ExoGAN: Exoplanets Generative Adversarial Network
Abstract
ExoGAN (Exoplanets Generative Adversarial Network) analyzes exoplanetary atmospheres using an unsupervised deep-learning algorithm that recognizes molecular features, atmospheric trace-gas abundances, and planetary parameters. After training, ExoGAN can be applied to a large number of instruments and planetary types and can be used either as a final atmospheric analysis or to provide prior constraints to subsequent retrieval.
- Publication:
-
Astrophysics Source Code Library
- Pub Date:
- December 2018
- Bibcode:
- 2018ascl.soft12007Z
- Keywords:
-
- Software