Automated quasar continuum estimation using neural networks

A comparative study of deep-learning architectures

¹ Dipartimento di Fisica ‘G. Occhialini’, Università degli Studi di Milano-Bicocca, Piazza della Scienza 3, 20126 Milano, Italy
² National Centre for Nuclear Research, ul. Pasteura 7, 02-093 Warsaw, Poland
³ INAF – Osservatorio di Astrofisica e Scienza dello Spazio di Bologna, Via Piero Gobetti 93/3, 40129 Bologna, Italy
⁴ INAF – Osservatorio Astronomico di Trieste, via G.B. Tiepolo 11, 34143 Trieste, Italy
⁵ INAF – Osservatorio Astronomico di Brera, Via Brera 28, 20122 Milano, via E. Bianchi 46, 23807 Merate, Italy
⁶ NRC Herzberg Astronomy and Astrophysics Research Centre, 5071 West Saanich Road, Victoria, B.C. V9E 2E7, Canada
⁷ Department of Physics and Astronomy Camosun College, 3100 Foul Bay Rd, Victoria, B.C. V8P 5J2, Canada
⁸ Aix Marseille Univ. CNRS, CNES, LAM, Marseille, France
⁹ IUCAA, Postbag 4, Ganeshkind, Pune 411007, India
¹⁰ Department of Astronomy, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
¹¹ Institute of Astronomy, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK
¹² Instituto de Astrofisica, Facultad de Fisica, Pontificia Universidad Catolica de Chile, Santiago, Chile
¹³ Departament de Fisica, EEBE, Universitat Politécnica de Catalunya, c/Eduard Maristany 10, 08930 Barcelona, Spain
¹⁴ Astronomical Observatory of the Jagiellonian University, Orla 171, 30-001 Cracow, Poland

^★ Corresponding author: francesco.pistis@unimib.it

Received: 10 December 2024
Accepted: 16 May 2025

Abstract

Context. Ongoing and upcoming large spectroscopic surveys are drastically increasing the number of observed quasar spectra, making the development of fast and accurate automated methods to estimate spectral continua necessary.

Aims. This study evaluates the performance of three neural networks (NNs) – an autoencoder, a convolutional NN (CNN), and a U-Net – in predicting quasar continua within the rest frame wavelength range of 1020 Å to 2000 Å. The ability to generalize and predict galaxy continua within the range of 3500 Å to 5500 Å is also tested.

Methods. We evaluated the performance of these architectures using the absolute fractional flux error (AFFE) on a library of mock quasar spectra for the WEAVE survey and on real data from the early data release observations of the Dark Energy Spectroscopic Instrument (DESI) and the VIMOS Public Extragalactic Redshift Survey (VIPERS).

Results. The autoencoder outperforms U-Net, achieving a median AFFE of 0.009 for quasars. The best model also effectively recovers the Lyα optical depth evolution in the DESI quasar spectra. With minimal optimization, the same architectures can be generalized to the galaxy case, with the autoencoder reaching a median AFFE of 0.014 and reproducing the D4000n break in DESI and VIPERS galaxies.