![Radial gas temperature maps for planets within the in-house 3D GCM framework. The panels illustrate equatorial slice plots of (Tgas, pgas) across three global temperature regimes: 800 K (left), 1600 K (center), and 2400 K (right). Host star types vary by row, descending from A-type to G-type and M-type stars [1] -- [astro-ph.EP]](https://i0.wp.com/astrobiology.com/wp-content/uploads/2026/09/Faithful.png?fit=1200%2C673&ssl=1)
[astro-ph.EP] With the rapid advancement of telescopes like JWST and Ariel, there is an urgent need for efficient 3D climate models to interpret observations of exoplanet atmospheres.
Traditional 3D general circulation models (GCMs) are computationally intensive, prompting the development of machine learning (ML) emulators to accelerate simulations. Recent work, such as that by Plaschzug et al. 2026 plaschzug 2026 accelerating, uses a dense neural network (DNN) to predict local gas temperatures and winds from input parameters, including local gas pressure, spatial coordinates (longitude and latitude), and global temperature.
However, this model relies on predicting individual temperature values (points) at specific grid points, which can be limited by the resolution and constraints of the training grid. In this work, we investigate a couple of alternative frameworks based on latent-space representations of local gas temperature (Tgas) to obtain a faithful, low-dimensional representation of these profiles.
This represents the first step toward developing a latent space regression model, offering a structurally cohesive alternative to the existing point-wise prediction method plaschzug 2026 accelerating. By capturing the optimal embedding space of atmospheric data, our proposed framework can produce simulated profiles while maintaining computational efficiency, making it suitable for large-scale exoplanet ensemble studies.
Amit Reza, Ludmila Carone, Christiane Helling
Comments: This work has been accepted for publication in the peer-reviewed proceedings of the European Space Agency’s Space Applications of Artificial Intelligence and Cognitive Engineering (SPAICE) Conference 2026
Subjects: Earth and Planetary Astrophysics (astro-ph.EP)
Cite as: arXiv:2609.21706 [astro-ph.EP] (or arXiv:2609.21706v1 [astro-ph.EP] for this version)
https://doi.org/10.48550/arXiv.2609.21706
Focus to learn more
Submission history
From: Amit Reza
[v1] Fri, 18 Sep 2026 12:43:59 UTC (926 KB)
https://arxiv.org/abs/2609.21706
Astrobiology, Exoplanet,
