Reconstructing Atmospheric Parameters of Exoplanets Using Deep Learning

Abstract

Exploring exoplanets has transformed our understanding of the universe by revealing many planetary systems that defy our current understanding. To study their atmospheres, spectroscopic observations are used to infer essential atmospheric properties that are not directly measurable. Estimating atmospheric parameters that best fit the observed spectrum within a specified atmospheric model is a complex problem that is difficult to model. In this paper, we present a multi-target probabilistic regression approach that combines deep learning and inverse modeling techniques within a multimodal architecture to extract atmospheric parameters from exoplanets. Our methodology overcomes computational limitations and outperforms previous approaches, enabling efficient analysis of exoplanetary atmospheres. This research contributes to advancements in the field of exoplanet research and offers valuable insights for future studies.

arXiv comment5 pages + references

References in corpus (16)

• The James Webb Space Telescope
• Origins of Hot Jupiters
• Exploring Exoplanet Populations with NASA's Kepler Mission
• How to Characterize Habitable Worlds and Signs of Life
• Retrieving scattering clouds and disequilibrium chemistry in the atmosphere of HR 8799e
• TauREx III: A fast, dynamic and extendable framework for retrievals
• Diurnal variations in the stratosphere of the ultrahot giant exoplanet WASP-121b
• On The Compatibility of Ground-based and Space-based Data: WASP-96 b, An Example
• ArielRad: the Ariel Radiometric Model
• Accurate Machine Learning Atmospheric Retrieval via a Neural Network Surrogate Model for Radiative Transfer
• Convolutional neural networks as an alternative to Bayesian retrievals
• Confirmation of Water Absorption in the Thermal Emission Spectrum of the Hot Jupiter WASP-77Ab with HST/WFC3
• Debris Disks in Kepler Exoplanet Systems
• On spectroscopic phase-curve retrievals: H2 dissociation and thermal inversion in the atmosphere of the ultra-hot Jupiter WASP-103 b
• Alfnoor: assessing the information content of Ariel's low resolution spectra with planetary population studies
• PyLightcurve-torch: a transit modelling package for deep learning applications in PyTorch