Evaluating Zero-Shot Anomaly Detection for Identifying Unusual Galaxy Morphologies in CEERS and NGDEEP

Abstract

Galaxy morphology out to z∼ 6 provides insight into galaxy formation and evolution, but identifying rare or structurally complex systems is difficult due to observational limits and the scale of modern imaging surveys. Here, we apply AdaCLIP, a Zero-Shot Anomaly Detection (ZSAD) model built upon the Contrastive Language-Image Pretraining (CLIP) model and adapted using non-astronomical anomaly-detection datasets, to identify structurally unusual galaxies without galaxy-specific anomaly-detection training or morphological labels. We extract anomaly scores and 768-dimensional feature embeddings from 38,853 galaxies in the Cosmic Evolution Early Release Science (CEERS) and Next Generation Deep Extragalactic Exploratory Public (NGDEEP) surveys, and compare the resulting anomaly scores with parametric GALFIT and nonparametric statmorph measurements. The feature embeddings reveal structure associated with galaxy morphology and observational properties, while anomaly scores show modest trends with structural measures, including asymmetry, concentration, M₂₀, and size, but weaker or less consistent trends with Sérsic index, axis ratio, smoothness, and Gini coefficient. These results highlight the potential of ZSAD as a scalable tool for identifying unusual galaxy morphologies in large astronomical imaging surveys, including those anticipated from the Nancy Grace Roman Space Telescope.

Anomaly detection in Fink. I. Discovery, follow-up, and classification of unusual sources
M. V. Pruzhinskaya, M. V. Kornilov, A. V. Dodin +19
Astronomy & Astrophysics5 Oct 2026Peer-reviewedPublisher termsHigh-energy astrophysicsCrossref
PISCES: Physics-Informed Solar-wind Convolutional autoEncoder for Space-weather Anomaly Detection and Early Warning
Kevin Lee, Alison J. March
arXiv23 Sep 2026PreprintCC BY 4.0Full textSolar & stellar physicsarXiv
Comparing Active Anomaly Detection Frameworks: From Light Curves to Images
Sreevarsha Sreejith, Robert C. Nichol
arXiv28 Sep 2026PreprintCC BY 4.0Full textInstrumentation & methodsarXiv
Quantum-inspired tensor network autoencoders for anomaly detection: a MERA-based approach
Emre Gurkanli, Michael Spannowsky
The European Physical Journal C22 Oct 2026Peer-reviewedCC BY 4.0Full textGeneral astronomy High-energy & particle physicsCrossrefDOAJ
MADGRAV: a multilevel anomaly-detection pipeline for gravitational-wave searches applied to LIGO data
Gianluca Inguglia, Huw Haigh, Ulyana Dupletsa +1
arXiv19 Oct 2026PreprintCC BY 4.0Full textInstrumentation & methods Gravitation & general relativityarXiv

Cite

BibTeX RIS

BibTeX

@misc{surakan2026evaluating,
  title = {{Evaluating Zero-Shot Anomaly Detection for Identifying Unusual Galaxy Morphologies in CEERS and NGDEEP}},
  author = {T. B. Surakan and J. S. Kartaltepe and R. Pattnaik and C. K. Binu and I. G. Cox and T. Y. Hsiao and R. A. Lucas and F. Pacucci and G. Troiani and L. Y. Aaron Yung},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.29868},
  eprint = {2610.29868},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.29868},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Evaluating Zero-Shot Anomaly Detection for Identifying Unusual Galaxy Morphologies in CEERS and NGDEEP
AU  - T. B. Surakan
AU  - J. S. Kartaltepe
AU  - R. Pattnaik
AU  - C. K. Binu
AU  - I. G. Cox
AU  - T. Y. Hsiao
AU  - R. A. Lucas
AU  - F. Pacucci
AU  - G. Troiani
AU  - L. Y. Aaron Yung
PY  - 2026
DA  - 2026/10/21
PB  - arXiv
DO  - 10.48550/arxiv.2610.29868
UR  - https://arxiv.org/abs/2610.29868
AB  - Galaxy morphology out to z∼ 6 provides insight into galaxy formation and evolution, but identifying rare or structurally complex systems is difficult due to observational limits and the scale of modern imaging surveys. Here, we apply AdaCLIP, a Zero-Shot Anomaly Detection (ZSAD) model built upon the Contrastive Language-Image Pretraining (CLIP) model and adapted using non-astronomical anomaly-detection datasets, to identify structurally unusual galaxies without galaxy-specific anomaly-detection training or morphological labels. We extract anomaly scores and 768-dimensional feature embeddings from 38,853 galaxies in the Cosmic Evolution Early Release Science (CEERS) and Next Generation Deep Extragalactic Exploratory Public (NGDEEP) surveys, and compare the resulting anomaly scores with parametric GALFIT and nonparametric statmorph measurements. The feature embeddings reveal structure associated with galaxy morphology and observational properties, while anomaly scores show modest trends with structural measures, including asymmetry, concentration, M_20, and size, but weaker or less consistent trends with Sérsic index, axis ratio, smoothness, and Gini coefficient. These results highlight the potential of ZSAD as a scalable tool for identifying unusual galaxy morphologies in large astronomical imaging surveys, including those anticipated from the Nancy Grace Roman Space Telescope.
ER  -

Abstract

Related

Cite