Accelerating exoplanet climate modelling: A machine learning approach to complement 3D GCM grid simulations

2025-08-14

AI Summary

High computational cost of 3D global climate models (GCMs) impedes large-scale atmospheric characterization of exoplanets. Method: We developed the first machine-learning climate surrogate model tailored to inflated hot Jupiters orbiting A–M dwarf stars, trained jointly on a dataset of 60 three-dimensional GCM simulations generated by ExoRad using both deep neural networks (DNNs) and XGBoost. Contribution/Results: The surrogate enables millisecond-scale, high-fidelity prediction of 3D temperature and wind fields for tidally locked gas giants. Reconstructed transmission spectra from DNN-predicted temperature fields deviate by <32 ppm from full GCM outputs, with negligible impact on chemical equilibrium and spectral synthesis. The model has been successfully deployed in validating PLATO mission candidates, substantially accelerating ensemble atmospheric characterization and observational interpretation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

With the development of ever-improving telescopes capable of observing exoplanet atmospheres in greater detail and number, there is a growing demand for enhanced 3D climate models to support and help interpret observational data from space missions like CHEOPS, TESS, JWST, PLATO, and Ariel. However, the computationally intensive and time-consuming nature of general circulation models (GCMs) poses significant challenges in simulating a wide range of exoplanetary atmospheres. This study aims to determine whether machine learning (ML) algorithms can be used to predict the 3D temperature and wind structure of arbitrary tidally-locked gaseous exoplanets in a range of planetary parameters. A new 3D GCM grid with 60 inflated hot Jupiters orbiting A, F, G, K, and M-type host stars modelled with Exorad has been introduced. A dense neural network (DNN) and a decision tree algorithm (XGBoost) are trained on this grid to predict local gas temperatures along with horizontal and vertical winds. To ensure the reliability and quality of the ML model predictions, WASP-121 b, HATS-42 b, NGTS-17 b, WASP-23 b, and NGTS-1 b-like planets, which are all targets for PLATO observation, are selected and modelled with ExoRad and the two ML methods as test cases. The DNN predictions for the gas temperatures are to such a degree that the calculated spectra agree within 32 ppm for all but one planet, for which only one single HCN feature reaches a 100 ppm difference. The developed ML emulators can reliably predict the complete 3D temperature field of an inflated warm to ultra-hot tidally locked Jupiter around A to M-type host stars. It provides a fast tool to complement and extend traditional GCM grids for exoplanet ensemble studies. The quality of the predictions is such that no or minimal effects on the gas phase chemistry, hence on the cloud formation and transmission spectra, are to be expected.

Problem

• Developing ML models to predict exoplanet climate structures efficiently
• Reducing computational cost of 3D GCM simulations for exoplanets
• Enhancing exoplanet atmospheric studies for space mission observations

Innovation

• Machine learning predicts exoplanet climate structures
• DNN and XGBoost trained on 3D GCM grid
• Fast ML tool complements traditional GCM simulations