A robust morphological classification method for galaxies using dual-encoding contrastive learning and multi-clustering voting on JWST/NIRCam images

¹ School of Mathematics and Physics, Anqing Normal University, Anqing 246133, China
² Institute of Astronomy and Astrophysics, Anqing Normal University, Anqing 246133, China
³ Key Laboratory of Modern Astronomy and Astrophysics (Nanjing University), Ministry of Education, Nanjing 210093, China
⁴ Department of Physics, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong S.A.R., China
⁵ Shanghai Astronomical Observatory, Chinese Academy of Sciences, 80 Nandan Road, Shanghai 200030, China
⁶ School of Astronomy and Space Science, University of Chinese Academy of Sciences, No. 19A Yuquan Road, Beijing 100049, China
⁷ School of Engineering, Dali University, Dali 671003, China

^⋆ Corresponding author: wen@mail.ustc.edu.cn

Received: 20 May 2025
Accepted: 25 August 2025

Abstract

The two-step galaxy morphology classification framework USmorph successfully combines unsupervised machine learning (UML) with supervised machine learning (SML) methods. To enhance the UML step, we employed a dual-encoder architecture (ConvNeXt and ViT) to effectively encode images, contrastive learning to accurately extract features, and principal component analysis to efficiently reduce dimensionality. Based on this improved framework, a sample of 46 176 galaxies at 0 < z < 4.2, selected in the COSMOS-Web field, is classified into five types using the JWST near-infrared images: 33% spherical (SPH), 25% early-type disk (ETD), 25% late-type disk (LTD), 7% irregular (IRR), and 10% unclassified (UNC) galaxies. We also performed parametric (Sérsic index, n, and effective radius, r_e) and nonparametric measurements (Gini coefficient, G, the second-order moment of light, M₂₀, concentration, C, multiplicity, Ψ, and three other parameters from the MID statistics) for massive galaxies (M_* > 10⁹ M_⊙) to verify the validity of our galaxy morphological classification system. The analysis of morphological parameters is consistent with our classification system: SPH and ETD galaxies with higher n, G, and C tend to be more bulge-dominated and more compact compared with other types of galaxies. This demonstrates the reliability of this classification system, which will be useful for a forthcoming large-sky survey from the Chinese Space Station Telescope.