Decoding RR Lyrae light curves with deep learning for accurate absolute magnitude estimation
Abstract
RR Lyrae stars are essential standard candles for distance measurements in the Milky Way and nearby galaxies. Traditional estimates rely on the Period--Absolute Magnitude--Metallicity relation but are limited by uncertainties in metallicity determinations. We present a deep learning approach that directly predicts absolute magnitudes from RRab and RRc light curves, eliminating the need for metallicity estimates. Our model achieves validation precisions of 0.053 mag and 0.036 mag (approximately 2.5% and 1.7% in distance) for individual RRab and RRc stars, respectively. Tests on globular clusters yield typical distance precisions of 1.0% for RRab and 1.7% for RRc stars. For the benchmark systems, combining the RRab- and RRc-based models yields distance moduli of 18.498 ± 0.001stat ± 0.018sys mag for the Large Magellanic Cloud and 19.564 ± 0.003stat ± 0.019sys mag for the Sculptor dwarf spheroidal galaxy. These measurements are in excellent agreement with previous results, achieve a distance precision of approximately 1%, and represent a 1.8-fold improvement over traditional RR Lyrae calibration relations. Our approach showcases the ability of AI to directly extract key physical parameters from complex, information-rich light curves, resolve degeneracies, and scale to broader applications.
Versions
Related
- The EBLM project - XX. Absolute dynamical masses of five low-mass eclipsing binaries, and an evaluation of mass estimation methods
- Decoding the Imprints of Energy-Momentum Squared Gravity in Neutron Stars with Machine Learning Analysis
- A deep learning algorithm for black hole spin estimation using hot spot secondary images
- A deep learning approach to member identification and mass estimation in galaxy clusters
- Super-Resolution of Solar Magnetograms via Adaptive Stratified Ensemble Learning with Uncertainty Estimation
BibTeX
@misc{he2026decoding,
title = {{Decoding RR Lyrae light curves with deep learning for accurate absolute magnitude estimation}},
author = {Shunxuan He and Huiwen Wu and Yang Huang and Deyi Zhang and Guirong Xue and Jifeng Liu and Xiaodian Chen and Xinyu Qi and Xiaoyu Tang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.14342},
eprint = {2609.14342},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.14342},
}
RIS
TY - UNPB
TI - Decoding RR Lyrae light curves with deep learning for accurate absolute magnitude estimation
AU - Shunxuan He
AU - Huiwen Wu
AU - Yang Huang
AU - Deyi Zhang
AU - Guirong Xue
AU - Jifeng Liu
AU - Xiaodian Chen
AU - Xinyu Qi
AU - Xiaoyu Tang
PY - 2026
DA - 2026/09/13
PB - arXiv
DO - 10.48550/arxiv.2609.14342
UR - https://arxiv.org/abs/2609.14342
AB - RR Lyrae stars are essential standard candles for distance measurements in the Milky Way and nearby galaxies. Traditional estimates rely on the Period--Absolute Magnitude--Metallicity relation but are limited by uncertainties in metallicity determinations. We present a deep learning approach that directly predicts absolute magnitudes from RRab and RRc light curves, eliminating the need for metallicity estimates. Our model achieves validation precisions of 0.053 mag and 0.036 mag (approximately 2.5% and 1.7% in distance) for individual RRab and RRc stars, respectively. Tests on globular clusters yield typical distance precisions of 1.0% for RRab and 1.7% for RRc stars. For the benchmark systems, combining the RRab- and RRc-based models yields distance moduli of 18.498 ± 0.001_stat ± 0.018_sys mag for the Large Magellanic Cloud and 19.564 ± 0.003_stat ± 0.019_sys mag for the Sculptor dwarf spheroidal galaxy. These measurements are in excellent agreement with previous results, achieve a distance precision of approximately 1%, and represent a 1.8-fold improvement over traditional RR Lyrae calibration relations. Our approach showcases the ability of AI to directly extract key physical parameters from complex, information-rich light curves, resolve degeneracies, and scale to broader applications.
ER -