Galaxy Spectra Networks (GaSNet). III. Generative pre-trained network for spectrum reconstruction, redshift estimate and anomaly detection

TL;DR

This paper introduces GaSNet-III, a generative neural network framework that simultaneously performs spectrum reconstruction, redshift estimation, and anomaly detection with high accuracy and efficiency for large-scale spectroscopic surveys.

Contribution

The paper presents a novel integrated neural network model using autoencoder-like and U-Net architectures for spectrum analysis, improving efficiency and accuracy over classical methods.

Findings

Achieves over 98% classification accuracy across all spectral classes.

Redshift estimation accuracy exceeds 99% for stars and 98% for galaxies.

Effectively detects anomalous spectra through chi-squared robustness analysis.

Abstract

Classification of spectra (1) and anomaly detection (2) are fundamental steps to guarantee the highest accuracy in redshift measurements (3) in modern all-sky spectroscopic surveys. We introduce a new Galaxy Spectra Neural Network (GaSNet-III) model that takes advantage of generative neural networks to perform these three tasks at once with very high efficiency. We use two different generative networks, an autoencoder-like network and U-Net, to reconstruct the rest-frame spectrum (after redshifting). The autoencoder-like network operates similarly to the classical PCA, learning templates (eigenspectra) from the training set and returning modeling parameters. The U-Net, in contrast, functions as an end-to-end model and shows an advantage in noise reduction. By reconstructing spectra, we can achieve classification, redshift estimation, and anomaly detection in the same framework. Each rest-frame reconstructed spectrum is extended to the UV and a small part of the infrared (covering the blueshift of stars). Owing to the high computational efficiency of deep learning, we scan the chi-squared value for the entire type and redshift space and find the best-fitting point. Our results show that generative networks can achieve accuracy comparable to the classical PCA methods in spectral modeling with higher efficiency, especially achieving an average of $>98\%$ classification across all classes ($>99.9\%$ for star), and $>99\%$ (stars), $>98\%$ (galaxies) and $>93\%$ (quasars) redshift accuracy under cosmology research requirements. By comparing different peaks of chi-squared curves, we define the ``robustness'' in the scanned space, offering a method to identify potential ``anomalous'' spectra. Our approach provides an accurate and high-efficiency spectrum modeling tool for handling the vast data volumes from future spectroscopic sky surveys.