Articles | Volume 19, issue 13
https://doi.org/10.5194/gmd-19-5907-2026
© 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/gmd-19-5907-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
07 Jul 2026
Development and technical paper |
| 07 Jul 2026
| 07 Jul 2026
Contribution of physical latent knowledge to the emulation of an atmospheric physics model: a study based on the LMDZ Atmospheric General Circulation Model
Ségolène Crossouard
CORRESPONDING AUTHOR
Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL), CEA-CNRS-UVSQ-Université Paris-Saclay, 91190 Gif-sur-Yvette, France
Soulivanh Thao
Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL), CEA-CNRS-UVSQ-Université Paris-Saclay, 91190 Gif-sur-Yvette, France
Thomas Dubos
Laboratoire de Météorologie Dynamique (LMD-IPSL), Ecole Polytechnique, 91120 Palaiseau, France
Masa Kageyama
Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL), CEA-CNRS-UVSQ-Université Paris-Saclay, 91190 Gif-sur-Yvette, France
Mathieu Vrac
Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL), CEA-CNRS-UVSQ-Université Paris-Saclay, 91190 Gif-sur-Yvette, France
Yann Meurdesoif
Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL), CEA-CNRS-UVSQ-Université Paris-Saclay, 91190 Gif-sur-Yvette, France
Related authors
No articles found.
Louise C. Sime, Rachel Diamond, Christian Stepanek, Chris Brierley, David Schroeder, Masa Kageyama, Matthew Pollock, Irene Malmierca-Vallet, Ed Blockley, Alex West, Danny Feltham, Jeff Ridley, Pascale Braconnot, Charles J. R. Williams, Xiaoxu Shi, Bette L. Otto-Bliesner, Sophia I. Macarewich, Silvana Ramos Buarque, Qiong Zhang, Allegra LeGrande, Weipeng Zheng, Dabang Jiang, Polina Morozova, Chuncheng Guo, Zhongshi Zhang, Nicholas Yeung, Laurie Menviel, Sandeep Narayanasetti, Masakazu Yoshimori, Olivia Reeves, and Anni Zhao
Geosci. Model Dev., 19, 5881–5905, https://doi.org/10.5194/gmd-19-5881-2026, https://doi.org/10.5194/gmd-19-5881-2026, 2026
Short summary
Short summary
The Arctic may have lost its summer sea ice 127,000 years ago during a naturally warm period in Earth’s past. Climate models can be tested by recreating those conditions, with similar sunlight and greenhouse gas levels. Analysing the large sea ice changes in these simulations helps us understand how the Arctic might respond in the near future and improves how we test and trust our climate models.
Grégoire Jacquemin, Mathieu Vrac, Xavier Freulon, and Denis Allard
EGUsphere, https://doi.org/10.5194/egusphere-2026-3269, https://doi.org/10.5194/egusphere-2026-3269, 2026
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary
Short summary
The outputs of climate simulations can be used to project the evolution of compound events in terms of frequency, but they are known to be statistically biased. This study evaluates three bias correction methods on two extremal statistics. Results show that bias correction is necessary to improve the statistical characterization of compound events. This work also reveals that the evolution of compound events in the simulations is preserved by the bias correction methods most of the time.
Clara Naldesi, Nathalie Bertrand, Davide Faranda, and Mathieu Vrac
EGUsphere, https://doi.org/10.5194/egusphere-2026-1466, https://doi.org/10.5194/egusphere-2026-1466, 2026
Short summary
Short summary
The public increasingly needs to know whether and how climate change influences specific extreme events. ClimaMeter is a scientific tool designed to address this demand. This paper reviews the ClimaMeter methodology, focusing on how it estimates the relative roles of natural variability and climate change. We propose a more flexible and general approach within the same framework, enabling a more nuanced assessment of natural variability.
Yoann Robin, Mathieu Vrac, Aurélien Ribes, Occitane Barbaux, and Philippe Naveau
Geosci. Model Dev., 19, 2349–2372, https://doi.org/10.5194/gmd-19-2349-2026, https://doi.org/10.5194/gmd-19-2349-2026, 2026
Short summary
Short summary
We describe an improved method and the associated free licensed package ANKIALE (ANalysis of Klimate with bayesian Inference: AppLication to extreme Events) for estimating the statistics of temperature extremes. This method uses climate model simulations (including multiple scenarios simultaneously) to provide a prior of the real-world changes, constrained by the observations. The method and the tool are illustrated via an application to temperature over Europe until 2100, for four scenarios.
Greta Cazzaniga, Anastasia Akakpo-Numado, Patrick Brockmann, Adrien Burq, Mathieu Vrac, and Davide Faranda
EGUsphere, https://doi.org/10.5194/egusphere-2026-1175, https://doi.org/10.5194/egusphere-2026-1175, 2026
Short summary
Short summary
Extreme weather events are becoming more frequent and severe, creating a strong need for rapid and reliable information. We developed an open tool that automatically detects and tracks heatwaves, cold spells, heavy rain, and strong winds across Europe, both in real time and in past decades. By comparing current events with long historical records, the tool shows how unusual an event is and reveals clear increases in heatwaves, while other hazards show more mixed changes.
Joséphine Schmutz, Mathieu Vrac, Bastien François, and Burak Bulut
Nat. Hazards Earth Syst. Sci., 26, 881–900, https://doi.org/10.5194/nhess-26-881-2026, https://doi.org/10.5194/nhess-26-881-2026, 2026
Short summary
Short summary
In recent years, Europe has faced severe hot and dry events affecting biodiversity, agriculture, and health. Understanding past significant variation in their occurrence is key for adaptation. This paper identifies emerging hotspots in Europe and North Africa. Since the 1970s, the Iberian Peninsula, Maghreb, and Central Europe have seen more frequent events, driven by rising temperature maxima, while Eastern Europe has experienced a decline due to changes in drought.
Guillaume Evin, Benoit Hingray, Guillaume Thirel, Agnès Ducharne, Laurent Strohmenger, Lola Corre, Yves Tramblay, Jean-Philippe Vidal, Jérémie Bonneau, François Colleoni, Joël Gailhard, Florence Habets, Frédéric Hendrickx, Louis Héraut, Peng Huang, Matthieu Le Lay, Claire Magand, Paola Marson, Céline Monteil, Simon Munier, Alix Reverdy, Jean-Michel Soubeyroux, Yoann Robin, Jean-Pierre Vergnes, Mathieu Vrac, and Eric Sauquet
Hydrol. Earth Syst. Sci., 30, 1023–1051, https://doi.org/10.5194/hess-30-1023-2026, https://doi.org/10.5194/hess-30-1023-2026, 2026
Short summary
Short summary
Explore2 provides hydrological projections for 1,735 French catchments. Using QUALYPSO (Quasi-Ergodic Analysis of Climate Projections Using Data Augmentation), this study assesses uncertainties, including internal variability. By the end of the century, low flows are projected to decline in southern France under high emissions, while other indicators remain uncertain. Emission scenarios and regional climate models are key uncertainty sources. Internal variability is often as large as climate-driven changes.
Héloïse Barathieu, Thibaut Caley, Masa Kageyama, Didier Swingedouw, and Pascale Braconnot
EGUsphere, https://doi.org/10.5194/egusphere-2026-254, https://doi.org/10.5194/egusphere-2026-254, 2026
Short summary
Short summary
This study evaluates climate model simulations of the Last Glacial Maximum using ocean surface density reconstructions from foraminiferal shells δ¹⁸O. Models capture global patterns but regional climate changes are less well simulated, especially in the North Indian Ocean. Tropical differences between reconstructions and model simulations are mainly driven by changes in ocean salinity linked to precipitation.
Valentin Wiener, Étienne Vignon, Thomas Caton Harrison, Christophe Genthon, Felipe Toledo, Guylaine Canut-Rocafort, Yann Meurdesoif, and Alexis Berne
Weather Clim. Dynam., 6, 1605–1627, https://doi.org/10.5194/wcd-6-1605-2025, https://doi.org/10.5194/wcd-6-1605-2025, 2025
Short summary
Short summary
Katabatic winds are a key feature of the climate of Antarctica, but substantial biases remain in their representation in atmospheric models. This study investigates a katabatic wind event in an atmospheric circulation model using in-situ observations. The framework allows to disentangle which part of the bias is due to horizontal resolution, to parameter calibration and to structural deficiencies in the model. We underline in particular the need to refine the physics of the model snow cover.
Pradeebane Vaittinada Ayar, Stella Bourdin, Davide Faranda, and Mathieu Vrac
Nat. Hazards Earth Syst. Sci., 25, 4655–4672, https://doi.org/10.5194/nhess-25-4655-2025, https://doi.org/10.5194/nhess-25-4655-2025, 2025
Short summary
Short summary
Tracking tropical cyclones (TCs) remains a matter of interest for investigating observed and simulated tropical cyclones. In this study, Random Forest (RF), a machine learning approach, is considered to track TCs. RF associates the TC occurrence or absence with different atmospheric configurations. Compared to trackers found in the literature, it shows similar performance for tracking TCs, better control over false alarms, more flexibility, and reveals key variables for TCs' detection.
Germain Bénard, Marion Gehlen, and Mathieu Vrac
EGUsphere, https://doi.org/10.5194/egusphere-2025-4680, https://doi.org/10.5194/egusphere-2025-4680, 2025
Short summary
Short summary
Climate change is transforming ocean ecosystem dynamics. We used causality methods to study how the relationships between ocean physics and biogeochemistry will change in the North Atlantic over the next century. By analyzing five different climate models, we discovered that environmental drivers' influence on ocean productivity evolves in complex ways under global warming. One environmental driver can become of major importance while others can become irrelevant.
Paul C. Astagneau, Raul R. Wood, Mathieu Vrac, Sven Kotlarski, Pradeebane Vaittinada Ayar, Bastien François, and Manuela I. Brunner
Hydrol. Earth Syst. Sci., 29, 5695–5718, https://doi.org/10.5194/hess-29-5695-2025, https://doi.org/10.5194/hess-29-5695-2025, 2025
Short summary
Short summary
To study floods and droughts that are likely to change in the future, we use climate projections from climate models. However, we first need to adjust the systematic biases of these projections at the catchment scale before using them in hydrological models. Our study compares statistical methods that can adjust these biases but specifically for climate projections that enable a quantification of internal climate variability. We provide recommendations on the most appropriate methods.
Denis Allard, Mathieu Vrac, Bastien François, and Iñaki García de Cortázar-Atauri
Hydrol. Earth Syst. Sci., 29, 4711–4738, https://doi.org/10.5194/hess-29-4711-2025, https://doi.org/10.5194/hess-29-4711-2025, 2025
Short summary
Short summary
Atmospheric variables from climate models often present biases relative to the past. In order to use these models to assess the impact of climate change on processes of interest, it is necessary to correct these biases. We tested several Multivariate Bias Correction Methods (MBCMs) for 5 physical variables that are input variables for 4 process models. We provide recommendations regarding the use of MBCMs when multivariate and time dependent processes are involved.
Robin Noyelle, Davide Faranda, Yoann Robin, Mathieu Vrac, and Pascal Yiou
Weather Clim. Dynam., 6, 817–839, https://doi.org/10.5194/wcd-6-817-2025, https://doi.org/10.5194/wcd-6-817-2025, 2025
Short summary
Short summary
Properties of extreme meteorological and climatological events are changing under human-caused climate change. Extreme event attribution methods seek to estimate the contribution of global warming in the probability and intensity changes of extreme events. Here we propose a procedure to estimate these quantities for the flow analogue method, which compares the observed event to similar events in the past.
Duncan Pappert, Alexandre Tuel, Dim Coumou, Mathieu Vrac, and Olivia Martius
Weather Clim. Dynam., 6, 769–788, https://doi.org/10.5194/wcd-6-769-2025, https://doi.org/10.5194/wcd-6-769-2025, 2025
Short summary
Short summary
This study compares the dynamical structures that characterise long-lasting (persistent) and short hot spells in Western Europe. We find differences in large-scale atmospheric flow patterns during the events and particular soil moisture evolutions, which can account for the variation in event duration. There is variability in how drivers combine in individual events. Understanding persistent heat extremes can help improve their representation in models and ultimately their prediction.
Germain Bénard, Marion Gehlen, and Mathieu Vrac
Earth Syst. Dynam., 16, 1085–1102, https://doi.org/10.5194/esd-16-1085-2025, https://doi.org/10.5194/esd-16-1085-2025, 2025
Short summary
Short summary
We introduce a novel approach to compare Earth system model output using a causality-based approach. The analysis of interactions between atmospheric, oceanic and biogeochemical variables in the North Atlantic subpolar gyre highlights the dynamics of each model. This method reveals potential underlying causes of model differences, offering a tool for enhanced model evaluation and improved understanding of complex Earth system dynamics under past and future climates.
Davide Faranda, Gabriele Messori, Erika Coppola, Tommaso Alberti, Mathieu Vrac, Flavio Pons, Pascal Yiou, Marion Saint Lu, Andreia N. S. Hisi, Patrick Brockmann, Stavros Dafis, Gianmarco Mengaldo, and Robert Vautard
Weather Clim. Dynam., 5, 959–983, https://doi.org/10.5194/wcd-5-959-2024, https://doi.org/10.5194/wcd-5-959-2024, 2024
Short summary
Short summary
We introduce ClimaMeter, a tool offering real-time insights into extreme-weather events. Our tool unveils how climate change and natural variability affect these events, affecting communities worldwide. Our research equips policymakers and the public with essential knowledge, fostering informed decisions and enhancing climate resilience. We analysed two distinct events, showcasing ClimaMeter's global relevance.
Laurent Menut, Arineh Cholakian, Romain Pennel, Guillaume Siour, Sylvain Mailler, Myrto Valari, Lya Lugon, and Yann Meurdesoif
Geosci. Model Dev., 17, 5431–5457, https://doi.org/10.5194/gmd-17-5431-2024, https://doi.org/10.5194/gmd-17-5431-2024, 2024
Short summary
Short summary
A new version of the CHIMERE model is presented. This version contains both computational and physico-chemical changes. The computational changes make it easy to choose the variables to be extracted as a result, including values of maximum sub-hourly concentrations. Performance tests show that the model is 1.5 to 2 times faster than the previous version for the same setup. Processes such as turbulence, transport schemes and dry deposition have been modified and updated.
Mathieu Vrac, Denis Allard, Grégoire Mariéthoz, Soulivanh Thao, and Lucas Schmutz
Earth Syst. Dynam., 15, 735–762, https://doi.org/10.5194/esd-15-735-2024, https://doi.org/10.5194/esd-15-735-2024, 2024
Short summary
Short summary
We aim to combine multiple global climate models (GCMs) to enhance the robustness of future projections. We introduce a novel approach, called "α pooling", aggregating the cumulative distribution functions (CDFs) of the models into a CDF more aligned with historical data. The new CDFs allow us to perform bias adjustment of all the raw climate simulations at once. Experiments with European temperature and precipitation demonstrate the superiority of this approach over conventional techniques.
Moctar Dembélé, Mathieu Vrac, Natalie Ceperley, Sander J. Zwart, Josh Larsen, Simon J. Dadson, Grégoire Mariéthoz, and Bettina Schaefli
Proc. IAHS, 385, 121–127, https://doi.org/10.5194/piahs-385-121-2024, https://doi.org/10.5194/piahs-385-121-2024, 2024
Short summary
Short summary
This study assesses the impact of climate change on the timing, seasonality and magnitude of mean annual minimum (MAM) flows and annual maximum flows (AMF) in the Volta River basin (VRB). Several climate change projection data are use to simulate river flow under multiple greenhouse gas emission scenarios. Future projections show that AMF could increase with various magnitude but negligible shift in time across the VRB, while MAM could decrease with up to 14 days of delay in occurrence.
Justin L. Willson, Kevin A. Reed, Christiane Jablonowski, James Kent, Peter H. Lauritzen, Ramachandran Nair, Mark A. Taylor, Paul A. Ullrich, Colin M. Zarzycki, David M. Hall, Don Dazlich, Ross Heikes, Celal Konor, David Randall, Thomas Dubos, Yann Meurdesoif, Xi Chen, Lucas Harris, Christian Kühnlein, Vivian Lee, Abdessamad Qaddouri, Claude Girard, Marco Giorgetta, Daniel Reinert, Hiroaki Miura, Tomoki Ohno, and Ryuji Yoshida
Geosci. Model Dev., 17, 2493–2507, https://doi.org/10.5194/gmd-17-2493-2024, https://doi.org/10.5194/gmd-17-2493-2024, 2024
Short summary
Short summary
Accurate simulation of tropical cyclones (TCs) is essential to understanding their behavior in a changing climate. One way this is accomplished is through model intercomparison projects, where results from multiple climate models are analyzed to provide benchmark solutions for the wider climate modeling community. This study describes and analyzes the previously developed TC test case for nine climate models in an intercomparison project, providing solutions that aid in model development.
Zoé Lloret, Frédéric Chevallier, Anne Cozic, Marine Remaud, and Yann Meurdesoif
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2023-140, https://doi.org/10.5194/gmd-2023-140, 2023
Revised manuscript not accepted
Short summary
Short summary
In this study, we evaluate the performance of a new model coupling, ICO, for simulating atmospheric carbon dioxide (CO2) transport. Using an unstructured grid, our model accurately captures seasonal CO2 variations at surface stations. The model exhibits comparable accuracy to a reference configuration and offers advantages in computational speed and storage. This highlights the importance of advanced modeling approaches and high-resolution grids in refining climate models.
Xin Ren, Daniel J. Lunt, Erica Hendy, Anna von der Heydt, Ayako Abe-Ouchi, Bette Otto-Bliesner, Charles J. R. Williams, Christian Stepanek, Chuncheng Guo, Deepak Chandan, Gerrit Lohmann, Julia C. Tindall, Linda E. Sohl, Mark A. Chandler, Masa Kageyama, Michiel L. J. Baatsen, Ning Tan, Qiong Zhang, Ran Feng, Stephen Hunter, Wing-Le Chan, W. Richard Peltier, Xiangyu Li, Youichi Kamae, Zhongshi Zhang, and Alan M. Haywood
Clim. Past, 19, 2053–2077, https://doi.org/10.5194/cp-19-2053-2023, https://doi.org/10.5194/cp-19-2053-2023, 2023
Short summary
Short summary
We investigate the Maritime Continent climate in the mid-Piacenzian warm period and find it is warmer and wetter and the sea surface salinity is lower compared with preindustrial period. Besides, the fresh and warm water transfer through the Maritime Continent was stronger. In order to avoid undue influence from closely related models in the multimodel results, we introduce a new metric, the multi-cluster mean, which could reveal spatial signals that are not captured by the multimodel mean.
Léa Terray, Emmanuelle Stoetzel, Eslem Ben Arous, Masa Kageyama, Raphaël Cornette, and Pascale Braconnot
Clim. Past, 19, 1245–1263, https://doi.org/10.5194/cp-19-1245-2023, https://doi.org/10.5194/cp-19-1245-2023, 2023
Short summary
Short summary
The reconstruction of paleoenvironments has long been a subject of great interest, particularly to study past biodiversity. Paleoenvironmental proxies often show inconsistencies, and age estimations can vary depending on the method used. We demonstrate the ability of paleoclimate simulations to address these discrepancies, illustrating the strong potential of our cross-disciplinary consistency approach to refine the context of archeological and paleontological sites.
Cedric Gacial Ngoungue Langue, Christophe Lavaysse, Mathieu Vrac, and Cyrille Flamant
Nat. Hazards Earth Syst. Sci., 23, 1313–1333, https://doi.org/10.5194/nhess-23-1313-2023, https://doi.org/10.5194/nhess-23-1313-2023, 2023
Short summary
Short summary
Heat waves (HWs) are climatic hazards that affect the planet. We assess here uncertainties encountered in the process of HW detection and analyse their recent trends in West Africa using reanalysis data. Three types of uncertainty have been investigated. We identified 6 years with higher frequency of HWs, possibly due to higher sea surface temperatures in the equatorial Atlantic. We noticed an increase in HW characteristics during the last decade, which could be a consequence of climate change.
Bastien François and Mathieu Vrac
Nat. Hazards Earth Syst. Sci., 23, 21–44, https://doi.org/10.5194/nhess-23-21-2023, https://doi.org/10.5194/nhess-23-21-2023, 2023
Short summary
Short summary
Compound events (CEs) result from a combination of several climate phenomena. In this study, we propose a new methodology to assess the time of emergence of CE probabilities and to quantify the contribution of marginal and dependence properties of climate phenomena to the overall CE probability changes. By applying our methodology to two case studies, we show the importance of considering changes in both marginal and dependence properties for future risk assessments related to CEs.
Antoine Grisart, Mathieu Casado, Vasileios Gkinis, Bo Vinther, Philippe Naveau, Mathieu Vrac, Thomas Laepple, Bénédicte Minster, Frederic Prié, Barbara Stenni, Elise Fourré, Hans Christian Steen-Larsen, Jean Jouzel, Martin Werner, Katy Pol, Valérie Masson-Delmotte, Maria Hoerhold, Trevor Popp, and Amaelle Landais
Clim. Past, 18, 2289–2301, https://doi.org/10.5194/cp-18-2289-2022, https://doi.org/10.5194/cp-18-2289-2022, 2022
Short summary
Short summary
This paper presents a compilation of high-resolution (11 cm) water isotopic records, including published and new measurements, for the last 800 000 years from the EPICA Dome C ice core, Antarctica. Using this new combined water isotopes (δ18O and δD) dataset, we study the variability and possible influence of diffusion at the multi-decadal to multi-centennial scale. We observe a stronger variability at the onset of the interglacial interval corresponding to a warm period.
Meriem Krouma, Pascal Yiou, Céline Déandreis, and Soulivanh Thao
Geosci. Model Dev., 15, 4941–4958, https://doi.org/10.5194/gmd-15-4941-2022, https://doi.org/10.5194/gmd-15-4941-2022, 2022
Short summary
Short summary
We evaluated the skill of a stochastic weather generator (SWG) to forecast precipitation at different time scales and in different areas of western Europe from analogs of Z500 hPa. The SWG has the skill to simulate precipitation for 5 and 10 d. We found that forecast weaknesses can be associated with specific weather patterns. The comparison with ECMWF forecasts confirms the skill of our model. This work is important because it provides information about weather forecasts over specific areas.
Miriam D'Errico, Flavio Pons, Pascal Yiou, Soulivanh Tao, Cesare Nardini, Frank Lunkeit, and Davide Faranda
Earth Syst. Dynam., 13, 961–992, https://doi.org/10.5194/esd-13-961-2022, https://doi.org/10.5194/esd-13-961-2022, 2022
Short summary
Short summary
Climate change is already affecting weather extremes. In a warming climate, we will expect the cold spells to decrease in frequency and intensity. Our analysis shows that the frequency of circulation patterns leading to snowy cold-spell events over Italy will not decrease under business-as-usual emission scenarios, although the associated events may not lead to cold conditions in the warmer scenarios.
Marie Sicard, Masa Kageyama, Sylvie Charbit, Pascale Braconnot, and Jean-Baptiste Madeleine
Clim. Past, 18, 607–629, https://doi.org/10.5194/cp-18-607-2022, https://doi.org/10.5194/cp-18-607-2022, 2022
Short summary
Short summary
The Last Interglacial (129–116 ka) is characterised by an increased summer insolation over the Arctic region, which leads to a strong temperature rise. The aim of this study is to identify and quantify the main processes and feedback causing this Arctic warming. Using the IPSL-CM6A-LR model, we investigate changes in the energy budget relative to the pre-industrial period. We highlight the crucial role of Arctic sea ice cover, ocean and clouds on the Last Interglacial Arctic warming.
Moctar Dembélé, Mathieu Vrac, Natalie Ceperley, Sander J. Zwart, Josh Larsen, Simon J. Dadson, Grégoire Mariéthoz, and Bettina Schaefli
Hydrol. Earth Syst. Sci., 26, 1481–1506, https://doi.org/10.5194/hess-26-1481-2022, https://doi.org/10.5194/hess-26-1481-2022, 2022
Short summary
Short summary
Climate change impacts on water resources in the Volta River basin are investigated under various global warming scenarios. Results reveal contrasting changes in future hydrological processes and water availability, depending on greenhouse gas emission scenarios, with implications for floods and drought occurrence over the 21st century. These findings provide insights for the elaboration of regional adaptation and mitigation strategies for climate change.
Léa Terray, Masa Kageyama, Emmanuelle Stoetzel, Eslem Ben Arous, Raphaël Cornette, and Pascale Braconnot
Clim. Past Discuss., https://doi.org/10.5194/cp-2021-185, https://doi.org/10.5194/cp-2021-185, 2022
Manuscript not accepted for further review
Short summary
Short summary
To reconstruct the paleoenvironmental and chronological context of archaeo/paleontological sites is a key step to understand the evolutionary history of past organisms. Paleoenvironmental proxies often show inconsistencies and age estimations can vary depending on the method used. We show the potential of paleoclimate simulations to address those discrepancies, illustrating the strong potential of our cross-disciplinary approach to refine the context of archaeo/paleontological sites.
Yoann Robin and Mathieu Vrac
Earth Syst. Dynam., 12, 1253–1273, https://doi.org/10.5194/esd-12-1253-2021, https://doi.org/10.5194/esd-12-1253-2021, 2021
Short summary
Short summary
We propose a new multivariate downscaling and bias correction approach called
time-shifted multivariate bias correction, which aims to correct temporal dependencies in addition to inter-variable and spatial ones. Our method is evaluated in a
perfect model experimentcontext where simulations are used as pseudo-observations. The results show a large reduction of the biases in the temporal properties, while inter-variable and spatial dependence structures are still correctly adjusted.
Cedric G. Ngoungue Langue, Christophe Lavaysse, Mathieu Vrac, Philippe Peyrillé, and Cyrille Flamant
Weather Clim. Dynam., 2, 893–912, https://doi.org/10.5194/wcd-2-893-2021, https://doi.org/10.5194/wcd-2-893-2021, 2021
Short summary
Short summary
This work assesses the forecast of the temperature over the Sahara, a key driver of the West African Monsoon, at a seasonal timescale. The seasonal models are able to reproduce the climatological state and some characteristics of the temperature during the rainy season in the Sahel. But, because of errors in the timing, the forecast skill scores are significant only for the first 4 weeks.
Anna Denvil-Sommer, Marion Gehlen, and Mathieu Vrac
Ocean Sci., 17, 1011–1030, https://doi.org/10.5194/os-17-1011-2021, https://doi.org/10.5194/os-17-1011-2021, 2021
Short summary
Short summary
In this work we explored design options for a future Atlantic-scale observational network enabling the release of carbon system estimates by combining data streams from various platforms. We used outputs of a physical–biogeochemical global ocean model at sites of real-world observations to reconstruct surface ocean pCO2 by applying a non-linear feed-forward neural network. The results provide important information for future BGC-Argo deployment, i.e. important regions and the number of floats.
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, https://www.tensorflow.org/ (last access: 13 April 2026), 2015. a
Arnold, C., Sharma, S., Weigel, T., and Greenberg, D. S.: Efficient and stable coupling of the SuperdropNet deep-learning-based cloud microphysics (v0.1.0) with the ICON climate and weather model (v2.6.5), Geosci. Model Dev., 17, 4017–4029, https://doi.org/10.5194/gmd-17-4017-2024, 2024. a
Balaji, V.: Climbing down Charney’s ladder: machine learning and the post-Dennard era of computational climate science, Philos. T. Roy. Soc. A, 379, 20200085, https://doi.org/10.1098/rsta.2020.0085, 2021. a
Balaji, V., Couvreux, F., Deshayes, J., Gautrais, J., Hourdin, F., and Rio, C.: Are general circulation models obsolete?, P. Natl. Acad. Sci. USA, 119, e2202075119, https://doi.org/10.1073/pnas.2202075119, 2022. a, b, c
Bauer, P., Stevens, B., and Hazeleger, W.: A digital twin of Earth for the green transition, Nat. Clim. Change, 11, 80–83, https://doi.org/10.1038/s41558-021-00986-y, 2021. a
Behrens, G., Beucler, T., Gentine, P., Iglesias-Suarez, F., Pritchard, M., and Eyring, V.: Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models, J. Adv. Model. Earth Sy., 14, e2022MS003130, https://doi.org/10.1029/2022MS003130, 2022. a
Belochitski, A. and Krasnopolsky, V.: Robustness of neural network emulations of radiative transfer parameterizations in a state-of-the-art general circulation model, Geosci. Model Dev., 14, 7425–7437, https://doi.org/10.5194/gmd-14-7425-2021, 2021. a
Beucler, T., Rasp, S., Pritchard, M., and Gentine, P.: Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling, arXiv [preprint], https://doi.org/10.48550/arXiv.1906.06622, 2019. a
Beucler, T., Pritchard, M., Gentine, P., and Rasp, S.: Towards Physically-consistent, Data-driven Models of Convection, arXiv [preprint], https://doi.org/10.48550/arXiv.2002.08525, 2020. a
Beucler, T., Pritchard, M., Rasp, S., Ott, J., Baldi, P., and Gentine, P.: Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems, Phys. Rev. Lett., 126, 098302, https://doi.org/10.1103/PhysRevLett.126.098302, 2021. a
Beucler, T., Gentine, P., Yuval, J., Gupta, A., Peng, L., Lin, J., Yu, S., Rasp, S., Ahmed, F., O’Gorman, P. A., Neelin, J. D., Lutsko, N. J., and Pritchard, M.: Climate-invariant machine learning, Sci. Adv., 10, eadj7250, https://doi.org/10.1126/sciadv.adj7250, 2024. a
Bolton, T. and Zanna, L.: Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization, J. Adv. Model. Earth Sy., 11, 376–399, https://doi.org/10.1029/2018MS001472, 2019. a
Brenowitz, N. D. and Bretherton, C. S.: Prognostic Validation of a Neural Network Unified Physics Parameterization, Geophys. Res. Lett., 45, 6289–6298, https://doi.org/10.1029/2018GL078510, 2018. a
Brenowitz, N. D. and Bretherton, C. S.: Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-Graining, J. Adv. Model. Earth Sy., 11, 2728–2744, https://doi.org/10.1029/2019MS001711, 2019. a
Brenowitz, N. D., Beucler, T., Pritchard, M., and Bretherton, C. S.: Interpreting and Stabilizing Machine-learning Parametrizations of Convection, J. Atmos. Sci., 77, 4357–4375, https://doi.org/10.1175/JAS-D-20-0082.1, 2020. a
Bretherton, C. S., Henn, B., Kwa, A., Brenowitz, N. D., Watt-Meyer, O., McGibbon, J., Perkins, W. A., Clark, S. K., and Harris, L.: Correcting Coarse-Grid Weather and Climate Models by Machine Learning From Global Storm-Resolving Simulations, J. Adv. Model. Earth Sy., 14, e2021MS002794, https://doi.org/10.1029/2021MS002794, 2022. a
Chantry, M., Hatfield, S., Dueben, P., Polichtchouk, I., and Palmer, T.: Machine Learning Emulation of Gravity Wave Drag in Numerical Weather Forecasting, J. Adv. Model. Earth Sy., 13, e2021MS002477, https://doi.org/10.1029/2021MS002477, 2021. a, b
Chollet, F.: Keras, https://keras.io (last access: 13 April 2026), 2015. a
Clark, S. K., Brenowitz, N. D., Henn, B., Kwa, A., McGibbon, J., Perkins, W. A., Watt-Meyer, O., Bretherton, C. S., and Harris, L. M.: Correcting a 200 km Resolution Climate Model in Multiple Climates by Machine Learning From 25 km Resolution Simulations, J. Adv. Model. Earth Sy., 14, e2022MS003219, https://doi.org/10.1029/2022MS003219, 2022. a
Crossouard, S., Thao, S., Dubos, T., Kageyama, M., Vrac, M., and Meurdesoif, Y.: Replication Code and Data for: Crossouard et al., 2025 “Contribution of physical latent knowledge to the emulation of an atmospheric physics model: a study based on the LMDZ Atmospheric General Circulation Model”, Harvard Dataverse [code, data set], https://doi.org/10.7910/DVN/3UFU9J, 2025. a
Curcic, M.: A parallel Fortran framework for neural networks and deep learning, arXiv [preprint], https://doi.org/10.48550/arXiv.1902.06714, 2019. a
Dubos, T., Dubey, S., Tort, M., Mittal, R., Meurdesoif, Y., and Hourdin, F.: DYNAMICO-1.0, an icosahedral hydrostatic dynamical core designed for consistency and versatility, Geosci. Model Dev., 8, 3131–3150, https://doi.org/10.5194/gmd-8-3131-2015, 2015. a, b
Espinosa, Z. I., Sheshadri, A., Cain, G. R., Gerber, E. P., and DallaSanta, K. J.: Machine Learning Gravity Wave Parameterization Generalizes to Capture the QBO and Response to Increased CO2, Geophys. Res. Lett., 49, e2022GL098174, https://doi.org/10.1029/2022GL098174, 2022. a
Eyring, V., Bony, S., Meehl, G. A., Senior, C. A., Stevens, B., Stouffer, R. J., and Taylor, K. E.: Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization, Geosci. Model Dev., 9, 1937–1958, https://doi.org/10.5194/gmd-9-1937-2016, 2016. a
Gates, W. L., Boyle, J. S., Covey, C., Dease, C. G., Doutriaux, C. M., Drach, R. S., Fiorino, M., Gleckler, P. J., Hnilo, J. J., Marlais, S. M., Phillips, T. J., Potter, G. L., Santer, B. D., Sperber, K. R., Taylor, K. E., and Williams, D. N.: An Overview of the Results of the Atmospheric Model Intercomparison Project (AMIP I), B. Am. Meteorol. Soc., 80, 29–55, https://doi.org/10.1175/1520-0477(1999)080<0029:AOOTRO>2.0.CO;2, 1999. a
Gentine, P., Pritchard, M., Rasp, S., Reinaudi, G., and Yacalis, G.: Could Machine Learning Break the Convection Parameterization Deadlock?, Geophys. Res. Lett., 45, 5742–5751, https://doi.org/10.1029/2018GL078202, 2018. a, b
Gettelman, A., Gagne, D. J., Chen, C., Christensen, M. W., Lebo, Z. J., Morrison, H., and Gantos, G.: Machine Learning the Warm Rain Process, J. Adv. Model. Earth Sy., 13, e2020MS002268, https://doi.org/10.1029/2020MS002268, 2021. a
Glorot, X., Bordes, A., and Bengio, Y.: Deep Sparse Rectifier Neural Networks, Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, 15, 315–323, 2011. a
Guillaumin, A. P. and Zanna, L.: Stochastic-Deep Learning Parameterization of Ocean Momentum Forcing, J. Adv. Model. Earth Sy., 13, e2021MS002534, https://doi.org/10.1029/2021MS002534, 2021. a
Han, Y., Zhang, G. J., Huang, X., and Wang, Y.: A Moist Physics Parameterization Based on Deep Learning, J. Adv. Model. Earth Sy., 12, e2020MS002076, https://doi.org/10.1029/2020MS002076, 2020. a, b
Han, Y., Zhang, G. J., and Wang, Y.: An Ensemble of Neural Networks for Moist Physics Processes, Its Generalizability and Stable Integration, J. Adv. Model. Earth Sy., 15, e2022MS003508, https://doi.org/10.1029/2022MS003508, 2023. a, b, c
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image Recognition, arXiv [preprint], https://doi.org/10.48550/arXiv.1512.03385, 2015. a
Heuer, H., Schwabe, M., Gentine, P., Giorgetta, M. A., and Eyring, V.: Interpretable multiscale Machine Learning-Based Parameterizations of Convection for ICON, J. Adv. Model. Earth Sy., 16, e2024MS004398, https://doi.org/10.1029/2024MS004398, 2024. a
Hourdin, F., Mauritsen, T., Gettelman, A., Golaz, J.-C., Balaji, V., Duan, Q., Folini, D., Ji, D., Klocke, D., Qian, Y., Rauser, F., Rio, C., Tomassini, L., Watanabe, M., and Williamson, D.: The Art and Science of Climate Model Tuning, B. Am. Meteorol. Soc., 98, 589–602, https://doi.org/10.1175/BAMS-D-15-00135.1, 2017. a
Hourdin, F., Rio, C., Grandpeix, J., Madeleine, J., Cheruy, F., Rochetin, N., Jam, A., Musat, I., Idelkadi, A., Fairhead, L., Foujols, M., Mellul, L., Traore, A., Dufresne, J., Boucher, O., Lefebvre, M., Millour, E., Vignon, E., Jouhaud, J., Diallo, F. B., Lott, F., Gastineau, G., Caubel, A., Meurdesoif, Y., and Ghattas, J.: LMDZ6A: The Atmospheric Component of the IPSL Climate Model With Improved and Better Tuned Physics, J. Adv. Model. Earth Sy., 12, e2019MS001892, https://doi.org/10.1029/2019MS001892, 2020. a, b
Hu, Z., Subramaniam, A., Kuang, Z., Lin, J., Yu, S., Hannah, W. M., Brenowitz, N. D., Romero, J., and Pritchard, M. S.: Stable Machine-Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection-Permitting Simulations, J. Adv. Model. Earth Sy., 17, e2024MS004618, https://doi.org/10.1029/2024MS004618, 2025. a, b, c
Krasnopolsky, V. M., Fox-Rabinovitz, M. S., and Chalikov, D. V.: New Approach to Calculation of Atmospheric Model Physics: Accurate and Fast Neural Network Emulation of Longwave Radiation in a Climate Model, Mon. Weather Rev., 133, 1370–1383, https://doi.org/10.1175/MWR2923.1, 2005. a
Krasnopolsky, V. M., Fox-Rabinovitz, M. S., and Belochitski, A. A.: Using Ensemble of Neural Networks to Learn Stochastic Convection Parameterizations for Climate and Numerical Weather Prediction Models from Data Simulated by a Cloud Resolving Model, Advances in Artificial Neural Systems, 2013, 1–13, https://doi.org/10.1155/2013/485913, 2013. a
Krinner, G., Viovy, N., De Noblet-Ducoudré, N., Ogée, J., Polcher, J., Friedlingstein, P., Ciais, P., Sitch, S., and Prentice, I. C.: A dynamic global vegetation model for studies of the coupled atmosphere-biosphere system, Global Biogeochem. Cy., 19, 2003GB002199, https://doi.org/10.1029/2003GB002199, 2005. a
Lagerquist, R., Turner, D., Ebert-Uphoff, I., Stewart, J., and Hagerty, V.: Using deep learning to emulate and accelerate a radiative-transfer model, J. Atmos. Ocean. Tech., https://doi.org/10.1175/JTECH-D-21-0007.1, 2021. a, b
LeCun, Y., Boser, B. E., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W. E., and Jackel, L. D.: Handwritten Digit Recognition with a Back-Propagation Network, in: Proc. Advances in Neural Information Processing Systems, 396–404, 1990. a
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015. a, b, c
Limon, G. C. and Jablonowski, C.: Probing the Skill of Random Forest Emulators for Physical Parameterizations Via a Hierarchy of Simple CAM6 Configurations, J. Adv. Model. Earth Sy., 15, e2022MS003395, https://doi.org/10.1029/2022MS003395, 2023. a
Lin, J., Yu, S., Peng, L., Beucler, T., Wong-Toi, E., Hu, Z., Gentine, P., Geleta, M., and Pritchard, M. S.: Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles, arXiv [preprint], https://doi.org/10.48550/arXiv.2309.16177, 2024. a
Liu, Y., Caballero, R., and Monteiro, J. M.: RadNet 1.0: exploring deep learning architectures for longwave radiative transfer, Geosci. Model Dev., 13, 4399–4412, https://doi.org/10.5194/gmd-13-4399-2020, 2020. a
Manabe, S. and Wetherald, R. T.: The Effects of Doubling the CO2 Concentration on the climate of a General Circulation Model, J. Atmos. Sci., https://doi.org/10.1175/1520-0469(1975)032<0003:TEODTC>2.0.CO;2, 1975. a
Medeiros, B., Williamson, D. L., and Olson, J. G.: Reference aquaplanet climate in the Community Atmosphere Model, Version 5, J. Adv. Model. Earth Sy., 8, 406–424, https://doi.org/10.1002/2015MS000593, 2016. a
Meyer, D., Hogan, R. J., Dueben, P. D., and Mason, S. L.: Machine Learning Emulation of 3D Cloud Radiative Effects, J. Adv. Model. Earth Sy., 14, e2021MS002550, https://doi.org/10.1029/2021MS002550, 2022. a
Mooers, G., Pritchard, M., Beucler, T., Ott, J., Yacalis, G., Baldi, P., and Gentine, P.: Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models With Real-Geography Boundary Conditions, J. Adv. Model. Earth Sy., 13, e2020MS002385, https://doi.org/10.1029/2020MS002385, 2021. a
O'Gorman, P. A. and Dwyer, J. G.: Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events, J. Adv. Model. Earth Sy., 10, 2548–2563, https://doi.org/10.1029/2018MS001351, 2018. a, b
Ott, J., Pritchard, M., Best, N., Linstead, E., Curcic, M., and Baldi, P.: A Fortran-Keras Deep Learning Bridge for Scientific Computing, arXiv [preprint], https://doi.org/10.48550/arXiv.2004.10652, 2020. a
Pal, A., Mahajan, S., and Norman, M. R.: Using Deep Neural Networks as Cost-Effective Surrogate Models for Super-Parameterized E3SM Radiative Transfer, Geophys. Res. Lett., 46, 6069–6079, https://doi.org/10.1029/2018GL081646, 2019. a, b
Partee, S., Ellis, M., Rigazzi, A., Bachman, S., Marques, G., Shao, A., and Robbins, B.: Using Machine Learning at Scale in HPC Simulations with SmartSim: An Application to Ocean Climate Modeling, arXiv [preprint], https://doi.org/10.48550/arXiv.2104.09355, 2021. a
Rasp, S., Pritchard, M. S., and Gentine, P.: Deep learning to represent subgrid processes in climate models, P. Natl. Acad. Sci. USA, 115, 9684–9689, https://doi.org/10.1073/pnas.1810286115, 2018. a, b, c
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. a
Roh, S. and Song, H.: Evaluation of Neural Network Emulations for Radiation Parameterization in Cloud Resolving Model, Geophys. Res. Lett., 47, e2020GL089444, https://doi.org/10.1029/2020GL089444, 2020. 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
Sanderson, B. M., Piani, C., Ingram, W. J., Stone, D. A., and Allen, M. R.: Towards constraining climate sensitivity by linear analysis of feedback patterns in thousands of perturbed-physics GCM simulations, Clim. Dynam., 30, 175–190, https://doi.org/10.1007/s00382-007-0280-7, 2008. a
Schneider, T., Lan, S., Stuart, A., and Teixeira, J.: Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations, Geophys. Res. Lett., 44, https://doi.org/10.1002/2017GL076101, 2017. a
Seifert, A. and Rasp, S.: Potential and Limitations of Machine Learning for Modeling Warm-Rain Cloud Microphysical Processes, J. Adv. Model. Earth Sy., 12, e2020MS002301, https://doi.org/10.1029/2020MS002301, 2020. a
Veit, A., Wilber, M., and Belongie, S.: Residual Networks Behave Like Ensembles of Relatively Shallow Networks, https://doi.org/10.48550/arXiv.1605.06431, 2016. a
Wang, X., Han, Y., Xue, W., Yang, G., and Zhang, G. J.: Stable climate simulations using a realistic general circulation model with neural network parameterizations for atmospheric moist physics and radiation processes, Geosci. Model Dev., 15, 3923–3940, https://doi.org/10.5194/gmd-15-3923-2022, 2022. a
Watt-Meyer, O., Brenowitz, N. D., Clark, S. K., Henn, B., Kwa, A., McGibbon, J., Perkins, W. A., Harris, L., and Bretherton, C. S.: Neural Network Parameterization of Subgrid-Scale Physics From a Realistic Geography Global Storm-Resolving Simulation, J. Adv. Model. Earth Sy., 16, e2023MS003668, https://doi.org/10.1029/2023MS003668, 2024. a
Yuval, J. and O'Gorman, P. A.: Neural-network parameterization of subgrid momentum transport in the atmosphere, https://doi.org/10.1002/essoar.10507557.1, 2021. a
Yuval, J. and O’Gorman, P. A.: Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions, Nat. Commun., 11, 3295, https://doi.org/10.1038/s41467-020-17142-3, 2020. a
Yuval, J., O'Gorman, P. A., and Hill, C. N.: Use of Neural Networks for Stable, Accurate and Physically Consistent Parameterization of Subgrid Atmospheric Processes With Good Performance at Reduced Precision, Geophys. Res. Lett., 48, e2020GL091363, https://doi.org/10.1029/2020GL091363, 2021. a
Zhang, T., Morcrette, C., Zhang, M., Lin, W., Xie, S., Liu, Y., Van Weverberg, K., and Rodrigues, J.: A Fortran–Python interface for integrating machine learning parameterization into earth system models, Geosci. Model Dev., 18, 1917–1928, https://doi.org/10.5194/gmd-18-1917-2025, 2025. a
Short summary
Current atmospheric models are limited by the computational time required for physical processes, known as physical parameterizations. To address this, we developed neural network-based emulators to replace these parameterizations in the IPSL climate model, using a simplified aquaplanet setup and a realistic configuration. We found that incorporating some physical knowledge, such as latent variables, into the learning process can improve predictions.
Current atmospheric models are limited by the computational time required for physical...
