Exoplanet Characterization using Conditional Invertible Neural Networks

Abstract

The characterization of an exoplanet's interior is an inverse problem, which requires statistical methods such as Bayesian inference in order to be solved. Current methods employ Markov Chain Monte Carlo (MCMC) sampling to infer the posterior probability of planetary structure parameters for a given exoplanet. These methods are time consuming since they require the calculation of a large number of planetary structure models. To speed up the inference process when characterizing an exoplanet, we propose to use conditional invertible neural networks (cINNs) to calculate the posterior probability of the internal structure parameters. cINNs are a special type of neural network which excel in solving inverse problems. We constructed a cINN using FrEIA, which was then trained on a database of $5.6\cdot 10^6$ internal structure models to recover the inverse mapping between internal structure parameters and observable features (i.e., planetary mass, planetary radius and composition of the host star). The cINN method was compared to a Metropolis-Hastings MCMC. For that we repeated the characterization of the exoplanet K2-111 b, using both the MCMC method and the trained cINN. We show that the inferred posterior probability of the internal structure parameters from both methods are very similar, with the biggest differences seen in the exoplanet's water content. Thus cINNs are a possible alternative to the standard time-consuming sampling methods. Indeed, using cINNs allows for orders of magnitude faster inference of an exoplanet's composition than what is possible using an MCMC method, however, it still requires the computation of a large database of internal structures to train the cINN. Since this database is only computed once, we found that using a cINN is more efficient than an MCMC, when more than 10 exoplanets are characterized using the same cINN.

arXiv comment15 pages, 13 figures, submitted to Astronomy & Astrophysics

References in corpus (20)

• emcee: The MCMC Hammer
• Bayes in the sky: Bayesian inference and model selection in cosmology
• Can we constrain interior structure of rocky exoplanets from mass and radius measurements?
• Exoplanetary Atmospheres: Key Insights, Challenges and Prospects
• A Framework for Quantifying the Degeneracies of Exoplanet Interior Compositions
• Data analysis recipes: Using Markov Chain Monte Carlo
• The CHEOPS mission
• A spectral survey of an ultra-hot Jupiter: Detection of metals in the transmission spectrum of KELT-9 b
• A generalized bayesian inference method for constraining the interiors of super Earths and sub-Neptunes
• AQUA: A Collection of H${}_2$O Equations of State for Planetary Models
• Elemental ratios in stars vs planets
• A new ab initio equation of state of hcp-Fe and its implication on the interior structure and mass-radius relations of rocky super-Earths
• Chemical Fingerprints of Formation in Rocky Super-Earths' Data
• Ab initio based equation of state of dense water for planetary and exoplanetary modeling
• Bayesian analysis of interiors of HD 219134b, Kepler-10b, Kepler-93b, CoRoT-7b, 55 Cnc e, and HD 97658b using stellar abundance proxies
• Machine learning inference of the interior structure of low-mass exoplanets
• K2-111: an old system with two planets in near-resonance
• Stellar Parameter Determination from Photometry using Invertible Neural Networks
• Using Deep Neural Networks to compute the mass of forming planets
• Emission-line diagnostics of HII regions using conditional Invertible Neural Networks

Cited by in corpus (1)

• Polar Encoding: A Simple Baseline Approach for Classification with Missing Values