Morpho-Photometric Classification of KiDS DR5 Sources Based on Neural Networks: A Comprehensive Star-Quasar-Galaxy Catalog

TL;DR

This paper introduces a multimodal neural network that combines morphological and spectral data to classify stars, galaxies, and quasars in the KiDS DR5 survey with high accuracy, enabling efficient large-scale astronomical source categorization.

Contribution

The paper presents a novel neural network architecture that integrates morphological and spectral features for improved astronomical source classification, validated on multiple datasets.

Findings

Achieved 98.76% accuracy on test data.

Correctly classified over 99% of external star and galaxy samples.

Generated a comprehensive classification catalog for over 27 million sources.

Abstract

We present a novel multimodal neural network (MNN) for classifying astronomical sources in multiband ground-based observations, from optical to near infrared, to separate sources in stars, galaxies and quasars. Our approach combines a convolutional neural network branch for learning morphological features from $r$-band images with an artificial neural network branch for extracting spectral energy distribution (SED) information. Specifically, we have used 9-band optical ($ugri$) and NIR ($ZYHJK_s$) data from the Kilo-Degree Survey (KiDS) Data Release 5. The two branches of the network are concatenated and feed into fully-connected layers for final classification. We train the network on a spectroscopically confirmed sample from the Sloan Digital Sky Survey cross-matched with KiDS. The trained model achieves 98.76\% overall accuracy on an independent testing dataset, with F1 scores exceeding 95\% for each class. Raising the output probability threshold, we obtain higher purity at the cost of a lower completeness. We have also validated the network using external catalogs cross-matched with KiDS, correctly classifying 99.74\% of a pure star sample selected from Gaia parallaxes and proper motions, and 99.74\% of an external galaxy sample from the Galaxy and Mass Assembly survey, adjusted for low-redshift contamination. We apply the trained network to 27,335,836 KiDS DR5 sources with $r \leqslant 23$ mag to generate a new classification catalog. This MNN successfully leverages both morphological and SED information to enable efficient and robust classification of stars, quasars, and galaxies in large photometric surveys.