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

arXiv: https://arxiv.org/abs/2512.04803 · HTML: https://mlsanity.com/paper/2512.04803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 43 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 1 of 1)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)

## Abstract (arXiv)

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 ≈ 14%, and coefficient of determination R2≈0.91 with respect to RM-based masses, far surpassing traditional single-line virial estimators. 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.