Publication: Optimizing exoplanet atmosphere retrieval using unsupervised machine-learning classification
1
Issued Date
2021-01-01
Resource Type
ISSN
13652966
00358711
00358711
Other identifier(s)
2-s2.0-85088572475
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
Monthly Notices of the Royal Astronomical Society. Vol.494, No.3 (2021), 4492-4508
Suggested Citation
J. J.C. Hayes, E. Kerins, S. Awiphan, I. McDonald, J. S. Morgan, P. Chuanraksasat, S. Komonjinda, N. Sanguansak, P. Kittara Optimizing exoplanet atmosphere retrieval using unsupervised machine-learning classification. Monthly Notices of the Royal Astronomical Society. Vol.494, No.3 (2021), 4492-4508. doi:10.1093/mnras/staa978 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/76871
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Optimizing exoplanet atmosphere retrieval using unsupervised machine-learning classification
Abstract
One of the principal bottlenecks to atmosphere characterization in the era of all-sky surveys is the availability of fast, autonomous, and robust atmospheric retrieval methods. We present a new approach using unsupervised machine learning to generate informed priors for retrieval of exoplanetary atmosphere parameters from transmission spectra. We use principal component analysis (PCA) to efficiently compress the information content of a library of transmission spectra forward models generated using the PLATON package. We then apply a k-means clustering algorithm in PCA space to segregate the library into discrete classes. We show that our classifier is almost always able to instantaneously place a previously unseen spectrum into the correct class, for low-to-moderate spectral resolutions, R, in the range R = 30−300 and noise levels up to 10 per cent of the peak-to-trough spectrum amplitude. The distribution of physical parameters for all members of the class therefore provides an informed prior for standard retrieval methods such as nested sampling. We benchmark our informed-prior approach against a standard uniform-prior nested sampler, finding that our approach is up to a factor of 2 faster, with negligible reduction in accuracy. We demonstrate the application of this method to existing and near-future observatories, and show that it is suitable for real-world application. Our general approach is not specific to transmission spectroscopy and should be more widely applicable to cases that involve the repetitive fitting of trusted high-dimensional models to large data catalogues, including beyond exoplanetary science.