DeepRed: an architecture for redshift estimation

2026-02-11

AI Summary

This work addresses the high cost of spectroscopic redshift estimation and the limited generalization of existing image-based methods by proposing DeepRed, an end-to-end deep learning pipeline that directly predicts redshifts from astronomical images. DeepRed systematically evaluates and integrates state-of-the-art vision architectures—including ResNet, EfficientNet, Swin Transformer, and MLP-Mixer—and demonstrates robust cross-domain generalization across diverse celestial objects (e.g., galaxies, gravitational lenses, and lensed supernovae) and observational conditions. Evaluated on multiple datasets including DeepGraviLens, KiDS, and SDSS, the method achieves state-of-the-art performance, improving the NMAD metric by up to 55%. Furthermore, SHAP-based interpretability analysis confirms that the model’s attention accurately focuses on target regions with over 95% precision.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Estimating redshift is a central task in astrophysics, but its measurement is costly and time-consuming. In addition, current image-based methods are often validated on homogeneous datasets. The development and comparison of networks able generalize across different morphologies, ranging from galaxies to gravitationally-lensed transients, and observational conditions, remain an open challenge. This work proposes DeepRed, a deep learning pipeline that demonstrates how modern computer vision architectures, including ResNet, EfficientNet, Swin Transformer, and MLP-Mixer, can estimate redshifts from images of galaxies, gravitational lenses, and gravitationally-lensed supernovae. We compare these architectures and their ensemble to both neural networks (A1, A3, NetZ, and PhotoZ) and a feature-based method (HOG+SVR) on simulated (DeepGraviLens) and real (KiDS, SDSS) datasets. Our approach achieves state-of-the-art results on all datasets. On DeepGraviLens, DeepRed achieves a significant improvement in the Normalized Mean Absolute Deviation compared to the best baseline (PhotoZ): 55% on DES-deep (using EfficientNet), 51% on DES-wide (Ensemble), 52% on DESI-DOT (Ensemble), and 46% on LSST-wide (Ensemble). On real observations from the KiDS survey, the pipeline outperforms the best baseline (NetZ), improving NMAD by 16% on a general test set without high-probability lenses (Ensemble) and 27% on high-probability lenses (Ensemble). For non-lensed galaxies in the SDSS dataset, the MLP-Mixer architecture achieves a 5% improvement over the best baselines (A3 and NetZ). SHAP shows that the models correctly focus on the objects of interest with over 95% localization accuracy on high-quality images, validating the reliability of the predictions. These findings suggest that deep learning is a scalable, robust, and interpretable solution for redshift estimation in large-scale surveys.

Problem

• redshift estimation
• generalization
• gravitational lensing
• deep learning
• astronomical surveys

Innovation

• redshift estimation
• deep learning
• computer vision architectures
• ensemble learning
• interpretable AI