Optimizing exoplanet atmosphere retrieval using unsupervised machine-learning classification

TL;DR

This paper introduces an unsupervised machine learning method using PCA and k-means clustering to generate informed priors for exoplanet atmosphere retrieval, significantly speeding up the process while maintaining accuracy.

Contribution

The novel approach combines PCA and clustering to create informed priors, improving retrieval speed and efficiency over traditional uniform priors in exoplanet atmosphere analysis.

Findings

Classifier accurately assigns unseen spectra to correct classes at R=30-300

Informed priors reduce retrieval time by up to 50%

Method is applicable to real-world and future observational data

Abstract

One of the principal bottlenecks to atmosphere characterisation 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 two 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 repetitive fitting of trusted high-dimensional models to large data catalogues, including beyond exoplanetary science.