Predicting Exoplanetary Features with a Residual Model for Uniform and Gaussian Distributions

TL;DR

This paper presents a novel deep learning approach combining Gaussian and uniform distribution models to predict exoplanetary features, achieving competitive results in the 2023 Ariel Data Challenge.

Contribution

It introduces a hybrid residual model that effectively predicts posterior distributions of exoplanet features, addressing stability issues in training and improving prediction accuracy.

Findings

Ensemble of uniform distributions achieved a competitive posterior score.

Combining Gaussian and uniform models improved overall prediction performance.

Final ranking was third in the 2023 Ariel Data Challenge.

Abstract

The advancement of technology has led to rampant growth in data collection across almost every field, including astrophysics, with researchers turning to machine learning to process and analyze this data. One prominent example of this data in astrophysics is the atmospheric retrievals of exoplanets. In order to help bridge the gap between machine learning and astrophysics domain experts, the 2023 Ariel Data Challenge was hosted to predict posterior distributions of 7 exoplanetary features. The procedure outlined in this paper leveraged a combination of two deep learning models to address this challenge: a Multivariate Gaussian model that generates the mean and covariance matrix of a multivariate Gaussian distribution, and a Uniform Quantile model that predicts quantiles for use as the upper and lower bounds of a uniform distribution. Training of the Multivariate Gaussian model was found to be unstable, while training of the Uniform Quantile model was stable. An ensemble of uniform distributions was found to have competitive results during testing (posterior score of 696.43), and when combined with a multivariate Gaussian distribution achieved a final rank of third in the 2023 Ariel Data Challenge (final score of 681.57).