Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation
By: Chenrui Ma , Zechang Sun , Tao Jing and more
Potential Business Impact:
Makes computers find rare space objects better.
Observational astronomy relies on visual feature identification to detect critical astrophysical phenomena. While machine learning (ML) increasingly automates this process, models often struggle with generalization in large-scale surveys due to the limited representativeness of labeled datasets -- whether from simulations or human annotation -- a challenge pronounced for rare yet scientifically valuable objects. To address this, we propose a conditional diffusion model to synthesize realistic galaxy images for augmenting ML training data. Leveraging the Galaxy Zoo 2 dataset which contains visual feature -- galaxy image pairs from volunteer annotation, we demonstrate that our model generates diverse, high-fidelity galaxy images closely adhere to the specified morphological feature conditions. Moreover, this model enables generative extrapolation to project well-annotated data into unseen domains and advancing rare object detection. Integrating synthesized images into ML pipelines improves performance in standard morphology classification, boosting completeness and purity by up to 30\% across key metrics. For rare object detection, using early-type galaxies with prominent dust lane features ( $\sim$0.1\% in GZ2 dataset) as a test case, our approach doubled the number of detected instances from 352 to 872, compared to previous studies based on visual inspection. This study highlights the power of generative models to bridge gaps between scarce labeled data and the vast, uncharted parameter space of observational astronomy and sheds insight for future astrophysical foundation model developments. Our project homepage is available at https://galaxysd-webpage.streamlit.app/.
Similar Papers
Category-based Galaxy Image Generation via Diffusion Models
Instrumentation and Methods for Astrophysics
Creates realistic pictures of galaxies for science.
Galaxy Morphology Classification with Counterfactual Explanation
Machine Learning (CS)
Explains how galaxies change over time.
Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep Learning
Instrumentation and Methods for Astrophysics
Makes telescopes see galaxies in new colors.