Abstract
Abstract Atmospheric retrievals on exoplanets usually involve computationally intensive Bayesian sampling methods. Large parameter spaces and increasingly complex atmospheric models create a computational bottleneck forcing a trade-off between statistical sampling accuracy and model complexity. It is especially true for upcoming JWST and ARIEL observations. We introduce ExoGAN, the Exoplanet Generative Adversarial Network, a new deep-learning algorithm able to recognize molecular features, atmospheric trace-gas abundances, and planetary parameters using unsupervised learning. Once trained, ExoGAN is widely applicable to a large number of instruments and planetary types. The ExoGAN retrievals constitute a significant speed improvement over traditional retrievals and can be used either as a final atmospheric analysis or provide prior constraints to subsequent retrieval.
Highlights
The modeling of exoplanetary atmospheric spectroscopy through so-called atmospheric retrieval algorithms has become the accepted standard in the interpretation of transmission and emission spectroscopic measurements (e.g., Rocchetto et al 2016; Barstow et al 2017; Sheppard et al 2017; Bruno et al 2018; Kreidberg et al 2018; Mansfield et al 2018; Spake et al 2018; Tsiaras et al 2018)
For each value we show the input value used for the spectrum and the predicted result from Exoplanet Generative Adversarial Network (ExoGAN)
We generated a second synthetic spectrum of HD 189733b between 0.3 and 15 μm, using the parameters of Venot et al (2012) and overplotted the TauREx retrieved posterior distributions with those derived by ExoGAN, Figure 11
Summary
The modeling of exoplanetary atmospheric spectroscopy through so-called atmospheric retrieval algorithms has become the accepted standard in the interpretation of transmission and emission spectroscopic measurements (e.g., Rocchetto et al 2016; Barstow et al 2017; Sheppard et al 2017; Bruno et al 2018; Kreidberg et al 2018; Mansfield et al 2018; Spake et al 2018; Tsiaras et al 2018). The most commonly adopted statistical sampling methods are Nested Sampling (Skilling 2004; Feroz & Hobson 2008; Feroz et al 2009) and Markov Chain Monte Carlo (e.g., Gregory 2011) These approaches typically require of the order of 105–106 forward model realizations until convergence. We present the first deep-learning architecture for exoplanetary atmospheric
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
