Faithful Neural Embeddings for 3D Exoplanet Climate Modeling
Abstract
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 \cite{plaschzug2026accelerating}, 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 \cite{plaschzug2026accelerating}. 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.
Related
- Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks
- Graph neural networks for exoplanet atmospheres
- The Fast and Fourier: Using neural operators to speed up radiative modeling of protoplanetary disks
- AEGIS: Differentiable Mars Climate Model with Neural Closures
- Modeling Multi-band Active Galactic Nuclei Lightcurves Using an Self-supervised Attentive Neural Process Network
BibTeX
@misc{reza2026faithful,
title = {{Faithful Neural Embeddings for 3D Exoplanet Climate Modeling}},
author = {Amit Reza and Ludmila Carone and Christiane Helling},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21706},
eprint = {2609.21706},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21706},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Faithful Neural Embeddings for 3D Exoplanet Climate Modeling
AU - Amit Reza
AU - Ludmila Carone
AU - Christiane Helling
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2609.21706
UR - https://arxiv.org/abs/2609.21706
AB - 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 \cite{plaschzug2026accelerating}, 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 (T_gas) 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 \cite{plaschzug2026accelerating}. 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.
ER -