Exoplanet characterization using conditional invertible neural networks
Abstract
Context. The characterization of the interior of an exoplanet is an inverse problem. The solution requires statistical methods such as Bayesian inference. Current methods employ Markov chain Monte Carlo (MCMC) sampling to infer the posterior probability of the planetary structure parameters for a given exoplanet. These methods are timeconsuming because they require the evaluation of a planetary structure model ~10^{5} times.
Aims: To speed up the inference process when characterizing an exoplanet, we propose to use conditional invertible neural networks to calculate the posterior probability of the planetary structure parameters.
Methods: Conditional invertible neural networks (cINNs) are a special type of neural network that excels at solving inverse problems. We constructed a cINN following the framework for easily invertible architectures (FreIA). This neural network was then trained on a database of 5.6 × 10^{6} internal structure models to recover the inverse mapping between internal structure parameters and observable features (i.e., planetary mass, planetary radius, and elemental composition of the host star). We also show how observational uncertainties can be accounted for.
Results: The cINN method was compared to a commonly used MetropolisHastings MCMC. To do this, we repeated the characterization of the exoplanet K2111 b, using both the MCMC method and the trained cINN. We show that the inferred posterior probability distributions of the internal structure parameters from both methods are very similar; the largest differences are seen in the exoplanet water content. Thus, cINNs are a possible alternative to the standard timeconsuming sampling methods. cINNs allow infering the composition of an exoplanet that is orders of magnitude faster than what is possible using an MCMC method. The computation of a large database of internal structures to train the neural network is still required, however. Because this database is only computed once, we found that using an invertible neural network is more efficient than an MCMC when more than ten exoplanets are characterized using the same neural network.
 Publication:

Astronomy and Astrophysics
 Pub Date:
 April 2023
 DOI:
 10.1051/00046361/202243230
 arXiv:
 arXiv:2202.00027
 Bibcode:
 2023A&A...672A.180H
 Keywords:

 planets and satellites: interiors;
 methods: numerical;
 methods: data analysis;
 Astrophysics  Earth and Planetary Astrophysics;
 Astrophysics  Instrumentation and Methods for Astrophysics;
 Computer Science  Machine Learning
 EPrint:
 15 pages, 13 figures, submitted to Astronomy &