UnEZ: A Fully Unsupervised Self-Templating Neural Network for Redshift and Line Strength Estimation
Abstract
As spectroscopic surveys grow, estimating galaxy properties such as metallicity, star formation rate, and redshift becomes computationally cumbersome. Methods of estimating such properties rely on template spectra or curated redshift catalogs, which fail to represent the diversity of objects seen in large-scale surveys. We present UnEZ, a fully unsupervised, physics-informed machine learning model that can predict spectroscopic redshifts and line strengths with no prior redshift or line strength labels. An encoder predicts emission and absorption line amplitudes/widths, and a fixed deterministic decoder constructs a unique template, estimated redshift, redshift confidence curve, and spectral model. UnEZ was tested on the Sloan Digital Sky Survey (SDSS) Data Release 18 due to its large dataset and thoroughly vetted redshift catalog which serves as an independent benchmark. Despite the lack of templates, line strength labels, or redshift labels, UnEZ's performance competes with modern redshift estimation algorithms. At SNR > 10, UnEZ achieves an outlier fraction of 0.459% and a normalized median absolute deviation (NMAD) of 1.237 × 10−4. At SNR > 3, UnEZ achieves an outlier fraction of 3.89% and an NMAD of 1.471 × 10−4. Furthermore, we demonstrate how UnEZ's line strength and redshift predictions can be utilized for various purposes such as constructing template spectra required in traditional redshift estimation algorithms. UnEZ illustrates how a fully unsupervised neural network can allow redshift, among other galaxy properties, to emerge naturally from the spectra themselves, providing a template-free, label-free approach that scales to the demands of future surveys.
Related
- Photometric Redshift Estimation with Hybrid Quantum Neural Network
- Probabilistic redshift estimation of undetected galaxies from multi-band background light maps
- Combining Rubin and Roman photometry and its implications for photometric redshift estimation
- Estimation of the magnetic field strength from ALMA dust polarization in the protocluster G327.29
- Bayesian nonparametric estimation of correlated gravitational wave detector network noise using matrix-gamma process priors
BibTeX
@misc{abd2026unez,
title = {{UnEZ: A Fully Unsupervised Self-Templating Neural Network for Redshift and Line Strength Estimation}},
author = {Asha Abd and Karl Glazebrook and Colin Jacobs},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.38816},
eprint = {2610.38816},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.38816},
}
RIS
TY - UNPB
TI - UnEZ: A Fully Unsupervised Self-Templating Neural Network for Redshift and Line Strength Estimation
AU - Asha Abd
AU - Karl Glazebrook
AU - Colin Jacobs
PY - 2026
DA - 2026/10/28
PB - arXiv
DO - 10.48550/arxiv.2610.38816
UR - https://arxiv.org/abs/2610.38816
AB - As spectroscopic surveys grow, estimating galaxy properties such as metallicity, star formation rate, and redshift becomes computationally cumbersome. Methods of estimating such properties rely on template spectra or curated redshift catalogs, which fail to represent the diversity of objects seen in large-scale surveys. We present UnEZ, a fully unsupervised, physics-informed machine learning model that can predict spectroscopic redshifts and line strengths with no prior redshift or line strength labels. An encoder predicts emission and absorption line amplitudes/widths, and a fixed deterministic decoder constructs a unique template, estimated redshift, redshift confidence curve, and spectral model. UnEZ was tested on the Sloan Digital Sky Survey (SDSS) Data Release 18 due to its large dataset and thoroughly vetted redshift catalog which serves as an independent benchmark. Despite the lack of templates, line strength labels, or redshift labels, UnEZ's performance competes with modern redshift estimation algorithms. At SNR > 10, UnEZ achieves an outlier fraction of 0.459% and a normalized median absolute deviation (NMAD) of 1.237 × 10^−4. At SNR > 3, UnEZ achieves an outlier fraction of 3.89% and an NMAD of 1.471 × 10^−4. Furthermore, we demonstrate how UnEZ's line strength and redshift predictions can be utilized for various purposes such as constructing template spectra required in traditional redshift estimation algorithms. UnEZ illustrates how a fully unsupervised neural network can allow redshift, among other galaxy properties, to emerge naturally from the spectra themselves, providing a template-free, label-free approach that scales to the demands of future surveys.
ER -