Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 6 min ago
Peer-reviewedCC BY 4.0Monthly Notices of the Royal Astronomical Society

An Efficient Galaxy Morphology Classification Framework updated with Two-Stage Feature Extraction with AlexNet Encoding and UMAP

  • Mengjiao Xie1,2
  • Guanwen Fang1,2
  • Zesen Lin3
  • Mengfei Zhang1,2
  • Xiaolei Yin1,2
  • Shiwei Zhu1,2
  • Yao Dai4,5
  • Xiaotong Guo1,2
  • Jie Song6,7
  • Jun Xu1,2
7 affiliations
  1. 1School of Physics and Astronomy, Anqing Normal University , Anqing 246011 ,
  2. 2Institute of Astronomy and Astrophysics, Anqing Normal University , Anqing 246133 ,
  3. 3Institute for Astrophysics, School of Physics, Zhengzhou University , Zhengzhou 450001 ,
  4. 4Shanghai Astronomical Observatory, Chinese Academy of Sciences , 80 Nandan Road, Shanghai 200030 ,
  5. 5School of Astronomy and Space Science, University of Chinese Academy of Sciences , No. 19A Yuquan Road, Beijing 100049 ,
  6. 6School of Astronomy and Space Science, University of Science and Technology of China , Hefei 230026 ,
  7. 7Institute of Deep Space Sciences, Deep Space Exploration Laboratory , Hefei 230026 ,
Open at sourcePDFDOICite

Abstract

In this study, we present an efficient framework for galaxy morphology classification by combining the AlexNet model for feature extraction with the Uniform Manifold Approximation and Projection (UMAP) algorithm for dimensionality reduction. Using the recently released COSMOS2025 catalogue, we select 100,362 galaxies at 0.5 < z < 6.0 with Imag < 27.5, and classify their morphology based on rest-frame optical images extracted from the COSMOS-Web survey. These galaxies are categorized into five morphological classes: spheroidal galaxies (SPH, 15,015), early-type disc galaxies (ETD, 34,361), late-type disc galaxies (LTD, 19,411), irregular galaxies (IRR, 21,034), and unclassified galaxies (UNC, 10,541). The performance of the supervised classification is assessed by using a validation set, which includes weighted averages of recall, precision, and an F1 score of ∼ 95%. The t-SNE-based visualisation of the feature space shows that different morphological classes form well-separated clusters with minimal overlap, supporting the robustness of the classification framework. We validate the classification results using parametric (Sérsic index n, effective radius re, and compactness Σ1.5) and non-parametric structural measurements. These measurements exhibit systematic trends that are consistent with established morphological sequences and theoretical expectations of galaxy evolution. This method provides a scalable approach for galaxy morphology classification and is well-suited for application to upcoming wide-field surveys, such as CSST.

Related

  1. Morphology classification for galaxies in the Kilo Degree Survey using a label-efficient self-supervised learning framework
    Xu Huang, Rui Li, Liang Gao +14
    arXivPreprintarXiv licenceFull textGalaxiesarXiv
  2. Morphology Classification for Galaxies in the Kilo Degree Survey Using a Label-efficient Self-supervised Learning Framework
    Xu Huang, Rui Li, Liang Gao +14
    The Astrophysical Journal Supplement SeriesPeer-reviewedCC BY 4.0Full textGalaxiesCrossref
  3. SpecLess: A Multi Survey Python Package for Machine Learning Classification of Galaxy Morphology and Activity from Photometry
    Uzay Aydin, Mehmet Tanriver
    arXivPreprintarXiv licenceFull textGalaxiesarXiv
  4. The assembly of bulge-dominated galaxies: two evolutionary channels traced through morphology, kinematics, and environment with a hybrid classification pipeline
    R. Flores-Freitas, R. R. de Carvalho, K. V. Nedkova +3
    arXivPreprintarXiv licenceFull textGalaxiesarXiv
  5. Efficient Context-Limited Telescope Bibliography Classification for the WASP-2025 Shared Task Using SciBERT
    Madhusudhana Naidu
    arXivPreprintCC BY 4.0Full textInstrumentation & methodsarXiv

Cite

BibTeXRIS
BibTeX
@article{xie2026efficient,
  title = {{An Efficient Galaxy Morphology Classification Framework updated with Two-Stage Feature Extraction with AlexNet Encoding and UMAP}},
  author = {Mengjiao Xie and Guanwen Fang and Zesen Lin and Mengfei Zhang and Xiaolei Yin and Shiwei Zhu and Yao Dai and Xiaotong Guo and Jie Song and Jun Xu},
  journal = {Monthly Notices of the Royal Astronomical Society},
  year = {2026},
  month = oct,
  doi = {10.1093/mnras/stag1998},
  url = {https://academic.oup.com/mnras/advance-article/doi/10.1093/mnras/stag1998/8965450},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - An Efficient Galaxy Morphology Classification Framework updated with Two-Stage Feature Extraction with AlexNet Encoding and UMAP
AU  - Mengjiao Xie
AU  - Guanwen Fang
AU  - Zesen Lin
AU  - Mengfei Zhang
AU  - Xiaolei Yin
AU  - Shiwei Zhu
AU  - Yao Dai
AU  - Xiaotong Guo
AU  - Jie Song
AU  - Jun Xu
PY  - 2026
DA  - 2026/10/21
JO  - Monthly Notices of the Royal Astronomical Society
DO  - 10.1093/mnras/stag1998
UR  - https://academic.oup.com/mnras/advance-article/doi/10.1093/mnras/stag1998/8965450
AB  - In this study, we present an efficient framework for galaxy morphology classification by combining the AlexNet model for feature extraction with the Uniform Manifold Approximation and Projection (UMAP) algorithm for dimensionality reduction. Using the recently released COSMOS2025 catalogue, we select 100,362 galaxies at 0.5 < z < 6.0 with Imag < 27.5, and classify their morphology based on rest-frame optical images extracted from the COSMOS-Web survey. These galaxies are categorized into five morphological classes: spheroidal galaxies (SPH, 15,015), early-type disc galaxies (ETD, 34,361), late-type disc galaxies (LTD, 19,411), irregular galaxies (IRR, 21,034), and unclassified galaxies (UNC, 10,541). The performance of the supervised classification is assessed by using a validation set, which includes weighted averages of recall, precision, and an F1 score of ∼ 95%. The t-SNE-based visualisation of the feature space shows that different morphological classes form well-separated clusters with minimal overlap, supporting the robustness of the classification framework. We validate the classification results using parametric (Sérsic index n, effective radius re, and compactness Σ1.5) and non-parametric structural measurements. These measurements exhibit systematic trends that are consistent with established morphological sequences and theoretical expectations of galaxy evolution. This method provides a scalable approach for galaxy morphology classification and is well-suited for application to upcoming wide-field surveys, such as CSST.
SN  - 0035-8711
SN  - 1365-2966
ER  -