Probabilistic Stellar Mass and Radius Estimation with Bayesian Hierarchical Stacking
Abstract
Accurate stellar parameters are essential for the characterisation of exoplanets, yet most host stars lack direct measurements of mass and radius. We aim to predict stellar masses and radii from commonly available observables and to quantify uncertainties and systematic effects in a way that is consistent with stellar observations. By not relying on a single model, we aim to obtain more robust predictive distributions and reduce sensitivity to model misspecification and outliers. We develop a Bayesian machine-learning framework that combines three probabilistic models through Bayesian hierarchical stacking (BHS): a Bayesian additive regression tree model, a two-process heteroscedastic sparse Gaussian process, and a hierarchical Bayesian neural network. The method propagates measurement uncertainties, accounts for correlations among inputs, and aggregates model variance into final predictive distributions. On a held-out test set the method attains a mean absolute relative difference (MARD) of 3.5% for mass and 2.1% for radius, improving on empirical-relation-based methods and standard machine-learning baselines. For 44 Kepler LEGACY stars, the BHS masses differ from estimates obtained with the BAyesian STellar Algorithm (BASTA) by a MARD of 4.8%, compared with 8.5% between the empirical relations and BASTA. Applied to about 2400 exoplanet host stars, the predictions differ from literature values by a MARD of 2.7% in both mass and radius. Residual analysis reveals mild underestimation for cool dwarfs, consistent with sparse training coverage, and positive offsets near the main-sequence turn-off that may reflect priors in isochrone-based catalogues. Internal consistency with g = GM/R^2 is greater for the BHS predictions, with a scatter in Delta log g lower by a factor of three than that of the literature values.
Related
- Probabilistic redshift estimation of undetected galaxies from multi-band background light maps
- Automated Detection of Double-Lined Spectroscopic Binaries in High-Resolution Spectra and a Probabilistic Analysis of Stellar Multiplicity
- LACHESIS: Robust stellar parameters through Bayesian model averaging of isochrone grids
- Constraining AGN Disk Properties with Gravitational Waves from Inspiraling Stellar-Mass Binary Black Holes in Hierarchical Triple Systems
- An improved standardization framework for Type II-P supernovae using a hierarchical Bayesian approach
BibTeX
@misc{lamirel2026probabilistic,
title = {{Probabilistic Stellar Mass and Radius Estimation with Bayesian Hierarchical Stacking}},
author = {Maxence Lamirel and Andrés Moya and Roberto J. López-Sastre and Luis Manuel Sarro},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.37968},
eprint = {2610.37968},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.37968},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Probabilistic Stellar Mass and Radius Estimation with Bayesian Hierarchical Stacking
AU - Maxence Lamirel
AU - Andrés Moya
AU - Roberto J. López-Sastre
AU - Luis Manuel Sarro
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.37968
UR - https://arxiv.org/abs/2610.37968
AB - Accurate stellar parameters are essential for the characterisation of exoplanets, yet most host stars lack direct measurements of mass and radius. We aim to predict stellar masses and radii from commonly available observables and to quantify uncertainties and systematic effects in a way that is consistent with stellar observations. By not relying on a single model, we aim to obtain more robust predictive distributions and reduce sensitivity to model misspecification and outliers. We develop a Bayesian machine-learning framework that combines three probabilistic models through Bayesian hierarchical stacking (BHS): a Bayesian additive regression tree model, a two-process heteroscedastic sparse Gaussian process, and a hierarchical Bayesian neural network. The method propagates measurement uncertainties, accounts for correlations among inputs, and aggregates model variance into final predictive distributions. On a held-out test set the method attains a mean absolute relative difference (MARD) of 3.5% for mass and 2.1% for radius, improving on empirical-relation-based methods and standard machine-learning baselines. For 44 Kepler LEGACY stars, the BHS masses differ from estimates obtained with the BAyesian STellar Algorithm (BASTA) by a MARD of 4.8%, compared with 8.5% between the empirical relations and BASTA. Applied to about 2400 exoplanet host stars, the predictions differ from literature values by a MARD of 2.7% in both mass and radius. Residual analysis reveals mild underestimation for cool dwarfs, consistent with sparse training coverage, and positive offsets near the main-sequence turn-off that may reflect priors in isochrone-based catalogues. Internal consistency with g = GM/R^2 is greater for the BHS predictions, with a scatter in Delta log g lower by a factor of three than that of the literature values.
ER -