Exoplanet characterization using conditional invertible neural networks

• Verfasst von: Haldemann, Jonas [VerfasserIn]
• Verfasst von: Ksoll, Victor F. [VerfasserIn]
• Verfasst von: Walter, Daniel [VerfasserIn]
• Verfasst von: Alibert, Yann [VerfasserIn]
• Verfasst von: Klessen, Ralf S. [VerfasserIn]
• Verfasst von: Benz, Willy [VerfasserIn]
• Verfasst von: Köthe, Ullrich [VerfasserIn]
• Verfasst von: Ardizzone, Lynton [VerfasserIn]
• Verfasst von: Rother, Carsten [VerfasserIn]
• Titel: Exoplanet characterization using conditional invertible neural networks
• Verf.angabe: Jonas Haldemann, Victor Ksoll, Daniel Walter, Yann Alibert, Ralf S. Klessen, Willy Benz, Ullrich Koethe, Lynton Ardizzone, and Carsten Rother
• E-Jahr: 2022
• Jahr: 31 Jan 2022
• Umfang: 15 S.
• Fussnoten: Gesehen am 12.10.2022
• Titel Quelle: Enthalten in: De.arxiv.org
• Ort Quelle: [S.l.] : Arxiv.org, 1991
• Jahr Quelle: 2022
• Band/Heft Quelle: (2022), Artikel-ID 2202.00027, Seite 1-15
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Astrophysics - Earth and Planetary Astrophysics
• Sach-SW: Astrophysics - Instrumentation and Methods for Astrophysics
• Sach-SW: Computer Science - Machine Learning
• K10plus-PPN: 1818769484

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.