pith. sign in

arxiv: 2605.28851 · v1 · pith:W5Y46RACnew · submitted 2026-05-16 · 🌌 astro-ph.EP · astro-ph.IM· cs.LG· physics.ao-ph

Towards a Foundation Model for the Martian Atmosphere

Sujit Roy , Udayshankar Nair , Yuling Wu , Georgios Priftis , Liping Wang , Anastasia Georgiou , Anne Jones , Bj\"orn L\"utjens
show 11 more authors
Johannes Schmude Campbell Watson Rachel A. Slank Ankur Kumar Anirbit Mukherjee Procheta Sen Ramin Lolachi Haonan Chen Manil Maskey Juan Bernab\'e-Moreno Rahul Ramachandran
This is my paper

Pith reviewed 2026-06-30 18:59 UTC · model grok-4.3

classification 🌌 astro-ph.EP astro-ph.IMcs.LGphysics.ao-ph
keywords martian atmospherefoundation modeldata assimilationgeneral circulation modelsmesoscale phenomenaatmospheric retrievalsAI for atmospheric physicsreanalysis datasets
0
0 comments X

The pith

Sparse and fragmented observations of the Martian atmosphere, combined with the high computational cost of detailed simulations, motivate the development of a data-driven foundation model.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper examines the challenges in modeling the Martian atmosphere, including the computational expense of general circulation models at mesoscale resolutions and the limitations of sparse satellite data. It argues that these issues point to the need for a foundation model that can efficiently handle multiple applications. The authors review available data sources like atmospheric retrievals and reanalysis datasets, existing physical models, potential downstream tasks, and relevant AI advancements in atmospheric modeling and data assimilation to map out the design space for such a model.

Core claim

The development of a data-driven foundation model for the Martian atmosphere is motivated by the need to address dynamical phenomena like dust storms and orographic clouds in a data- and compute-efficient way, requiring a clear understanding of the interplay between data availability, physical processes, and AI techniques to determine what applications a single model can sensibly address.

What carries the argument

The design landscape for the foundation model, shaped by the interplay between available data (atmospheric retrievals and reanalysis), physical models (general circulation models), candidate downstream applications, and AI developments (models for atmospheric physics, data-driven data assimilation, and limited-data methods).

If this is right

  • The model could simulate mesoscale features without the computational burden of traditional high-resolution GCMs.
  • It would enable better handling of sparse and fragmented observation records for forecasting.
  • A single model could cover a wide range of phenomena from planet-encircling dust storms to nocturnal low-level jets.
  • Relevant AI techniques could be leveraged to work effectively even with limited Martian data.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Extending this approach might allow foundation models for other planetary atmospheres with similar data constraints.
  • Integration with existing reanalysis datasets could enhance the model's accuracy for assimilation tasks.
  • The emphasis on limited-data AI methods could lead to more robust models that generalize across different observation instruments.

Load-bearing premise

That elucidating the interplay between available data, underlying physics, and AI developments can meaningfully guide the design of one foundation model to address multiple use cases efficiently.

What would settle it

Demonstrating that no single model architecture can efficiently handle both large-scale dust storm simulation and mesoscale cloud forecasting without significant performance loss or increased data requirements would falsify the motivation.

Figures

Figures reproduced from arXiv: 2605.28851 by Anastasia Georgiou, Anirbit Mukherjee, Ankur Kumar, Anne Jones, Bj\"orn L\"utjens, Campbell Watson, Georgios Priftis, Haonan Chen, Johannes Schmude, Juan Bernab\'e-Moreno, Liping Wang, Manil Maskey, Procheta Sen, Rachel A. Slank, Rahul Ramachandran, Ramin Lolachi, Sujit Roy, Udayshankar Nair, Yuling Wu.

Figure 1
Figure 1. Figure 1: (left) An illustration of Ames MGCM in c48 (1.875 [PITH_FULL_IMAGE:figures/full_fig_p013_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: (left) The simulation ran for 2 martian years using the same dust scenario for MY30. [PITH_FULL_IMAGE:figures/full_fig_p015_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Spatial and temporal scales of martian atmospheric phenomena targeted by the MAFM. [PITH_FULL_IMAGE:figures/full_fig_p018_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Forecast evolution of the Mars SpectFormer model with MAE error for Mars Year 35, [PITH_FULL_IMAGE:figures/full_fig_p035_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Autoregressive rollout performance of the combined-loss Mars SpectFormer model over a [PITH_FULL_IMAGE:figures/full_fig_p037_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Forecast evolution of the Mars GraphCast model with MAE error for Mars Year 35, [PITH_FULL_IMAGE:figures/full_fig_p038_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Autoregressive rollout performance of the combined-loss Mars GraphCast model over a [PITH_FULL_IMAGE:figures/full_fig_p039_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Forecast evolution of the Mars Prithvi-WxC model with MAE error for Mars Year 35, [PITH_FULL_IMAGE:figures/full_fig_p040_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Autoregressive rollout performance of the combined-loss Mars Prithvi-WxC model over a [PITH_FULL_IMAGE:figures/full_fig_p042_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Extending Poseidon (scOT) to three dimension. (Source: [151].) [PITH_FULL_IMAGE:figures/full_fig_p043_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: When extending the training to 40,000 steps, the randomly initialized model not only [PITH_FULL_IMAGE:figures/full_fig_p043_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Model performance (MAE) after 20,000 training steps. The figure shows [PITH_FULL_IMAGE:figures/full_fig_p044_12.png] view at source ↗
read the original abstract

The martian atmosphere hosts dynamical phenomena ranging from planet-encircling dust storms to mesoscale orographic clouds and nocturnal low-level jets. General circulation model show capability to simulate these phenomena, but is computationally expensive at resolution needed to resolve mesoscale features. While assimilation of satellite remote sensing observation enable forecasting capabilities using such models, observation record is often sparse, short and fragmented across instrument generators. These constraints motivate the development of a data-driven foundation model for the Martian atmosphere. Foundation models live in a complex design landscape. There is an interplay between the available data, the physics of the underlying processes and corresponding developments in AI. Even though the idea of a foundation model is to address multiple use cases in a data- and compute-efficient manner, it is important to have a clear picture what applications can sensibly addressed by a single model. The purpose of this paper is to elucidate this design landscape. We discuss available data ranging from atmospheric retrievals to reanalysis datasets as well as existing physical models. Moreover, we identify a wide range of candidate downstream applications. Finally, we consider relevant recent developments in artificial intelligence (AI) that can be leveraged in this context. Here, we put a particular emphasis on AI models for atmospheric physics, data-driven approaches to data assimilation as well as methods to work in a limited data setting.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The manuscript is a position/discussion paper arguing that computational expense of high-resolution GCMs and sparsity/fragmentation of observational records for the Martian atmosphere motivate development of a data-driven foundation model. It surveys data sources (retrievals and reanalysis), physical models, downstream applications, and AI techniques (data assimilation, limited-data methods) to elucidate the design landscape, emphasizing the interplay between data, physics, and AI for multi-use-case efficiency.

Significance. If the motivation holds, the paper provides a useful high-level synthesis of Martian atmospheric data, modeling constraints, and relevant AI methods that could guide community efforts toward efficient foundation models in data-sparse planetary settings. The explicit framing of application compatibility within a single model is a constructive contribution to the design discussion.

minor comments (3)
  1. [Abstract] Abstract: 'General circulation model show capability' contains a subject-verb agreement error and should read 'models show'.
  2. [Abstract] Abstract: 'observation record is often sparse, short and fragmented across instrument generators' is unclear; 'instrument generators' appears to be a possible typo for 'instruments' or 'generations of instruments'.
  3. The discussion of downstream applications and AI techniques remains at a high level without concrete criteria for determining which use cases can be jointly addressed by one foundation model, which would help readers assess the practicality of the proposed approach.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of the manuscript as a useful high-level synthesis and for recommending minor revision. The paper is intended as a discussion piece to map the design landscape for a foundation model of the Martian atmosphere, and we are glad this framing is viewed constructively.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper is a position and survey piece whose purpose is to motivate and map the design space for a potential foundation model. It contains no derivations, equations, fitted parameters, predictions, or load-bearing self-citations that reduce any claim to its own inputs. The central statements are observational (data sparsity, computational cost of GCMs) and motivational; they do not assert a specific architecture, performance result, or uniqueness theorem. All referenced AI techniques and data sources are external to the paper and are discussed at a high level without internal reduction. This is the normal, non-circular case for a discussion manuscript.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The paper rests on standard domain assumptions about computational costs of high-resolution atmospheric modeling and data limitations; no free parameters, invented entities, or ad-hoc axioms are introduced beyond these.

axioms (2)
  • domain assumption General circulation models are computationally expensive at resolutions needed to resolve mesoscale features.
    Invoked in the abstract as the primary motivation for a data-driven alternative.
  • domain assumption Observational records for the Martian atmosphere are sparse, short, and fragmented.
    Stated directly in the abstract to justify the need for foundation models.

pith-pipeline@v0.9.1-grok · 5857 in / 1310 out tokens · 27054 ms · 2026-06-30T18:59:22.680401+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

175 extracted references · 86 canonical work pages · 6 internal anchors

  1. [1]

    On the possibility of liquid water on present-day mars.Journal of Geophysical Research: Planets, 106(E10):23317–23326, 2001

    Robert M Haberle, Christopher P McKay, James Schaeffer, Nathalie A Cabrol, Edmon A Grin, Aaron P Zent, and Richard Quinn. On the possibility of liquid water on present-day mars.Journal of Geophysical Research: Planets, 106(E10):23317–23326, 2001

    2001

  2. [2]

    Abundance and isotopic composition of gases in the martian atmosphere from the curiosity rover.Science, 341(6143):263–266, 2013

    Paul R Mahaffy, Christopher R Webster, Sushil K Atreya, Heather Franz, Michael Wong, Pamela G Conrad, Dan Harpold, John J Jones, Laurie A Leshin, Heidi Manning, et al. Abundance and isotopic composition of gases in the martian atmosphere from the curiosity rover.Science, 341(6143):263–266, 2013

    2013

  3. [3]

    Sánchez-Lavega, T

    A. Sánchez-Lavega, T. del Río-Gaztelurrutia, A. Spiga, J. Hernández-Bernal, E. Larsen, D. Tirsch, A. Cardesin-Moinelo, and P. Machado. Dynamical phenomena in the Martian atmosphere through Mars Express imaging.Space Science Reviews, 220(16), 2024. doi: 10.1007/s11214-024-01047-4

    work page doi:10.1007/s11214-024-01047-4 2024

  4. [6]

    N. J. Kelly, W. V. Boynton, K. Kerry, D. Hamara, D. Janes, R. C. Reedy, K. J. Kim, and R. M. Haberle. Seasonal polar carbon dioxide frost on Mars: CO2 mass and columnar thickness distribution.Journal of Geophysical Research: Planets, 111(E3), 2006. doi: 10. 1029/2006JE002678

    2006

  5. [7]

    Robert B Leighton and Bruce C Murray. Behavior of carbon dioxide and other volatiles on mars: A thermal model of the martian surface suggests that mars’s polar caps are solid carbon dioxide.Science, 153(3732):136–144, 1966

    1966

  6. [8]

    Timothy n

    TIMOTHY I MICHAELS and THOMAS H PRETTYMAN. Timothy n. titus, shane byrne, anthony colaprete, françois forget.The Atmosphere and Climate of Mars, page 374, 2017

    2017

  7. [9]

    A topographically forced asymmetry in the martian circulation and climate.Nature, 416(6878):298–301, 2002

    Mark I Richardson and R John Wilson. A topographically forced asymmetry in the martian circulation and climate.Nature, 416(6878):298–301, 2002

    2002

  8. [10]

    A comparison of co2 seasonal activity in mars’ northern and southern hemispheres.Icarus, 419:115801, 2024

    Candice J Hansen, Shane Byrne, Wendy M Calvin, Serina Diniega, Colin M Dundas, Paul O Hayne, Alfred S McEwen, Lauren E McKeown, Sylvain Piqueux, Ganna Portyankina, et al. A comparison of co2 seasonal activity in mars’ northern and southern hemispheres.Icarus, 419:115801, 2024

    2024

  9. [13]

    Wang and M

    H. Wang and M. I. Richardson. The origin, evolution, and trajectory of large dust storms on Mars during Mars years 24–30 (1999–2011).Icarus, 251:112–127, 2015. doi: 10.1016/j.icarus. 2013.10.033

    work page doi:10.1016/j.icarus 1999

  10. [14]

    H. Wang, M. Saidel, M. I. Richardson, A. D. Toigo, and J. M. Battalio. Martian dust storm distribution and annual cycle from Mars daily global map observations.Icarus, 394:115416,

  11. [16]

    Modeling the martian dust cycle and surface dust reservoirs with the nasa ames general circulation model.Journal of Geophysical Research: Planets, 111(E6), 2006

    Melinda A Kahre, James R Murphy, and Robert M Haberle. Modeling the martian dust cycle and surface dust reservoirs with the nasa ames general circulation model.Journal of Geophysical Research: Planets, 111(E6), 2006

    2006

  12. [17]

    Interannual variability in tes atmospheric observations of mars during 1999–2003.Icarus, 167(1):148–165, 2004

    Michael D Smith. Interannual variability in tes atmospheric observations of mars during 1999–2003.Icarus, 167(1):148–165, 2004

    1999

  13. [18]

    Mars climate sounder observation of mars’ 2018 global dust storm.Geophysical Research Letters, 47(23):e2019GL083931, 2020

    DM Kass, JT Schofield, A Kleinböhl, DJ McCleese, NG Heavens, JH Shirley, and LJ Steele. Mars climate sounder observation of mars’ 2018 global dust storm.Geophysical Research Letters, 47(23):e2019GL083931, 2020

    2018

  14. [19]

    Martian dust storms: 1999 mars orbiter camera observations.Journal of Geophysical Research: Planets, 106(E10):23653–23687, 2001

    Bruce A Cantor, Philip B James, Michael Caplinger, and Michael J Wolff. Martian dust storms: 1999 mars orbiter camera observations.Journal of Geophysical Research: Planets, 106(E10):23653–23687, 2001

    1999

  15. [20]

    Bruce A Cantor, Katharine M Kanak, and Kenneth S Edgett. Mars orbiter camera observa- tions of martian dust devils and their tracks (september 1997 to january 2006) and evaluation of theoretical vortex models.Journal of Geophysical Research: Planets, 111(E12), 2006

    1997

  16. [21]

    Richardson

    Huiqun Wang and Mark I. Richardson. The origin, evolution, and trajectory of large dust storms on mars during mars years 24–30 (1999–2011).Icarus, 251:112–127, 2015. ISSN 0019-

    1999

  17. [22]

    URLhttps://www.sciencedirect

    doi: https://doi.org/10.1016/j.icarus.2013.10.033. URLhttps://www.sciencedirect. com/science/article/pii/S0019103513004624. Dynamic Mars

    work page doi:10.1016/j.icarus.2013.10.033 2013

  18. [23]

    C. L. Campbell, A. M. Kling, S. D. Guzewich, C. L. Smith, J. L. Kloos, M. T. Lemmon, C. A. Moore, B. A. Cooper, R. M. Haberle, and J. E. Moores. Estimating the altitudes of Martian water-ice clouds above the Mars Science Laboratory rover landing site.Planetary and Space Science, 182:104785, 2020. doi: 10.1016/j.pss.2019.104785

    work page doi:10.1016/j.pss.2019.104785 2020

  19. [24]

    Hernández-Bernal, A

    J. Hernández-Bernal, A. Sánchez-Lavega, T. del Río-Gaztelurrutia, E. Ravanis, A. Cardesín- Moinelo, K.Connour, et al. An extremely elongated cloud over Arsia Mons volcano on Mars: I. Life cycle.Journal of Geophysical Research: Planets, 126, 2021. doi: 10.1029/2020JE006517. e2020JE006517

    work page doi:10.1029/2020je006517 2021

  20. [25]

    R. T. Clancy, A. W. Grossman, M. J. Wolff, P. B. James, D. J. Rudy, Y. N. Billawala, B. J. Sandor, S. W. Lee, and D. O. Muhleman. Water vapor saturation at low altitudes around Mars aphelion: A key to Mars climate?Icarus, 122(1):36–62, 1996. doi: 10.1006/icar.1996.0108

    work page doi:10.1006/icar.1996.0108 1996

  21. [26]

    Mid latitude elongated clouds on mars

    E Larsen, A Sanchez-Lavega, T del Rio-Gaztelurrutia, and J Hernandez-Bernal. Mid latitude elongated clouds on mars. InProceedings of the VIII Iberian Congress on Planetary Sciences and Solar System Exploration, page 115, 2025

    2025

  22. [27]

    Montmessin, F

    F. Montmessin, F. Forget, P. Rannou, M. Cabane, and R. M. Haberle. Origin and role of water ice clouds in the martian water cycle as inferred from a general circulation model.Journal of 48 Geophysical Research: Planets, 109(E10), 2004. doi: https://doi.org/10.1029/2004JE002284. URLhttps://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2004JE002284

    work page doi:10.1029/2004je002284 2004

  23. [28]

    R. M. Haberle, M. A. Kahre, J. L. Hollingsworth, F. Montmessin, R. J. Wilson, R. A. Urata, A.S.Brecht, M.J.Wolff, A.M.Kling, andJ.R.Schaeffer. DocumentationoftheNASA/Ames legacy Mars global climate model: Simulations of the present seasonal water cycle.Icarus, 333:130–164, 2019. doi: 10.1016/j.icarus.2019.03.026

    work page doi:10.1016/j.icarus.2019.03.026 2019

  24. [29]

    Harris, X

    L. Harris, X. Chen, W. Putman, L. Zhou, and J.-H. Chen. A scientific description of the GFDL finite-volume cubed-sphere dynamical core. Technical report, NOAA Technical Memorandum OAR GFDL ; 2021-001, 2021

    2021

  25. [30]

    M. I. Richardson, A. D. Toigo, and C. E. Newman. PlanetWRF: A general purpose, lo- cal to global numerical model for planetary atmospheric and climate dynamics.Journal of Geophysical Research: Planets, 112(E9), 2007

    2007

  26. [31]

    Atime-splitnonhydrostaticatmosphericmodelforweather research and forecasting applications.Journal of Computational Physics, 227(7):3465–3485, 2008

    W.C.SkamarockandJ.B.Klemp. Atime-splitnonhydrostaticatmosphericmodelforweather research and forecasting applications.Journal of Computational Physics, 227(7):3465–3485, 2008

    2008

  27. [32]

    J. A. Holmes, S. R. Lewis, M. R. Patel, and F. Lefèvre. A reanalysis of ozone on Mars from assimilation of SPICAM observations.Icarus, 302:308–318, 2018. doi: 10.1016/j.icarus.2017. 11.026

    work page doi:10.1016/j.icarus.2017 2018

  28. [33]

    Holmes, Stephen R

    James A. Holmes, Stephen R. Lewis, and Manish R. Patel. Openmars: A global record of mar- tian weather from 1999 to 2015.Planetary and Space Science, 188:104962, 2020. ISSN 0032-

    1999

  29. [37]

    DJ McCleese, JT Schofield, FW Taylor, SB Calcutt, MC Foote, DM Kass, CB Leovy, DA Paige, PL Read, and RW Zurek. Mars climate sounder: An investigation of thermal and water vapor structure, dust and condensate distributions in the atmosphere, and energy balance of the polar regions.Journal of Geophysical Research: Planets, 112(E5), 2007

    2007

  30. [38]

    Korablev, F

    O. Korablev, F. Montmessin, A. Trokhimovskiy, A. A. Fedorova, A. V. Shakun, A. V. Grigoriev, et al. The Atmospheric Chemistry Suite (ACS) of three spectrometers for the ExoMars 2016 Trace Gas Orbiter.Space Science Reviews, 214(7), 2018. doi: 10.1007/ s11214-017-0437-6

    2016

  31. [39]

    A. C. Vandaele, J.-J. Lopez-Moreno, M. R. Patel, G. Bellucci, F. Daerden, B. Ristic, et al. NOMAD, an integrated suite of three spectrometers for the ExoMars Trace Gas Mission: technical description, science objectives and expected performance.Space Science Reviews, 214(80), 2018. doi: 10.1007/s11214-018-0517-2. 49

    work page doi:10.1007/s11214-018-0517-2 2018

  32. [40]

    S. J. Greybush, E. Kalnay, R. J. Wilson, R. N. Hoffman, T. Nehrkorn, M. Leidner, J. Eluszkiewicz, H. E. Gillespie, M. Wespetal, Y. Zhao, et al. The Ensemble Mars Atmo- sphere Reanalysis System (EMARS) version 1.0.Geoscience Data Journal, 6(2):137–150, 2019

    2019

  33. [41]

    FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

    J. Pathak, S. Subramanian, P. Harrington, S. Raja, A. Chattopadhyay, M. Mardani, T. Kurth, D. Hall, Z. Li, K. Azizzadenesheli, et al. FourCastNet: A global data-driven high-resolution weather model using adaptive Fourier neural operators.arXiv preprint arXiv:2202.11214, 2022

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  34. [42]

    Forecasting global weather with graph neural net- works,

    Ryan Keisler. Forecasting global weather with graph neural networks.arXiv preprint arXiv:2202.07575, 2022

    work page arXiv 2022

  35. [45]

    K. Chen, T. Han, J. Gong, L. Bai, F. Ling, J.-J. Luo, X. Chen, L. Ma, T. Zhang, R. Su, et al. FengWu: Pushing the skillful global medium-range weather forecast beyond 10 days lead.arXiv preprint arXiv:2304.02948, 2023

    work page arXiv 2023

  36. [46]

    Fuxi: A cascade machine learning forecasting system for 15-day global weather forecast.npj climate and atmospheric science, 6(1):190, 2023

    Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Yuan Qi, and Hao Li. Fuxi: A cascade machine learning forecasting system for 15-day global weather forecast.npj climate and atmospheric science, 6(1):190, 2023

    2023

  37. [47]

    Spherical fourier neural operators: Learning stable dynamics on the sphere

    Boris Bonev, Thorsten Kurth, Christian Hundt, Jaideep Pathak, Maximilian Baust, Karthik Kashinath, and Anima Anandkumar. Spherical fourier neural operators: Learning stable dynamics on the sphere. InInternational conference on machine learning, pages 2806–2823. PMLR, 2023

    2023

  38. [48]

    AIFS – ECMWF’s data-driven forecast- ing system,

    Simon Lang, Mihai Alexe, Matthew Chantry, Jesper Dramsch, Florian Pinault, Baudouin Raoult, Mariana CA Clare, Christian Lessig, Michael Maier-Gerber, Linus Magnusson, et al. Aifs–ecmwf’s data-driven forecasting system.arXiv preprint arXiv:2406.01465, 2024

    work page arXiv 2024

  39. [49]

    Aifs- crps: ensemble forecasting using a model trained with a loss function based on the continuous ranked probability score.npj Artificial Intelligence, 2(1):18, 2026

    Simon Lang, Mihai Alexe, Mariana CA Clare, Christopher Roberts, Rilwan Adewoyin, Zied BenBouallègue, MatthewChantry, JesperDramsch, PeterDDueben, SaraHahner, etal. Aifs- crps: ensemble forecasting using a model trained with a loss function based on the continuous ranked probability score.npj Artificial Intelligence, 2(1):18, 2026

    2026

  40. [50]

    Climax: A foundation model for weather and climate,

    Tung Nguyen, Johannes Brandstetter, Ashish Kapoor, Jayesh K Gupta, and Aditya Grover. Climax: A foundation model for weather and climate.arXiv preprint arXiv:2301.10343, 2023

    work page arXiv 2023

  41. [51]

    Lessig, I

    C. Lessig, I. Luise, B. Gong, M. Langguth, S. Stadler, and M. Schultz. AtmoRep: A stochas- tic model of atmosphere dynamics using large scale representation learning.arXiv preprint arXiv:2308.13280, 2023

    work page arXiv 2023

  42. [53]

    A foundation model for the earth system.Nature, 641(8065):1180–1187, 2025

    Cristian Bodnar, Wessel P Bruinsma, Ana Lucic, Megan Stanley, Anna Allen, Johannes Brandstetter, Patrick Garvan, Maik Riechert, Jonathan A Weyn, Haiyu Dong, et al. A foundation model for the earth system.Nature, 641(8065):1180–1187, 2025

    2025

  43. [54]

    The challenge of atmospheric data assimilation on mars.Earth and Space Science, 4(12):690–722, 2017

    T Navarro, F Forget, E Millour, SJ Greybush, E Kalnay, and T Miyoshi. The challenge of atmospheric data assimilation on mars.Earth and Space Science, 4(12):690–722, 2017

    2017

  44. [55]

    The ensemble mars atmosphere reanalysis system (emars) version 1.0.Geoscience data journal, 6(2):137–150, 2019

    Steven J Greybush, Eugenia Kalnay, R John Wilson, Ross N Hoffman, Thomas Nehrkorn, Mark Leidner, Janusz Eluszkiewicz, Hartzel E Gillespie, Matthew Wespetal, Yongjing Zhao, et al. The ensemble mars atmosphere reanalysis system (emars) version 1.0.Geoscience data journal, 6(2):137–150, 2019

    2019

  45. [56]

    Holmes, Stephen R

    James A. Holmes, Stephen R. Lewis, Manish R. Patel, and Franck Lefèvre. A reanalysis of ozoneonmarsfromassimilationofspicamobservations.Icarus, 302:308–318, 2018. ISSN0019-

    2018

  46. [57]

    URLhttps://www.sciencedirect

    doi: https://doi.org/10.1016/j.icarus.2017.11.026. URLhttps://www.sciencedirect. com/science/article/pii/S0019103517302889

    work page doi:10.1016/j.icarus.2017.11.026 2017

  47. [58]

    The meteorological office analysis correction data assimilation scheme.Quarterly Journal of the Royal Meteorological Society, 117(497):59–89, 1991

    AC Lorenc, RS Bell, and B Macpherson. The meteorological office analysis correction data assimilation scheme.Quarterly Journal of the Royal Meteorological Society, 117(497):59–89, 1991

    1991

  48. [59]

    Christensen, Donald L

    Philip R. Christensen, Donald L. Anderson, Stillman C. Chase, Roger N. Clark, Hugh H. Kieffer, Michael C. Malin, John C. Pearl, James Carpenter, Nuno Bandiera, F. Gerald Brown, and Steven Silverman. Thermal emission spectrometer experiment: Mars observer mission. Journal of Geophysical Research: Planets, 97(E5):7719–7734, 1992. doi: https://doi.org/ 10.10...

    work page doi:10.1029/92je00453 1992

  49. [60]

    P. R. Christensen, J. L. Bandfield, V. E. Hamilton, S. W. Ruff, H. H. Kieffer, T. N. Titus, M. C. Malin, R. V. Morris, M. D. Lane, R. L. Clark, B. M. Jakosky, M. T. Mellon, J. C. Pearl, B. J. Conrath, M. D. Smith, R. T. Clancy, R. O. Kuzmin, T. Roush, G. L. Mehall, N. Gorelick, K. Bender, K. Murray, S. Dason, E. Greene, S. Silverman, and M. Greenfield. Ma...

  50. [61]

    URLhttps://agupubs.onlinelibrary

    doi: https://doi.org/10.1029/2000JE001370. URLhttps://agupubs.onlinelibrary. wiley.com/doi/abs/10.1029/2000JE001370

    work page doi:10.1029/2000je001370

  51. [62]

    Mars climate sounder limb profile retrieval of atmospheric temperature, pressure, and dust and water ice opacity.Journal of Geophysical Research: Planets, 114(E10), 2009

    Armin Kleinböhl, John T Schofield, David M Kass, Wedad A Abdou, Charles R Backus, Bhaswar Sen, James H Shirley, W Gregory Lawson, Mark I Richardson, Fredric W Taylor, et al. Mars climate sounder limb profile retrieval of atmospheric temperature, pressure, and dust and water ice opacity.Journal of Geophysical Research: Planets, 114(E10), 2009

    2009

  52. [63]

    The emirates mars mission (emm) emirates mars infrared spectrometer (emirs) instrument.Space Science Reviews, 217(7):77, 2021

    Christopher S Edwards, Philip R Christensen, Greg L Mehall, Saadat Anwar, Eman Al Tu- naiji, Khalid Badri, Heather Bowles, Stillman Chase, Zoltan Farkas, Tara Fisher, et al. The emirates mars mission (emm) emirates mars infrared spectrometer (emirs) instrument.Space Science Reviews, 217(7):77, 2021. 51

    2021

  53. [64]

    Scot C. R. Rafkin, Robert M. Haberle, and Timothy I. Michaels. The Mars Regional Atmo- spheric Modeling System: Model description and selected simulations.Icarus, 151(2):228–256,

  54. [65]

    doi: 10.1006/icar.2001.6605

    work page doi:10.1006/icar.2001.6605 2001

  55. [66]

    Toigo, Christopher Lee, Claire E

    Anthony D. Toigo, Christopher Lee, Claire E. Newman, and Mark I. Richardson. The impact of resolution on the dynamics of the Martian global atmosphere: Varying resolution studies with the MarsWRF GCM.Icarus, 221(1):276–288, 2012. doi: 10.1016/j.icarus.2012.07.020

    work page doi:10.1016/j.icarus.2012.07.020 2012

  56. [67]

    Newman, Javier Gómez-Elvira, M

    Claire E. Newman, Javier Gómez-Elvira, M. Marin, S. Navarro, J. Torres, Mark I. Richardson, J. M. Battalio, Scott D. Guzewich, R. Sullivan, M. de la Torre Juárez, Ashwin R. Vasavada, and Nathan T. Bridges. Winds measured by the Rover Environmental Monitoring Station (REMS) during the Mars Science Laboratory (MSL) rover’s Bagnold Dunes campaign and compari...

    2017

  57. [68]

    Richardson, Xi Zhang, Jun Cui, Nicholas G

    Zhaopeng Wu, Mark I. Richardson, Xi Zhang, Jun Cui, Nicholas G. Heavens, Christopher Lee, Tao Li, Yuan Lian, Claire E. Newman, Alejandro Soto, Anthony D. Toigo, Marcin L. Witek, and Jun Yang. Large eddy simulations of the dusty Martian convective boundary layer with MarsWRF.Journal of Geophysical Research: Planets, 126(9):e2020JE006752, 2021. doi: 10.1029...

    work page doi:10.1029/2020je006752 2021

  58. [69]

    Senel, Stefano Porchetta, Domingo Muñoz-Esparza, Michael A

    Orkun Temel, Cem M. Senel, Stefano Porchetta, Domingo Muñoz-Esparza, Michael A. Mis- chna, Tim Van Hoolst, Jeroen van Beeck, and Özgür Karatekin. Large eddy simulations of the Martian convective boundary layer: Towards developing a new planetary boundary layer scheme.Atmospheric Research, 250:105381, 2021. doi: 10.1016/j.atmosres.2020.105381

    work page doi:10.1016/j.atmosres.2020.105381 2021

  59. [70]

    Developmentofafast, accurate radiative transfer model for the Martian atmosphere, past and present.Journal of Geophysical Research: Planets, 117(E10):E10009, 2012

    MichaelA.Mischna, ChristopherLee, andMarkI.Richardson. Developmentofafast, accurate radiative transfer model for the Martian atmosphere, past and present.Journal of Geophysical Research: Planets, 117(E10):E10009, 2012. doi: 10.1029/2012JE004110

    work page doi:10.1029/2012je004110 2012

  60. [71]

    ChristopherLee, W.GregoryLawson, MarkI.Richardson, JeffreyL.Anderson, NancyCollins, Tim Hoar, and Michael A. Mischna. Demonstration of ensemble data assimilation for Mars using DART, MarsWRF, and radiance observations from MGS TES.Journal of Geophysical Research: Planets, 116(E11):E11011, 2011. doi: 10.1029/2011JE003815

    work page doi:10.1029/2011je003815 2011

  61. [72]

    Co2 polar mass on mars determined from insight pressure data

    Victor Corchete. Co2 polar mass on mars determined from insight pressure data. Frontiers in Astronomy and Space Sciences, Volume 11 - 2024, 2025. ISSN 2296- 987X. doi: 10.3389/fspas.2024.1532334. URLhttps://www.frontiersin.org/journals/ astronomy-and-space-sciences/articles/10.3389/fspas.2024.1532334

    work page doi:10.3389/fspas.2024.1532334 2024

  62. [73]

    María Ruíz, Eduardo Sebastián-Martínez, Jose Antonio Rodríguez-Manfredi, Jorge Pla- García, Manuel de la Torre-Juarez, and Scot C. R. Rafkin. Meteorological changes across cu- riosity rover’s traverse using rems measurements and comparisons between measurements and mrams model results.Remote Sensing, 17(3), 2025. ISSN 2072-4292. doi: 10.3390/rs17030368. U...

    work page doi:10.3390/rs17030368 2025

  63. [74]

    Kok and Nilton O

    Jasper F. Kok and Nilton O. Renno. Enhancement of the emission of mineral dust aerosols by electric forces.Geophysical Research Letters, 33(19), 2006. doi: https://doi. org/10.1029/2006GL026284. URLhttps://agupubs.onlinelibrary.wiley.com/doi/abs/ 10.1029/2006GL026284. 52

    work page doi:10.1029/2006gl026284 2006

  64. [75]

    Ares, atmospheric relaxation and electric field sensor, the electric field experiment on netlander.Planetary and Space Science, 48 (12):1193–1200, 2000

    J.J Berthelier, R Grard, H Laakso, and M Parrot. Ares, atmospheric relaxation and electric field sensor, the electric field experiment on netlander.Planetary and Space Science, 48 (12):1193–1200, 2000. ISSN 0032-0633. doi: https://doi.org/10.1016/S0032-0633(00)00103-3. URLhttps://www.sciencedirect.com/science/article/pii/S0032063300001033. Mars Exploratio...

    work page doi:10.1016/s0032-0633(00)00103-3 2000

  65. [76]

    Fernández

    W. Fernández. Martian dust storms: A review.Earth, Moon, and Planets, 77:19–46, 1997. doi: https://doi.org/10.1023/A:1006134805153

    work page doi:10.1023/a:1006134805153 1997

  66. [77]

    Laura Kulowski, Huiqun Wang, and Anthony D. Toigo. The seasonal and spatial distribu- tion of textured dust storms observed by mars global surveyor mars orbiter camera.Ad- vances in Space Research, 59(2):715–721, 2017. ISSN 0273-1177. doi: https://doi.org/ 10.1016/j.asr.2016.10.028. URLhttps://www.sciencedirect.com/science/article/pii/ S0273117716306226

    work page doi:10.1016/j.asr.2016.10.028 2017

  67. [78]

    Martian dust storm distribution and annual cycle from mars daily global map observations

    HuiqunWang, MorganSaidel, MarkI.Richardson, AnthonyD.Toigo, andJ.MichaelBattalio. Martian dust storm distribution and annual cycle from mars daily global map observations. Icarus, 394:115416, 2023. ISSN 0019-1035. doi: https://doi.org/10.1016/j.icarus.2022.115416. URLhttps://www.sciencedirect.com/science/article/pii/S0019103522005085

    work page doi:10.1016/j.icarus.2022.115416 2023

  68. [79]

    Wang and J

    H. Wang and J. A. Fisher. North polar frontal clouds and dust storms on Mars during spring and summer.Icarus, 204(1):103–113, 2009. doi: 10.1016/j.icarus.2009.05.028

    work page doi:10.1016/j.icarus.2009.05.028 2009

  69. [80]

    D. P. Hinson and H. Wang. Further observations of regional dust storms and baroclinic eddies in the northern hemisphere of Mars.Icarus, 206:290–305, 2010. doi: 10.1016/j.icarus.2009.08. 019

    work page doi:10.1016/j.icarus.2009.08 2010

  70. [81]

    Ingersoll

    Huiqun Wang and Andrew P. Ingersoll. Martian clouds observed by mars global sur- veyor mars orbiter camera.Journal of Geophysical Research: Planets, 107(E10):8–1–8–16,

  71. [82]

    URLhttps://agupubs.onlinelibrary

    doi: https://doi.org/10.1029/2001JE001815. URLhttps://agupubs.onlinelibrary. wiley.com/doi/abs/10.1029/2001JE001815

    work page doi:10.1029/2001je001815

  72. [83]

    Martian extratropical cyclones.Nature, 278:531–532, 1979

    James PB Hunt GE. Martian extratropical cyclones.Nature, 278:531–532, 1979. doi: https: //doi.org/10.1038/278531a0

    work page doi:10.1038/278531a0 1979

  73. [84]

    Traveling waves in the martian atmosphere from mgs tes nadir data.Icarus, 170(2):365–403, 2004

    D Banfield, BJ Conrath, PJ Gierasch, R John Wilson, and MD Smith. Traveling waves in the martian atmosphere from mgs tes nadir data.Icarus, 170(2):365–403, 2004

    2004

  74. [85]

    Huiqun Wang, Richard W Zurek, and Mark I Richardson. Relationship between frontal dust storms and transient eddy activity in the northern hemisphere of mars as observed by mars global surveyor.Journal of Geophysical Research: Planets, 110(E7), 2005

    2005

  75. [86]

    D. P. Hinson. Radio occultation measurements of transient eddies in the northern hemisphere of mars.Journal of Geophysical Research, 111(E05002), 2006. doi: 10.1029/2005JE002612

    work page doi:10.1029/2005je002612 2006

  76. [87]

    J. L. Hollingsworth and M. A. Kahre. Extratropical cyclones, frontal waves, and Mars dust: Modeling and considerations.Geophysical Research Letters, 37(L22202), 2010. doi: 10.1029/ 2010GL044262

    2010

  77. [88]

    Sánchez-Lavega, A

    A. Sánchez-Lavega, A. Garro, T. del Río-Gaztelurrutia, R. Hueso, I. Ordoñez-Etxeberria, H. Chen Chen, et al. A seasonally recurrent annular cyclone in Mars northern latitudes and observations of a companion vortex.Journal of Geophysical Research: Planets, 123:3020–3034,

  78. [89]

    doi: 10.1029/2018JE005740. 53

    work page doi:10.1029/2018je005740

  79. [90]

    Marli: Mars Lidar for Measuring Global Wind and Aerosol Profiles from Orbit.Bulletin of the AAS, 55(8), oct 23 2023

    James Abshire, Daniel Cremons, Xiaoli Sun, Scott Guzewich, Michael Smith, and Floyd Hovis. Marli: Mars Lidar for Measuring Global Wind and Aerosol Profiles from Orbit.Bulletin of the AAS, 55(8), oct 23 2023. URLhttps://baas.aas.org/pub/2023n8i317p04

    2023

  80. [91]

    T. I. Michaels, A. Colaprete, and S. C. R. Rafkin. Significant vertical water transport by mountain-induced circulations on mars.Geophysical Research Letters, 33(16), 2006. doi: https://doi.org/10.1029/2006GL026562

    work page doi:10.1029/2006gl026562 2006

Showing first 80 references.