16 new quasars at the end of the reionization unveiled by self-supervised learning

¹ Max Planck Institut für Astronomie, Königstuhl 17, D-69117 Heidelberg, Germany
² Instituto de Astrofísica, Facultad de Física, Pontificia Universidad Católica de Chile, Av. Vicuña Mackenna 4860, 7820436 Macul, Santiago, Chile
³ Fakultät für Physik und Astronomie, Universität Heidelberg Im Neuenheimer Feld 226, 69115 Heidelberg, Germany
⁴ Millennium Institute of Astrophysics (MAS), Nuncio Monseñor Sótero Sanz 100 Providencia, Santiago, Chile
⁵ INAF – Osservatorio di Astrofisica e Scienza dello Spazio, Via Gobetti 93/3, I-40129 Bologna, Italy
⁶ Instituto de Alta Investigación, Universidad de Tarapacá, Casilla 7D, Arica, Chile
⁷ Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, Pasadena, CA 91109, USA
⁸ Instituto de Estudios Astrofísicos, Facultad de Ingeniería y Ciencias, Universidad Diego Portales, Avenida Ejercito Libertador 441, Santiago, Chile
⁹ Department of Astronomy, University of Geneva, Chemin Pegasi 51, 1290 Versoix, Switzerland

^★ Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Received: 29 August 2025
Accepted: 23 February 2026

Abstract

Luminous quasars at z > 6 are key probes of early supermassive black hole (SMBH) growth, massive galaxy evolution, and intergalactic medium properties during cosmic reionization. However, their discovery is very challenging due to their scarcity and overwhelming contamination. Foreground ultracool dwarfs (UCDs) outnumber z > 6 quasars by 2–4 orders of magnitude. In this work, we leveraged the extensive coverage of DESI Legacy Survey DR10 to conduct a self-supervised search for quasars at z > 6, directly analyzing multiband optical images and minimizing the biases of the traditional catalog-driven color-color selection criteria. By applying a contrastive learning (CL) method followed by spectral energy distribution (SED) fitting prioritization, we identified 1139 high-priority quasar candidates, for which we expect a competitive 1:1 quasar-to-UCD ratio based on the literature samples. We spectroscopically confirm 16 new quasars at z = 5.94 − 6.45, achieving a 45% success rate. Remarkably, all 16 objects are relatively bright (M₁₄₅₀ < −25.5) quasars, including several with unusual properties such as narrow Ly[[INLINE10]] emission (FWHM ≲ 2600 km s⁻¹), strong Ly[[INLINE13]]+N V emission with an equivalent width > 100 Å, and a mild observed-frame red near-infrared (NIR) continua (z − J > 0.4). Notably, three of them would have been missed by traditional color–color selections. These results highlight the power of self-supervised machine learning, combined with SED fitting prioritization, to uncover rare, distant sources beyond the limitations of conventional techniques. Our approach offers a scalable and robust framework for data mining and can be readily extended to forthcoming wide-field surveys such as Rubin/LSST, 4MOST, Euclid, and Roman. These applications will advance the census of high-redshift quasars, potentially extend the redshift frontier, and improve constraints on SMBH formation and evolution in the first billion years of the Universe.