Revisiting mass-radius relationships for exoplanet populations: a machine learning insight
This work provides incremental insights into exoplanet classification and radius prediction using machine learning, aiding astronomers in understanding planetary populations.
The study applied machine learning to analyze 762 exoplanets and eight Solar System planets, classifying them into 'small' and 'giant' categories with cut-offs at 8.13 Earth radii and 52.48 Earth masses, revealing that giant planets have lower densities suggesting higher H-He fractions while small planets are denser. It found that Support Vector Regression outperformed other models for predicting exoplanet radius, with key predictors being planetary mass, orbital period, and stellar mass, and observed a positive linear mass-radius relation for small planets and a strong correlation between giant planet radius and host star mass.
The growing number of exoplanet discoveries and advances in machine learning techniques have opened new avenues for exploring and understanding the characteristics of worlds beyond our Solar System. In this study, we employ efficient machine learning approaches to analyze a dataset comprising 762 confirmed exoplanets and eight Solar System planets, aiming to characterize their fundamental quantities. By applying different unsupervised clustering algorithms, we classify the data into two main classes: 'small' and 'giant' planets, with cut-off values at $R_{p}=8.13R_{\oplus}$ and $M_{p}=52.48M_{\oplus}$. This classification reveals an intriguing distinction: giant planets have lower densities, suggesting higher H-He mass fractions, while small planets are denser, composed mainly of heavier elements. We apply various regression models to uncover correlations between physical parameters and their predictive power for exoplanet radius. Our analysis highlights that planetary mass, orbital period, and stellar mass play crucial roles in predicting exoplanet radius. Among the models evaluated, the Support Vector Regression consistently outperforms others, demonstrating its promise for obtaining accurate planetary radius estimates. Furthermore, we derive parametric equations using the M5P and Markov Chain Monte Carlo methods. Notably, our study reveals a noteworthy result: small planets exhibit a positive linear mass-radius relation, aligning with previous findings. Conversely, for giant planets, we observe a strong correlation between planetary radius and the mass of their host stars, which might provide intriguing insights into the relationship between giant planet formation and stellar characteristics.