287,872 Supermassive Black Holes Masses: Deep Learning Approaching Reverberation Mapping Accuracy

• URL: http://arxiv.org/abs/2512.04803v1
• Date: Thu, 04 Dec 2025 13:55:04 GMT
• Title: 287,872 Supermassive Black Holes Masses: Deep Learning Approaching Reverberation Mapping Accuracy
• Authors: Yuhao Lu, HengJian SiTu, Jie Li, Yixuan Li, Yang Liu, Wenbin Lin, Yu Wang,
• Abstract summary: We present a population-scale catalogue of 287,872 supermassive black hole masses with high accuracy.<n>Using a deep encoder-decoder network trained on optical spectra with reverberation-mapping (RM) based labels of 849 quasars, our method achieves a root-mean-square error of $0.058$,dex.<n> Notably, the high accuracy is maintained for both low ($107.5,M_odot$) and high ($>109,M_odot$) mass quasars, where empirical relations are unreliable.
• Score: 23.192042019520255
• License: http://creativecommons.org/licenses/by/4.0/
• 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 ($<10^{7.5}\,M_\odot$) and high ($>10^{9}\,M_\odot$) mass quasars, where empirical relations are unreliable.

Related papers

• A Probabilistic Inference Scaling Theory for LLM Self-Correction [49.42817548142699]
  Large Language Models (LLMs) have demonstrated the capability to refine their generated answers through self-correction.<n>We propose a probabilistic theory to model the dynamics of accuracy change and explain the performance improvements observed in multi-round self-correction.
  arXiv  Detail & Related papers  (2025-08-22T15:15:38Z)
• Towards the "puzzle" of Chromium dimer Cr$_2$: predicting the Born-Oppenheimer rovibrational spectrum [44.99833362998488]
  This paper calculates the potential energy curve for the state $X1Sigma+$ of the Cr$$$ dimer. It is found for the first time for the whole range of internuclear distances $R$.
  arXiv  Detail & Related papers  (2024-01-06T17:00:12Z)
• Bayesian deep learning for cosmic volumes with modified gravity [0.0]
  This study aims at extracting cosmological parameters from modified gravity (MG) simulations through deep neural networks endowed with uncertainty estimations. We train both BNNs with real-space density fields and power-spectra from a suite of 2000 dark matter only particle mesh $N$-body simulations. BNNs excel in accurately predicting parameters for $Omega_m$ and $sigma_8$ and their respective correlation with the MG parameter.
  arXiv  Detail & Related papers  (2023-09-01T17:59:06Z)
• Average-case Speedup for Product Formulas [69.68937033275746]
  Product formulas, or Trotterization, are the oldest and still remain an appealing method to simulate quantum systems. We prove that the Trotter error exhibits a qualitatively better scaling for the vast majority of input states. Our results open doors to the study of quantum algorithms in the average case.
  arXiv  Detail & Related papers  (2021-11-09T18:49:48Z)
• AGNet: Weighing Black Holes with Deep Learning [2.4522011090845846]
  Supermassive black holes (SMBHs) are ubiquitously found at the centers of most massive galaxies. Traditional methods require spectroscopic data which is expensive to gather. We present an algorithm that weighs SMBHs using quasar light time series.
  arXiv  Detail & Related papers  (2021-08-17T16:45:11Z)
• Low overhead fault-tolerant quantum error correction with the surface-GKP code [60.44022726730614]
  We propose a highly effective use of the surface-GKP code, i.e., the surface code consisting of bosonic GKP qubits instead of bare two-dimensional qubits. We show that a low logical failure rate $p_L 10-7$ can be achieved with moderate hardware requirements.
  arXiv  Detail & Related papers  (2021-03-11T23:07:52Z)
• A New Framework for Variance-Reduced Hamiltonian Monte Carlo [88.84622104944503]
  We propose a new framework of variance-reduced Hamiltonian Monte Carlo (HMC) methods for sampling from an $L$-smooth and $m$-strongly log-concave distribution. We show that the unbiased gradient estimators, including SAGA and SVRG, based HMC methods achieve highest gradient efficiency with small batch size. Experimental results on both synthetic and real-world benchmark data show that our new framework significantly outperforms the full gradient and gradient HMC approaches.
  arXiv  Detail & Related papers  (2021-02-09T02:44:24Z)
• AGNet: Weighing Black Holes with Machine Learning [2.598391092244943]
  Supermassive black holes (SMBHs) are ubiquitously found at the centers of most galaxies. Traditional methods require spectral data which is expensive to gather. We present an algorithm that weighs SMBHs using quasar light time series.
  arXiv  Detail & Related papers  (2020-11-30T18:30:24Z)
• Accuracy and precision of the estimation of the number of missing levels in chaotic spectra using long-range correlations [0.0]
  We study the accuracy and precision for estimating the fraction of observed levels $varphi$ in quantum chaotic spectra through long-range correlations. We use Monte Carlo simulations of the spectra from the diagonalization of Gaussian Orthogonal Ensemble matrices with a definite number of levels randomly taken out to fit the formulas. The precision is generally better for the estimation using the power spectrum of the $delta_n$ as compared to the estimation using the $Delta_3$ statistic.
  arXiv  Detail & Related papers  (2020-11-03T12:42:07Z)
• Benchmarking a high-fidelity mixed-species entangling gate [0.0]
  We implement a two-qubit logic gate between a $43mathrmCa+,$ hyperfine qubit and a $88mathrmSr+,$ Zeeman qubit. For this pair of ion species, the S--P optical transitions are close enough that a single laser wavelength of $402,mathrmnm$ can be used to drive the gate.
  arXiv  Detail & Related papers  (2020-04-17T10:41:00Z)
• Kernel-Based Reinforcement Learning: A Finite-Time Analysis [53.47210316424326]
  We introduce Kernel-UCBVI, a model-based optimistic algorithm that leverages the smoothness of the MDP and a non-parametric kernel estimator of the rewards. We empirically validate our approach in continuous MDPs with sparse rewards.
  arXiv  Detail & Related papers  (2020-04-12T12:23:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.