storm surge peaks in estuaries. We found that high-resolution atmospheric data gives the best results, and coarser data with same resolution as current global climate models give poorer results. We show that investing in localized, high-resolution atmospheric data can significantly improve results.
Sylvie Charbit, Christophe Dumas, Fabienne Maignan, Catherine Ottlé, Nina Raoult, Xavier Fettweis, and Philippe Conesa
The Cryosphere, 18, 5067–5099, https://doi.org/10.5194/tc-18-5067-2024, https://doi.org/10.5194/tc-18-5067-2024, 2024
Short summary
Short summary
The evolution of the Greenland ice sheet is highly dependent on surface melting and therefore on the processes operating at the snow–atmosphere interface and within the snow cover. Here we present new developments to apply a snow model to the Greenland ice sheet. The performance of this model is analysed in terms of its ability to simulate ablation processes. Our analysis shows that the model performs well when compared with the MAR regional polar atmospheric model.
Baptiste Vandecrux, Robert S. Fausto, Jason E. Box, Federico Covi, Regine Hock, Åsa K. Rennermalm, Achim Heilig, Jakob Abermann, Dirk van As, Elisa Bjerre, Xavier Fettweis, Paul C. J. P. Smeets, Peter Kuipers Munneke, Michiel R. van den Broeke, Max Brils, Peter L. Langen, Ruth Mottram, and Andreas P. Ahlstrøm
The Cryosphere, 18, 609–631, https://doi.org/10.5194/tc-18-609-2024, https://doi.org/10.5194/tc-18-609-2024, 2024
Short summary
Short summary
How fast is the Greenland ice sheet warming? In this study, we compiled 4500+ temperature measurements at 10 m below the ice sheet surface (T10m) from 1912 to 2022. We trained a machine learning model on these data and reconstructed T10m for the ice sheet during 1950–2022. After a slight cooling during 1950–1985, the ice sheet warmed at a rate of 0.7 °C per decade until 2022. Climate models showed mixed results compared to our observations and underestimated the warming in key regions.
Alison Delhasse, Johanna Beckmann, Christoph Kittel, and Xavier Fettweis
The Cryosphere, 18, 633–651, https://doi.org/10.5194/tc-18-633-2024, https://doi.org/10.5194/tc-18-633-2024, 2024
Short summary
Short summary
Aiming to study the long-term influence of an extremely warm climate in the Greenland Ice Sheet contribution to sea level rise, a new regional atmosphere–ice sheet model setup was established. The coupling, explicitly considering the melt–elevation feedback, is compared to an offline method to consider this feedback. We highlight mitigation of the feedback due to local changes in atmospheric circulation with changes in surface topography, making the offline correction invalid on the margins.
Idunn Aamnes Mostue, Stefan Hofer, Trude Storelvmo, and Xavier Fettweis
The Cryosphere, 18, 475–488, https://doi.org/10.5194/tc-18-475-2024, https://doi.org/10.5194/tc-18-475-2024, 2024
Short summary
Short summary
The latest generation of climate models (Coupled Model Intercomparison Project Phase 6 – CMIP6) warm more over Greenland and the Arctic and thus also project a larger mass loss from the Greenland Ice Sheet (GrIS) compared to the previous generation of climate models (CMIP5). Our work suggests for the first time that part of the greater mass loss in CMIP6 over the GrIS is driven by a difference in the surface mass balance sensitivity from a change in cloud representation in the CMIP6 models.
Wenwen Li, Chia-Yu Hsu, and Marco Tedesco
EGUsphere, https://doi.org/10.5194/egusphere-2023-2831, https://doi.org/10.5194/egusphere-2023-2831, 2024
Preprint withdrawn
Short summary
Short summary
This review paper fills a knowledge gap in comprehensive literature review at the junction of AI-Arctic sea ice research. We provide a fine-grained review of AI applications in a variety of sea ice research domains. Based on these analyses, we point out exciting opportunities where the Arctic sea ice community can continue benefiting from cutting-edge AI. These future research directions will foster the continuous growth of the Arctic sea ice–AI research community.
Laura J. Dietrich, Hans Christian Steen-Larsen, Sonja Wahl, Anne-Katrine Faber, and Xavier Fettweis
The Cryosphere, 18, 289–305, https://doi.org/10.5194/tc-18-289-2024, https://doi.org/10.5194/tc-18-289-2024, 2024
Short summary
Short summary
The contribution of the humidity flux to the surface mass balance in the accumulation zone of the Greenland Ice Sheet is uncertain. Here, we evaluate the regional climate model MAR using a multi-annual dataset of eddy covariance measurements and bulk estimates of the humidity flux. The humidity flux largely contributes to the summer surface mass balance (SMB) in the accumulation zone, indicating its potential importance for the annual SMB in a warming climate.
Marco Tedesco, Paolo Colosio, Xavier Fettweis, and Guido Cervone
The Cryosphere, 17, 5061–5074, https://doi.org/10.5194/tc-17-5061-2023, https://doi.org/10.5194/tc-17-5061-2023, 2023
Short summary
Short summary
We developed a technique to improve the outputs of a model that calculates the gain and loss of Greenland and consequently its contribution to sea level rise. Our technique generates “sharper” images of the maps generated by the model to better understand and quantify where losses occur. This has implications for improving models, understanding what drives the contributions of Greenland to sea level rise, and more.
Damien Maure, Christoph Kittel, Clara Lambin, Alison Delhasse, and Xavier Fettweis
The Cryosphere, 17, 4645–4659, https://doi.org/10.5194/tc-17-4645-2023, https://doi.org/10.5194/tc-17-4645-2023, 2023
Short summary
Short summary
The Arctic is warming faster than the rest of the Earth. Studies have already shown that Greenland and the Canadian Arctic are experiencing a record increase in melting rates, while Svalbard has been relatively less impacted. Looking at those regions but also extending the study to Iceland and the Russian Arctic archipelagoes, we see a heterogeneity in the melting-rate response to the Arctic warming, with the Russian archipelagoes experiencing lower melting rates than other regions.
Prateek Gantayat, Alison F. Banwell, Amber A. Leeson, James M. Lea, Dorthe Petersen, Noel Gourmelen, and Xavier Fettweis
Geosci. Model Dev., 16, 5803–5823, https://doi.org/10.5194/gmd-16-5803-2023, https://doi.org/10.5194/gmd-16-5803-2023, 2023
Short summary
Short summary
We developed a new supraglacial hydrology model for the Greenland Ice Sheet. This model simulates surface meltwater routing, meltwater drainage, supraglacial lake (SGL) overflow, and formation of lake ice. The model was able to reproduce 80 % of observed lake locations and provides a good match between the observed and modelled temporal evolution of SGLs.
Thomas Dethinne, Quentin Glaude, Ghislain Picard, Christoph Kittel, Patrick Alexander, Anne Orban, and Xavier Fettweis
The Cryosphere, 17, 4267–4288, https://doi.org/10.5194/tc-17-4267-2023, https://doi.org/10.5194/tc-17-4267-2023, 2023
Short summary
Short summary
We investigate the sensitivity of the regional climate model
Modèle Atmosphérique Régional(MAR) to the assimilation of wet-snow occurrence estimated by remote sensing datasets. The assimilation is performed by nudging the MAR snowpack temperature. The data assimilation is performed over the Antarctic Peninsula for the 2019–2021 period. The results show an increase in the melt production (+66.7 %) and a decrease in surface mass balance (−4.5 %) of the model for the 2019–2020 melt season.
Inès N. Otosaka, Andrew Shepherd, Erik R. Ivins, Nicole-Jeanne Schlegel, Charles Amory, Michiel R. van den Broeke, Martin Horwath, Ian Joughin, Michalea D. King, Gerhard Krinner, Sophie Nowicki, Anthony J. Payne, Eric Rignot, Ted Scambos, Karen M. Simon, Benjamin E. Smith, Louise S. Sørensen, Isabella Velicogna, Pippa L. Whitehouse, Geruo A, Cécile Agosta, Andreas P. Ahlstrøm, Alejandro Blazquez, William Colgan, Marcus E. Engdahl, Xavier Fettweis, Rene Forsberg, Hubert Gallée, Alex Gardner, Lin Gilbert, Noel Gourmelen, Andreas Groh, Brian C. Gunter, Christopher Harig, Veit Helm, Shfaqat Abbas Khan, Christoph Kittel, Hannes Konrad, Peter L. Langen, Benoit S. Lecavalier, Chia-Chun Liang, Bryant D. Loomis, Malcolm McMillan, Daniele Melini, Sebastian H. Mernild, Ruth Mottram, Jeremie Mouginot, Johan Nilsson, Brice Noël, Mark E. Pattle, William R. Peltier, Nadege Pie, Mònica Roca, Ingo Sasgen, Himanshu V. Save, Ki-Weon Seo, Bernd Scheuchl, Ernst J. O. Schrama, Ludwig Schröder, Sebastian B. Simonsen, Thomas Slater, Giorgio Spada, Tyler C. Sutterley, Bramha Dutt Vishwakarma, Jan Melchior van Wessem, David Wiese, Wouter van der Wal, and Bert Wouters
Earth Syst. Sci. Data, 15, 1597–1616, https://doi.org/10.5194/essd-15-1597-2023, https://doi.org/10.5194/essd-15-1597-2023, 2023
Short summary
Short summary
By measuring changes in the volume, gravitational attraction, and ice flow of Greenland and Antarctica from space, we can monitor their mass gain and loss over time. Here, we present a new record of the Earth’s polar ice sheet mass balance produced by aggregating 50 satellite-based estimates of ice sheet mass change. This new assessment shows that the ice sheets have lost (7.5 x 1012) t of ice between 1992 and 2020, contributing 21 mm to sea level rise.
Benjamin E. Smith, Brooke Medley, Xavier Fettweis, Tyler Sutterley, Patrick Alexander, David Porter, and Marco Tedesco
The Cryosphere, 17, 789–808, https://doi.org/10.5194/tc-17-789-2023, https://doi.org/10.5194/tc-17-789-2023, 2023
Short summary
Short summary
We use repeated satellite measurements of the height of the Greenland ice sheet to learn about how three computational models of snowfall, melt, and snow compaction represent actual changes in the ice sheet. We find that the models do a good job of estimating how the parts of the ice sheet near the coast have changed but that two of the models have trouble representing surface melt for the highest part of the ice sheet. This work provides suggestions for how to better model snowmelt.
Jilu Li, Fernando Rodriguez-Morales, Xavier Fettweis, Oluwanisola Ibikunle, Carl Leuschen, John Paden, Daniel Gomez-Garcia, and Emily Arnold
The Cryosphere, 17, 175–193, https://doi.org/10.5194/tc-17-175-2023, https://doi.org/10.5194/tc-17-175-2023, 2023
Short summary
Short summary
Alaskan glaciers' loss of ice mass contributes significantly to ocean surface rise. It is important to know how deeply and how much snow accumulates on these glaciers to comprehend and analyze the glacial mass loss process. We reported the observed seasonal snow depth distribution from our radar data taken in Alaska in 2018 and 2021, developed a method to estimate the annual snow accumulation rate at Mt. Wrangell caldera, and identified transition zones from wet-snow zones to ablation zones.
Raf M. Antwerpen, Marco Tedesco, Xavier Fettweis, Patrick Alexander, and Willem Jan van de Berg
The Cryosphere, 16, 4185–4199, https://doi.org/10.5194/tc-16-4185-2022, https://doi.org/10.5194/tc-16-4185-2022, 2022
Short summary
Short summary
The ice on Greenland has been melting more rapidly over the last few years. Most of this melt comes from the exposure of ice when the overlying snow melts. This ice is darker than snow and absorbs more sunlight, leading to more melt. It remains challenging to accurately simulate the brightness of the ice. We show that the color of ice simulated by Modèle Atmosphérique Régional (MAR) is too bright. We then show that this means that MAR may underestimate how fast the Greenland ice is melting.
Christoph Kittel, Charles Amory, Stefan Hofer, Cécile Agosta, Nicolas C. Jourdain, Ella Gilbert, Louis Le Toumelin, Étienne Vignon, Hubert Gallée, and Xavier Fettweis
The Cryosphere, 16, 2655–2669, https://doi.org/10.5194/tc-16-2655-2022, https://doi.org/10.5194/tc-16-2655-2022, 2022
Short summary
Short summary
Model projections suggest large differences in future Antarctic surface melting even for similar greenhouse gas scenarios and warming rates. We show that clouds containing a larger amount of liquid water lead to stronger melt. As surface melt can trigger the collapse of the ice shelves (the safety band of the Antarctic Ice Sheet), clouds could be a major source of uncertainties in projections of sea level rise.
Sébastien Doutreloup, Xavier Fettweis, Ramin Rahif, Essam Elnagar, Mohsen S. Pourkiaei, Deepak Amaripadath, and Shady Attia
Earth Syst. Sci. Data, 14, 3039–3051, https://doi.org/10.5194/essd-14-3039-2022, https://doi.org/10.5194/essd-14-3039-2022, 2022
Short summary
Short summary
This data set provides historical (1980–2014) and future (2015–2100) weather data for 12 cities in Belgium. This data set is intended for architects or building or energy designers. In particular, it makes available to all users hourly open-access weather data according to certain standards to recreate a Typical and an Extreme Meteorological Year. In addition, it provides hourly data on heatwaves from 1980 to 2100. Weather data were produced from the outputs of the MAR model simulations.
Kenneth D. Mankoff, Xavier Fettweis, Peter L. Langen, Martin Stendel, Kristian K. Kjeldsen, Nanna B. Karlsson, Brice Noël, Michiel R. van den Broeke, Anne Solgaard, William Colgan, Jason E. Box, Sebastian B. Simonsen, Michalea D. King, Andreas P. Ahlstrøm, Signe Bech Andersen, and Robert S. Fausto
Earth Syst. Sci. Data, 13, 5001–5025, https://doi.org/10.5194/essd-13-5001-2021, https://doi.org/10.5194/essd-13-5001-2021, 2021
Short summary
Short summary
We estimate the daily mass balance and its components (surface, marine, and basal mass balance) for the Greenland ice sheet. Our time series begins in 1840 and has annual resolution through 1985 and then daily from 1986 through next week. Results are operational (updated daily) and provided for the entire ice sheet or by commonly used regions or sectors. This is the first input–output mass balance estimate to include the basal mass balance.
Ruth Mottram, Nicolaj Hansen, Christoph Kittel, J. Melchior van Wessem, Cécile Agosta, Charles Amory, Fredrik Boberg, Willem Jan van de Berg, Xavier Fettweis, Alexandra Gossart, Nicole P. M. van Lipzig, Erik van Meijgaard, Andrew Orr, Tony Phillips, Stuart Webster, Sebastian B. Simonsen, and Niels Souverijns
The Cryosphere, 15, 3751–3784, https://doi.org/10.5194/tc-15-3751-2021, https://doi.org/10.5194/tc-15-3751-2021, 2021
Short summary
Short summary
We compare the calculated surface mass budget (SMB) of Antarctica in five different regional climate models. On average ~ 2000 Gt of snow accumulates annually, but different models vary by ~ 10 %, a difference equivalent to ± 0.5 mm of global sea level rise. All models reproduce observed weather, but there are large differences in regional patterns of snowfall, especially in areas with very few observations, giving greater uncertainty in Antarctic mass budget than previously identified.
Louis Le Toumelin, Charles Amory, Vincent Favier, Christoph Kittel, Stefan Hofer, Xavier Fettweis, Hubert Gallée, and Vinay Kayetha
The Cryosphere, 15, 3595–3614, https://doi.org/10.5194/tc-15-3595-2021, https://doi.org/10.5194/tc-15-3595-2021, 2021
Short summary
Short summary
Snow is frequently eroded from the surface by the wind in Adelie Land (Antarctica) and suspended in the lower atmosphere. By performing model simulations, we show firstly that suspended snow layers interact with incoming radiation similarly to a near-surface cloud. Secondly, suspended snow modifies the atmosphere's thermodynamic structure and energy exchanges with the surface. Our results suggest snow transport by the wind should be taken into account in future model studies over the region.
Cited articles
Agosta, C., Amory, C., Kittel, C., Orsi, A., Favier, V., Gallée, H., van den Broeke, M. R., Lenaerts, J. T. M., van Wessem, J. M., van de Berg, W. J., and Fettweis, X.: Estimation of the Antarctic surface mass balance using the regional climate model MAR (1979–2015) and identification of dominant processes, The Cryosphere, 13, 281–296, https://doi.org/10.5194/tc-13-281-2019, 2019.
Al-Najjar, H. A. H., Pradhan, B., Beydoun, G., Sarkar, R., Park, H.-J., and Alamri, A.: A novel method using explainable artificial intelligence (XAI)-based Shapley Additive Explanations for spatial landslide prediction using Time-Series SAR dataset, Gondwana Res., 123, 107–124, https://doi.org/10.1016/j.gr.2022.08.004, 2023.
Batunacun, Wieland, R., Lakes, T., and Nendel, C.: Using Shapley additive explanations to interpret extreme gradient boosting predictions of grassland degradation in Xilingol, China, Geosci. Model Dev., 14, 1493–1510, https://doi.org/10.5194/gmd-14-1493-2021, 2021.
Bentéjac, C., Csörgő, A., and Martínez-Muñoz, G.: A comparative analysis of gradient boosting algorithms, Artif. Intell. Rev., 54, 1937–1967, https://doi.org/10.1007/s10462-020-09896-5, 2021.
Bergstra, J. and Bengio, Y.: Random search for hyper-parameter optimization, J. Mach. Learn. Res., 13, 281–305, 2012.
Bochow, N., Hess, P., and Robinson, A.: Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperature, arXiv [preprint], https://doi.org/10.48550/arXiv.2507.22485, 2025.
Box, J. E., Fettweis, X., Stroeve, J. C., Tedesco, M., Hall, D. K., and Steffen, K.: Greenland ice sheet albedo feedback: thermodynamics and atmospheric drivers, The Cryosphere, 6, 821–839, https://doi.org/10.5194/tc-6-821-2012, 2012.
Brun, E., David, P., Sudul, M., and Brunot, G.: A numerical model to simulate snow-cover stratigraphy for operational avalanche forecasting, J. Glaciol., 38, 13–22, https://doi.org/10.3189/S0022143000009552, 1992.
Chen, T. and Guestrin, C.: XGBoost: a scalable tree boosting system, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794, https://doi.org/10.1145/2939672.2939785, 2016.
Coléou, C. and Lesaffre, B.: Irreducible water saturation in snow: experimental results in a cold laboratory, Ann. Glaciol., 26, 64–68, https://doi.org/10.3189/1998AoG26-1-64-68, 1998.
Delhasse, A., Kittel, C., Amory, C., Hofer, S., van As, D., S. Fausto, R., and Fettweis, X.: Brief communication: Evaluation of the near-surface climate in ERA5 over the Greenland Ice Sheet, The Cryosphere, 14, 957–965, https://doi.org/10.5194/tc-14-957-2020, 2020.
Descals, A., Verger, A., Yin, G., Filella, I., and Peñuelas, J.: Local interpretation of machine learning models in remote sensing with SHAP: the case of global climate constraints on photosynthesis phenology, Int. J. Remote Sens., 44, 3160–3173, https://doi.org/10.1080/01431161.2023.2217982, 2023.
Dikshit, A. and Pradhan, B.: Interpretable and explainable AI (XAI) model for spatial drought prediction, Sci. Total Environ., 801, 149797, https://doi.org/10.1016/j.scitotenv.2021.149797, 2021.
Doury, A., Somot, S., Gadat, S., Ribes, A., and Corre, L.: Regional climate model emulator based on deep learning: concept and first evaluation of a novel hybrid downscaling approach, Clim. Dynam., 60, 1751–1779, https://doi.org/10.1007/s00382-022-06343-9, 2023.
Feng, S., Cook, J. M., Anesio, A. M., Benning, L. G., and Tranter, M.: Long time series (1984–2020) of albedo variations on the Greenland ice sheet from harmonized Landsat and Sentinel 2 imagery, J. Glaciol., 69, 1225–1240, https://doi.org/10.1017/jog.2023.13, 2023.
Fettweis, X.: Reconstruction of the 1979–2006 Greenland ice sheet surface mass balance using the regional climate model MAR, The Cryosphere, 1, 21–40, https://doi.org/10.5194/tc-1-21-2007, 2007.
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.
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.
Fettweis, X., Hofer, S., Krebs-Kanzow, U., Amory, C., Aoki, T., Berends, C. J., Born, A., Box, J. E., Delhasse, A., Fujita, K., Gierz, P., Goelzer, H., Hanna, E., Hashimoto, A., Huybrechts, P., Kapsch, M.-L., King, M. D., Kittel, C., Lang, C., Langen, P. L., Lenaerts, J. T. M., Liston, G. E., Lohmann, G., Mernild, S. H., Mikolajewicz, U., Modali, K., Mottram, R. H., Niwano, M., Noël, B., Ryan, J. C., Smith, A., Streffing, J., Tedesco, M., van de Berg, W. J., van den Broeke, M., van de Wal, R. S. W., van Kampenhout, L., Wilton, D., Wouters, B., Ziemen, F., and Zolles, T.: GrSMBMIP: intercomparison of the modelled 1980–2012 surface mass balance over the Greenland Ice Sheet, The Cryosphere, 14, 3935–3958, https://doi.org/10.5194/tc-14-3935-2020, 2020.
Feurer, M., Klein, A., Eggensperger, K., Springenberg, J., Blum, M., and Hutter, F.: Efficient and robust automated machine learning, Adv. Neur. In., 28, 2962–2970, 2015.
Franco, B., Fettweis, X., Lang, C., and Erpicum, M.: Impact of spatial resolution on the modelling of the Greenland ice sheet surface mass balance between 1990–2010, using the regional climate model MAR, The Cryosphere, 6, 695–711, https://doi.org/10.5194/tc-6-695-2012, 2012.
Freund, Y. and Schapire, R. E.: A decision-theoretic generalization of on-line learning and an application to boosting, J. Comput. Syst. Sci., 55, 119–139, https://doi.org/10.1006/jcss.1997.1504, 1997.
Ghafarian, F., Wieland, R., Lüttschwager, D., and Nendel, C.: Application of extreme gradient boosting and Shapley Additive explanations to predict temperature regimes inside forests from standard open-field meteorological data, Environ. Modell. Softw., 156, 105466, https://doi.org/10.1016/j.envsoft.2022.105466, 2022.
Gholamy, A., Kreinovich, V., and Kosheleva, O.: Why 70/30 or 80/20 relation between training and testing sets: a pedagogical explanation, Departmental Technical Reports (CS), University of Texas at El Paso, https://scholarworks.utep.edu/cgi/viewcontent.cgi?article=2202&context=cs_techrep (last access: 21 June 2026), 2018.
Grinsztajn, L., Oyallon, E., and Varoquaux, G.: Why do tree-based models still outperform deep learning on typical tabular data?, Adv. Neur. In., 35, 507–520, 2022.
Head, T., MechCoder, G., Shcherbatyi, I., F, Zé Vinícius, C. Schröder, N. Campos, Young, T., Cereda, S., Fan, T. , Shi, K. (KJ), Schwabedal, J., Hvass-Labs, Pak, M., and Fabisch, A.: scikit-optimize/scikit-optimize: v0.5.2, Zenodo [code], https://doi.org/10.5281/zenodo.1207017, 2018.
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., De Chiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R. J., Hólm, E., Janisková, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., de Rosnay, P., Rozum, I., Vamborg, F., Villaume, S., and Thépaut, J.-N.: The ERA5 global reanalysis, Q. J. Roy. Meteor. Soc., 146, 1999–2049, https://doi.org/10.1002/qj.3803, 2020.
Hofer, S., Tedstone, A. J., Fettweis, X., and Bamber, J. L.: Decreasing cloud cover drives the recent mass loss on the Greenland Ice Sheet, Science Advances, 3, e1700584, https://doi.org/10.1126/sciadv.1700584, 2017.
Kim, J. H.: Multicollinearity and misleading statistical results, Korean Journal of Anesthesiology, 72, 558–569, https://doi.org/10.4097/kja.19087, 2019.
Koo, Y., Xie, H., Kurtz, N. T., Ackley, S. F., and Wang, W.: Sea ice surface type classification of ICESat-2 ATL07 data by using data-driven machine learning model: Ross Sea, Antarctic as an example, Remote Sens. Environ., 296, 113726, https://doi.org/10.1016/j.rse.2023.113726, 2023.
Langen, P. L., Fausto, R. S., Vandecrux, B., Mottram, R. H., and Box, J. E.: Liquid water flow and retention on the Greenland ice sheet in the regional climate model HIRHAM5: local and large-scale impacts, Frontiers in Earth Science, 4, 110, https://doi.org/10.3389/feart.2016.00110, 2017.
Larour, E., Seroussi, H., Morlighem, M., and Rignot, E.: Continental scale, high order, high spatial resolution, ice sheet modeling using the Ice Sheet System Model (ISSM), J. Geophys. Res.-Earth, 117, F01022, https://doi.org/10.1029/2011JF002140, 2012.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
Lenaerts, J. T. M., van den Broeke, M. R., van Angelen, J. H., van Meijgaard, E., and Déry, S. J.: Drifting snow climate of the Greenland ice sheet: a study with a regional climate model, The Cryosphere, 6, 891–899, https://doi.org/10.5194/tc-6-891-2012, 2012.
Lenaerts, J. T. M., Medley, B., van den Broeke, M. R., and Wouters, B.: Observing and modeling ice sheet surface mass balance, Rev. Geophys., 57, 376–420, https://doi.org/10.1029/2018RG000622, 2019.
Li, K., Wang, F., Yang, L., and Liu, R.: Deep feature screening: feature selection for ultra high-dimensional data via deep neural networks, Neurocomputing, 538, 126186, https://doi.org/10.1016/j.neucom.2023.03.047, 2023.
Lundberg, S. and Lee, S.-I.: A unified approach to interpreting model predictions, Adv. Neur. In., 30, 4765–4774, 2017.
Lütjens, B., Alexander, P., Antwerpen, R., Widmann, T., Cervone, G., and Tedesco, M.: MeltwaterBench: deep learning for spatiotemporal downscaling of surface meltwater, arXiv [preprint], https://doi.org/10.48550/arXiv.2512.12142, 2025.
Ma, M., Zhao, G., He, B., Li, Q., Dong, H., Wang, S., and Wang, Z.: XGBoost-based method for flash flood risk assessment, J. Hydrol., 598, 126382, https://doi.org/10.1016/j.jhydrol.2021.126382, 2021.
Materia, S., Palma García, L., van Straaten, C., Sungmin, O., Mamalakis, A., Cavicchia, L., Coumou, D., de Luca, P., Kretschmer, M., and Donat, M.: Artificial intelligence for climate prediction of extremes: state of the art, challenges, and future perspectives, Wiley Interdisciplinary Reviews: Climate Change, 15, e914, https://doi.org/10.1002/wcc.914, 2024.
Mayr, A., Binder, H., Gefeller, O., and Schmid, M.: The evolution of boosting algorithms, Method. Inform. Med., 53, 419–427, https://doi.org/10.3414/ME13-01-0122, 2018.
Mioduszewski, J. R., Rennermalm, A. K., Robinson, D. A., and Mote, T. L.: Attribution of snowmelt onset in Northern Canada, J. Geophys. Res.-Atmos., 119, 9638–9653, https://doi.org/10.1002/2013JD021024, 2014.
Neff, W., Compo, G. P., Ralph, F. M., and Shupe, M. D.: Continental heat anomalies and the extreme melting of the Greenland ice surface in 2012 and 1889, J. Geophys. Res.-Atmos., 119, 6520–6536, https://doi.org/10.1002/2014JD021470, 2014.
Nghiem, S. V., Hall, D. K., Mote, T. L., Tedesco, M., Albert, M. R., Keegan, K., Shuman, C. A., DiGirolamo, N. E., and Neumann, G.: The extreme melt across the Greenland ice sheet in 2012, Geophys. Res. Lett., 39, L20502, https://doi.org/10.1029/2012GL053611, 2012.
Noël, B., van de Berg, W. J., van Meijgaard, E., Kuipers Munneke, P., van de Wal, R. S. W., and van den Broeke, M. R.: Evaluation of the updated regional climate model RACMO2.3: summer snowfall impact on the Greenland Ice Sheet, The Cryosphere, 9, 1831–1844, https://doi.org/10.5194/tc-9-1831-2015, 2015.
Noël, B., van de Berg, W. J., van Wessem, J. M., van Meijgaard, E., van As, D., Lenaerts, J. T. M., Lhermitte, S., Kuipers Munneke, P., Smeets, C. J. P. P., van Ulft, L. H., van de Wal, R. S. W., and van den Broeke, M. R.: Modelling the climate and surface mass balance of polar ice sheets using RACMO2 – Part 1: Greenland (1958–2016), The Cryosphere, 12, 811–831, https://doi.org/10.5194/tc-12-811-2018, 2018.
racheetmatai: racheetmatai/MAR_emulator: MAR-IA v1.0.0 – Code accompanying the MAR-IA manuscript (v1.0.0), Zenodo [code], https://doi.org/10.5281/zenodo.20838627, 2026.
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., and Prabhat: Deep learning and process understanding for data-driven Earth system science, Nature, 566, 195–204, https://doi.org/10.1038/s41586-019-0912-1, 2019.
Rohmer, J., Thieblemont, R., Le Cozannet, G., Goelzer, H., and Durand, G.: Improving interpretation of sea-level projections through a machine-learning-based local explanation approach, The Cryosphere, 16, 4637–4657, https://doi.org/10.5194/tc-16-4637-2022, 2022.
Schlager, E., Scher, S., Mottram, R. H., and Langen, P. L.: Learning to melt: Emulating Greenland surface melt from a polar RCM with machine learning, The Cryosphere, 20, 3313–3343, https://doi.org/10.5194/tc-20-3313-2026, 2026.
Sivakumar, M., Parthasarathy, S., and Padmapriya, T.: Trade-off between training and testing ratio in machine learning for medical image processing, PeerJ Computer Science, 10, e2245, https://doi.org/10.7717/peerj-cs.2245, 2024.
Smith, B. E., Medley, B., Fettweis, X., Sutterley, T., Alexander, P., Porter, D., and Tedesco, M.: Evaluating Greenland surface-mass-balance and firn-densification data using ICESat-2 altimetry, The Cryosphere, 17, 789–808, https://doi.org/10.5194/tc-17-789-2023, 2023.
Snoek, J., Larochelle, H., and Adams, R. P.: Practical Bayesian optimization of machine learning algorithms, Adv. Neur. In., 25, 2951–2959, 2012.
Tedesco, M., Doherty, S., Fettweis, X., Alexander, P., Jeyaratnam, J., and Stroeve, J.: The darkening of the Greenland ice sheet: trends, drivers, and projections (1981–2100), The Cryosphere, 10, 477–496, https://doi.org/10.5194/tc-10-477-2016, 2016a.
Tedesco, M., Mote, T., Fettweis, X., Hanna, E., Jeyaratnam, J., Booth, J. F., Datta, R., and Briggs, K.: Arctic cut-off high drives the poleward shift of a new Greenland melting record, Nat. Commun., 7, 11723, https://doi.org/10.1038/ncomms11723, 2016b.
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.
Tedesco, M., Matai, R., and Fettweis, X.: MAR_ERA5_dataset_1979_2024_Greenland, Zenodo [data set], https://doi.org/10.5281/zenodo.17942115, 2025.
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.
Veldhuijsen, S. B. M., van de Berg, W. J., Kuipers Munneke, P., Hansen, N., Boberg, F., Kittel, C., Amory, C., and van den Broeke, M. R.: Emulating the expansion of Antarctic perennial firn aquifers in the 21st century, The Cryosphere, 19, 5157–5173, https://doi.org/10.5194/tc-19-5157-2025, 2025.
Wang, W., Zender, C. S., van As, D., Fausto, R. S., and Laffin, M. K.: Greenland surface melt dominated by solar and sensible heating, Geophys. Res. Lett., 48, e2020GL090653, https://doi.org/10.1029/2020GL090653, 2021.
Xu, J., Wu, C., Li, Y.-F., Danoy, G., and Bouvry, P.: Survey and taxonomy: the role of data-centric AI in transformer-based time series forecasting, arXiv [preprint], https://doi.org/10.48550/arXiv.2407.19784, 2024.
Zamani Joharestani, M., Cao, C., Ni, X., Bashir, B., and Talebiesfandarani, S.: PM2.5 prediction based on random forest, XGBoost, and deep learning using multisource remote sensing data, Atmosphere, 10, 373, https://doi.org/10.3390/atmos10070373, 2019.
Zhang, Q.-L., Ding, M.-H., van den Broeke, M. R., Noël, B., Fettweis, X., Wang, S., Sun, W.-J., You, Q.-L., Xiao, C.-D., Qin, D.-H., and Huai, B.-J.: Variations in Greenland surface melt and extreme events from 1958 to 2023, Advances in Climate Change Research, 16, 910–921, https://doi.org/10.1016/j.accre.2025.05.004, 2025.
Short summary
We developed a machine learning emulator of a climate model simulating melting over Greenland that performs as well as the original model but it is much faster. We show that this emulator can be used as powerful tools to complement regional climate models by enabling computationally efficient ensemble simulations and physically interpretable attribution of past and future Greenland surface melt. Development of regional climate models should go hand in hand with ML-based tools.
We developed a machine learning emulator of a climate model simulating melting over Greenland...
