VAR-PZnn: A machine-learning framework for AGN photometric redshifts using color and variability-based features
S. Satheesh-Sheeba, P. Sánchez-Sáez, R. J. Assef, T. Anguita, R. Shirley, M. Salvato, P. Arévalo, T T. Ananna, F. E. Bauer, C. G. Bornancini, W. N. Brandt, D. De Cicco, M. Espinoza-Ortiz, J. Fagin, M. Fatović, A. W. Graham, H. Guo, L. Hernandez-García, D. Ilić, A. B. Kovačević, P. Lira, A. I. Malz, M. Marculewicz, D. Marsango, C. Mazzucchelli, T. Mkrtchyan, S. Panda, A. Peca, V. Petrecca, B. Rani, C. Ricci, G. T. Richards, R. A. Riffel, A. Rojas-Lilayú, E. Saremi, D. P. Schneider, B. Sotomayor, M. J. Temple, A. Viitanen, I. Yoon, Z. Yu, F. Zou
astro-ph.GA
Submitted: 2026-07-17
Comments: 18 pages, 12 figures, 4 tables, Submitted to Astronomy & Astrophysics Journal
License: http://creativecommons.org/licenses/by/4.0/
The gist: Photometric redshift estimation for active galactic nuclei (AGNs) remains a fundamental challenge for current and upcoming large-scale photometric surveys.
Terminology
Abstract
Photometric redshift estimation for active galactic nuclei (AGNs) remains a fundamental challenge for current and upcoming large-scale photometric surveys. Traditional spectral energy distribution (SED) fitting suffers from color-redshift degeneracies, particularly for AGNs whose power-law continua hide the strong spectral features required to anchor redshift estimates. While AGN variability provides additional constraining power, existing frameworks require multi-band light curves that are not always available. This work presents VAR-PZnn, a fully connected mixture density network that integrates 26 variability features extracted from ZTF g-band light curves with optical photometry from Pan-STARRS1, mid-infrared (MIR) photometry from CatWISE, and, for a subsample, NIR photometry from UKIDSS. The model is trained and tested on 72,728 spectroscopically confirmed AGNs/QSOs spanning 0.01 < z < 4.5 and g-band magnitudes from 17 to 21.5. For the main sample, we achieve sigma NMAD = 0.058 and an outlier fraction of eta = 8.2%, which reduces to 5.4% when the 10% of sources with the highest predicted uncertainty are excluded. An ablation study demonstrates that MIR photometry provides the dominant constraint for photo-z accuracy, while variability features serve as a secondary refiner. Using UKIDSS NIR data as a proxy for future synergies between LSST and space-based missions like Euclid and Roman, we obtain eta = 13.3% without MIR data and eta = 4.6% when MIR is available. We benchmark against Low-Resolution Templates (LRT) SED fitting (eta = 28.7%) and the VAR-PZ framework; applying single-band VAR-PZ priors worsens LRT performance to eta = 39.4% due to single-band light-curve degeneracies, confirmed via simulations (eta = 27.6% to 28.1%). This framework provides a scalable approach for the Legacy Survey of Space and Time (LSST).
Sources
- The Pan-STARRS1 Surveys
- The DESI Experiment Part I: Science,Targeting, and Survey Design
- Data Release 1 of the Dark Energy Spectroscopic Instrument
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- Adam: A Method for Stochastic Optimization
- Predicting Quasar Counts Detectable in the LSST Survey
- The Nineteenth Data Release of the Sloan Digital Sky Survey
Related papers
- Apparent Stability in Self-Gravitating Turbulence and the Evolution of Molecular Clouds
- Two sets of potential-density basis pairs for the study of radial perturbations in collisionless spherical stellar systems
- Constraining reionization-era Ly alpha escape with JELS-MUSE: a highly complete H alpha-selected sample at z about6.1
- Deriving volume density profiles of filaments from observed surface densities
- Little Red Dots and Supermassive Black Hole Seed Formation in Ultralight Dark Matter Halos
- MEGATRON: how the first stars can create an iron metallicity plateau in the smallest dwarf galaxies