Habitability classification of exoplanets: a machine learning insight

Abstract

We explore the efficacy of machine learning (ML) in characterizing exoplanets into different classes. The source of the data used in this work is University of Puerto Rico's Planetary Habitability Laboratory's Exoplanets Catalog (PHL-EC). We perform a detailed analysis of the structure of the data and propose methods that can be used to effectively categorize new exoplanet samples. Our contributions are twofold. We elaborate on the results obtained by using ML algorithms by stating the accuracy of each method used and propose a paradigm to automate the task of exoplanet classification for relevant outcomes. In particular, we focus on the results obtained by novel neural network architectures for the classification task, as they have performed very well despite complexities that are inherent to this problem. The exploration led to the development of new methods fundamental and relevant to the context of the problem and beyond. The data exploration and experimentation also result in the development of a general data methodology and a set of best practices which can be used for exploratory data analysis experiments.

On the application of machine learning in astronomy and astrophysics: A text‐mining‐based scientometric analysis

“…Another field related to stellar astrophysics that appears in this group—through the terms “planets and satellites: detect” and “light curves”—is the detection of exoplanets and transit objects. In this regard, ML models have substantially improved the accuracy in identifying candidates for extrasolar planets (Armstrong et al, 2018; Jara‐Maldonado et al, 2020; Mislis et al, 2018), determining their possible habitability (Basak et al, 2021; Saha et al, 2018), and evaluating the composition of their atmosphere (Hayes et al, 2020; Márquez‐Neila et al, 2018). With regard to transit objects, AI has made it possible to accelerate their identification, especially in real‐time applications (Bellm et al, 2019; Djorgovski et al, 2016; Sánchez et al, 2018).…”

Measure or infer? Role of modeling and machine learning in modern astronomy

“…Archana Mathur et al [4] delve further into this challenging problem of classification of exoplanets using ML. They propose a paradigm to automate the task of exoplanet classification by performing a detailed analysis of the structure of the Puerto Rico's Planetary Habitability Laboratory's Exoplanet Catalog dataset (PHL-EC).…”