DeepDISC-Euclid: Source Classification and Photometric Redshifts in Euclid Deep Field North With a Pixel-Level Deep Learning Approach

TL;DR

This paper introduces DeepDISC, a deep learning framework for source classification and photometric redshift estimation in the Euclid Deep Field North, demonstrating high accuracy and releasing a large catalog of objects.

Contribution

The work presents a novel pixel-level deep learning approach for simultaneous source detection, classification, and photo-z estimation in Euclid data, outperforming previous methods.

Findings

DeepDISC achieves ~93% completeness and ~80% purity in source detection.

Correctly recovers over 99% of stars, galaxies, and quasars with spectroscopic classifications.

Provides comparable or improved photo-z accuracy for quasars and galaxies.

Abstract

The first Euclid Quick Data Release (Q1) provides extensive imaging and spectroscopic data for hundreds of millions of photometric objects across several deep fields. Accurate classifications and photometric redshifts (photo-z) for these sources are crucial to maximizing the value of these data. In this work, we perform source classification and photo-z estimation for the Euclid Deep Field North (EDF-N) around the North Ecliptic Pole, using a deep learning framework (DeepDISC) that learns and infers using 9-band images simultaneously. We train three dedicated models for (1) source detection and classification, (2) galaxy photo-z, and (3) quasar photo-z. The Euclid Q1 input source catalog, and classifications and spectroscopic redshifts (spec-z) from the Dark Energy Spectroscopic Instrument Data Release 1 are adopted as our training data. DeepDISC source detection achieves overall completeness of ~93% and purity of ~80% if using the Euclid source catalog as the ground truth. Using a JWST source catalog within EDF-N as the reference, we estimate a true purity of ~ 90% for DeepDISC sources. About 99.2%, 99.0%, and 84.8% of stars, galaxies, and quasars, respectively, are correctly recovered with their spectroscopic classifications. The DeepDISC photo-zs show good agreement with spectroscopic redshifts, for both galaxies and quasars. Comparisons with other Euclid Q1 products demonstrate that DeepDISC provides comparable or improved performance in source detection/deblending, classification and photo-z, especially for quasars. These results demonstrate the potential of pixel-level deep learning approaches for large-scale sky surveys such as Euclid and Roman, which will continue to improve with better training labels. We release the full DeepDISC source catalog (~13 million objects) for EDF-N with classifications and photo-zs, including photo-z probability distributions.