{"ID":2833001,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.04803","arxiv_id":"2512.04803","title":"287,872 Supermassive Black Holes Masses: Deep Learning Approaching Reverberation Mapping Accuracy","abstract":"We present a population-scale catalogue of 287,872 supermassive black hole masses with high accuracy. Using a deep encoder-decoder network trained on optical spectra with reverberation-mapping (RM) based labels of 849 quasars and applied to all SDSS quasars up to $z=4$, our method achieves a root-mean-square error of $0.058$\\,dex, a relative uncertainty of $\\approx 14\\%$, and coefficient of determination $R^{2}\\approx0.91$ with respect to RM-based masses, far surpassing traditional single-line virial estimators. Notably, the high accuracy is maintained for both low ($\u003c10^{7.5}\\,M_\\odot$) and high ($\u003e10^{9}\\,M_\\odot$) mass quasars, where empirical relations are unreliable.","short_abstract":"We present a population-scale catalogue of 287,872 supermassive black hole masses with high accuracy. Using a deep encoder-decoder network trained on optical spectra with reverberation-mapping (RM) based labels of 849 quasars and applied to all SDSS quasars up to $z=4$, our method achieves a root-mean-square error of $...","url_abs":"https://arxiv.org/abs/2512.04803","url_pdf":"https://arxiv.org/pdf/2512.04803v1","authors":"[\"Yuhao Lu\",\"HengJian SiTu\",\"Jie Li\",\"Yixuan Li\",\"Yang Liu\",\"Wenbin Lin\",\"Yu Wang\"]","published":"2025-12-04T13:55:04Z","proceeding":"astro-ph.GA","tasks":"[\"astro-ph.GA\",\"astro-ph.HE\",\"astro-ph.IM\",\"cs.AI\"]","methods":"[]","has_code":false}