Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 343 - Astrostatistics Interest Group: Student Paper Award
Type: Topic-Contributed
Date/Time: Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
Sponsor: Astrostatistics Special Interest Group
Abstract #317364
Title: Assessment of Supervised Machine Learning for Atmospheric Retrieval of Exoplanets
Author(s): Matthew Conor Nixon* and Nikku Madhusudhan
Companies: Institute of Astronomy, University of Cambridge and Institute of Astronomy, University of Cambridge
Keywords: Exoplanets; Machine Learning; Random Forest; Atmospheric Retrieval; Astrophysics; Astrostatistics

Atmospheric retrieval of exoplanets from spectroscopic observations requires an extensive exploration of a highly degenerate and high-dimensional parameter space. Retrieval methods commonly conduct Bayesian parameter estimation and statistical inference using sampling algorithms such as Markov chain Monte Carlo or Nested Sampling. Recently several attempts have been made to use machine learning algorithms either to complement or to replace fully Bayesian methods. In this talk, I will discuss work investigating the efficacy of machine learning for atmospheric retrieval. As a case study, we use the Random Forest algorithm which has been applied previously with some success for atmospheric retrieval. We extend this method to develop a new algorithm that results in a closer match to a fully Bayesian retrieval. We demonstrate excellent agreement between our method and a Bayesian retrieval of the transmission spectrum of a hot Jupiter. Despite this success, and achieving high computational efficiency, we find that the machine learning approach is computationally prohibitive for high-dimensional parameter spaces that are routinely explored with Bayesian retrievals.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program