发表机构
University of Chinese Academy of Sciences; National Astronomical Observatories, Chinese Academy of Sciences; Zhejiang Laboratory（中国科学院大学; 中国科学院国家天文台; 浙江实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出用深度学习直接从天琴座RR型变星光变曲线预测绝对星等，无需金属丰度，达到约1%的距离精度，较传统方法提升1.8倍。
AI 中文摘要
天琴座RR型变星是测量银河系及邻近星系距离的重要标准烛光。传统估计依赖于周期-绝对星等-金属丰度关系，但受限于金属丰度测定中的不确定性。我们提出了一种深度学习方法，直接从RRab和RRc型光变曲线预测绝对星等，无需金属丰度估计。我们的模型对单个RRab和RRc型星分别实现了0.053星等和0.036星等的验证精度（对应距离精度约2.5%和1.7%）。对球状星团的测试显示，RRab和RRc型星的距离精度典型值分别为1.0%和1.7%。对于基准系统，结合基于RRab和RRc的模型，得到大麦哲伦云的距离模数为18.498 $\pm$ 0.001$_{\text{stat}}$ $\pm$ 0.018$_{\text{sys}}$星等，玉夫座矮椭球星系的距离模数为19.564 $\pm$ 0.003$_{\text{stat}}$ $\pm$ 0.019$_{\text{sys}}$星等。这些测量结果与以往结果高度一致，实现了约1%的距离精度，相比传统天琴座RR型变星校准关系有1.8倍的改进。我们的方法展示了人工智能直接从复杂、信息丰富的光变曲线中提取关键物理参数、解决简并问题并扩展到更广泛应用的能力。
英文摘要
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 $\pm$ 0.001$_{\text{stat}}$ $\pm$ 0.018$_{\text{sys}}$ mag for the Large Magellanic Cloud and 19.564 $\pm$ 0.003$_{\text{stat}}$ $\pm$ 0.019$_{\text{sys}}$ 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.
Comments40 pages, 11 figures, published online in The Innovation
DOI：10.1016/j.xinn.2026.101535
