PICZL: Image-based photometric redshifts for AGN

¹ Max-Planck-Institut für extraterrestrische Physik, Giessenbachstr. 1, 85748 Garching, Germany
² Exzellenzcluster ORIGINS, Boltzmannstr. 2, 85748 Garching, Germany
³ LMU Munich, Arnold Sommerfeld Center for Theoretical Physics, Theresienstr. 37 80333 München, Germany
⁴ LMU Munich, Universitäts-Sternwarte, Scheinerstr. 1, 81679 München, Germany
⁵ Technical University of Munich Department of Computer Science - I26 Boltzmannstr. 3 85748 Garching b. München, Germany
⁶ Max Planck Institut für Astronomie, Königstuhl 17, 69117 Heidelberg, Germany
⁷ Instituto de Astrofísica, Facultad de Física, Pontificia Universidad Católica de Chile, Campus San Joaquín, Av. Vicuña Mackenna 4860, Macul Santiago 7820436, Chile
⁸ Centro de Astroingeniería, Facultad de Física, Pontificia Universidad Católica de Chile, Campus San Joaquín, Av. Vicuña Mackenna 4860, Macul Santiago 7820436, Chile
⁹ Millennium Institute of Astrophysics, Nuncio Monseñor Sótero Sanz 100, Of 104, Providencia, Santiago, Chile
¹⁰ Space Science Institute, 4750 Walnut Street, Suite 205, Boulder, Colorado 80301, USA
¹¹ Institute for Astronomy, University of Edinburgh, Royal Observatory, Edinburgh EH9 3HJ, UK
¹² Instituto de Estudios Astrofísicos, Universidad Diego Portales, Av. Ejército Libertador 441, Santiago 8370191, Chile
¹³ Kavli Institute for Astronomy and Astrophysics, Peking University, Beijing 100871, China
¹⁴ Department of Astronomy, University of Washington, Box 351580, Seattle, WA, 98195, USA
¹⁵ Department of Astronomy, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
¹⁶ National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
¹⁷ Center for Artificial Intelligence Innovation, University of Illinois at Urbana-Champaign, 1205 West Clark Street, Urbana, IL 61801, USA

^★ Corresponding author; wroster@mpe.mpg.de

Received: 24 September 2024
Accepted: 7 November 2024

Abstract

Context. Computing reliable photometric redshifts (photo-z) for active galactic nuclei (AGN) is a challenging task, primarily due to the complex interplay between the unresolved relative emissions associated with the supermassive black hole and its host galaxy. Spectral energy distribution (SED) fitting methods, while effective for galaxies and AGN in pencil-beam surveys, face limitations in wide or all-sky surveys with fewer bands available, lacking the ability to accurately capture the AGN contribution to the SED, hindering reliable redshift estimation. This limitation is affecting the many tens of millions of AGN detected in existing datasets, such as those AGN clearly singled out and identified by SRG/eROSITA.

Aims. Our goal is to enhance photometric redshift performance for AGN in all-sky surveys while simultaneously simplifying the approach by avoiding the need to merge multiple data sets. Instead, we employ readily available data products from the 10th Data Release of the Imaging Legacy Survey for the Dark Energy Spectroscopic Instrument, which covers >20 000 deg² of extragalactic sky with deep imaging and catalog-based photometry in the ɡriɀW1-W4 bands. We fully utilize the spatial flux distribution in the vicinity of each source to produce reliable photo-z.

Methods. We introduce PICZL, a machine-learning algorithm leveraging an ensemble of convolutional neural networks. Utilizing a cross-channel approach, the algorithm integrates distinct SED features from images with those obtained from catalog-level data. Full probability distributions are achieved via the integration of Gaussian mixture models.

Results. On a validation sample of 8098 AGN, PICZL achieves an accuracy σ_NMAD of 4.5% with an outlier fraction η of 5.6%. These results significantly outperform previous attempts to compute accurate photo-z for AGN using machine learning. We highlight that the model’s performance depends on many variables, predominantly the depth of the data and associated photometric error. A thorough evaluation of these dependencies is presented in the paper.

Conclusions. Our streamlined methodology maintains consistent performance across the entire survey area, when accounting for differing data quality. The same approach can be adopted for future deep photometric surveys such as LSST and Euclid, showcasing its potential for wide-scale realization. With this paper, we release updated photo-z (including errors) for the XMM-SERVS W-CDF-S, ELAIS-S1 and LSS fields.