Template-Fitting Meets Deep Learning: Redshift Estimation Using Physics-Guided Neural Networks

TL;DR

This paper introduces a physics-guided neural network that combines template fitting and deep learning for accurate photometric redshift estimation, leveraging spectral templates and multimodal data fusion.

Contribution

The work presents a novel hybrid model embedding spectral templates into neural networks, improving redshift estimation accuracy and uncertainty quantification in large-scale surveys.

Findings

Achieved RMS error of 0.0507 on the PREML dataset.

Reduced catastrophic outlier rate to 0.13%.

Met two of three LSST redshift accuracy requirements for z<3.

Abstract

Accurate photometric redshift estimation is critical for observational cosmology, especially in large-scale surveys where spectroscopic measurements are impractical. Traditional approaches include template fitting and machine learning, each with distinct strengths and limitations. We present a hybrid method that integrates template fitting with deep learning using physics-guided neural networks. By embedding spectral energy distribution templates into the network architecture, our model encodes physical priors into the training process. The system employs a multimodal design, incorporating cross-attention mechanisms to fuse photometric and image data, along with Bayesian layers for uncertainty estimation. We evaluate our model on the publicly available PREML dataset, which includes approximately 400,000 galaxies from the Hyper Suprime-Cam PDR3 release, with 5-band photometry, multi-band imaging, and spectroscopic redshifts. Our approach achieves an RMS error of 0.0507, a 3-sigma catastrophic outlier rate of 0.13%, and a bias of 0.0028. The model satisfies two of the three LSST photometric redshift requirements for redshifts below 3. These results highlight the potential of combining physically motivated templates with data-driven models for robust redshift estimation in upcoming cosmological surveys.