Supervised Machine Learning Methods with Uncertainty Quantification for Exoplanet Atmospheric Retrievals from Transmission Spectroscopy
By: Roy T. Forestano , Konstantin T. Matchev , Katia Matcheva and more
Potential Business Impact:
Faster computer guesses about alien planets.
Standard Bayesian retrievals for exoplanet atmospheric parameters from transmission spectroscopy, while well understood and widely used, are generally computationally expensive. In the era of the JWST and other upcoming observatories, machine learning approaches have emerged as viable alternatives that are both efficient and robust. In this paper we present a systematic study of several existing machine learning regression techniques and compare their performance for retrieving exoplanet atmospheric parameters from transmission spectra. We benchmark the performance of the different algorithms on the accuracy, precision, and speed. The regression methods tested here include partial least squares (PLS), support vector machines (SVM), k nearest neighbors (KNN), decision trees (DT), random forests (RF), voting (VOTE), stacking (STACK), and extreme gradient boosting (XGB). We also investigate the impact of different preprocessing methods of the training data on the model performance. We quantify the model uncertainties across the entire dynamical range of planetary parameters. The best performing combination of ML model and preprocessing scheme is validated on a the case study of JWST observation of WASP-39b.
Similar Papers
Understanding Exoplanet Habitability: A Bayesian ML Framework for Predicting Atmospheric Absorption Spectra
Earth and Planetary Astrophysics
Helps find alien planets' air.
Exoplanetary atmospheres retrieval via a quantum extreme learning machine
Quantum Physics
Quantum computers help find alien planet air faster.
Accelerating exoplanet climate modelling: A machine learning approach to complement 3D GCM grid simulations
Earth and Planetary Astrophysics
Helps predict alien planet weather faster.