English

Towards a Foundation Model for the Martian Atmosphere

Earth and Planetary Astrophysics 2026-05-29 v1 Instrumentation and Methods for Astrophysics Machine Learning Atmospheric and Oceanic Physics

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.

Keywords

Cite

@article{arxiv.2605.28851,
  title  = {Towards a Foundation Model for the Martian Atmosphere},
  author = {Sujit Roy and Udayshankar Nair and Yuling Wu and Georgios Priftis and Liping Wang and Anastasia Georgiou and Anne Jones and Björn Lütjens and Johannes Schmude and Campbell Watson and Rachel A. Slank and Ankur Kumar and Anirbit Mukherjee and Procheta Sen and Ramin Lolachi and Haonan Chen and Manil Maskey and Juan Bernabé-Moreno and Rahul Ramachandran},
  journal= {arXiv preprint arXiv:2605.28851},
  year   = {2026}
}
R2 v1 2026-07-22T07:37:52.276Z