Mapping Galaxy Images Across Ultraviolet, Visible and Infrared Bands Using Generative Deep Learning

2025-01-25

AI Summary

This study addresses cross-domain translation of multi-band galaxy images—enabling high-fidelity mapping among ultraviolet, optical, and infrared bands—and inferring galaxy morphology under partial band缺失. We present the first systematic application of generative deep learning—specifically, a supervised U-Net-based image-to-image translation model—trained on Illustris simulation data, incorporating astrophysically grounded morphology metrics (e.g., GINI and M20) to enforce physical consistency. The method supports both band interpolation and extrapolation, achieving high accuracy across quantitative metrics (MAE, SSIM, PSNR) and astronomical morphology indicators. Crucially, it generalizes successfully to real observational data from the DECaLS survey. Our approach bridges the gap between cosmological simulations and empirical observations, delivering an interpretable, verifiable tool for multi-band image completion, telescope mission planning, and studies of galaxy morphological evolution.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

We demonstrate that generative deep learning can translate galaxy observations across ultraviolet, visible, and infrared photometric bands. Leveraging mock observations from the Illustris simulations, we develop and validate a supervised image-to-image model capable of performing both band interpolation and extrapolation. The resulting trained models exhibit high fidelity in generating outputs, as verified by both general image comparison metrics (MAE, SSIM, PSNR) and specialized astronomical metrics (GINI coefficient, M20). Moreover, we show that our model can be used to predict real-world observations, using data from the DECaLS survey as a case study. These findings highlight the potential of generative learning to augment astronomical datasets, enabling efficient exploration of multi-band information in regions where observations are incomplete. This work opens new pathways for optimizing mission planning, guiding high-resolution follow-ups, and enhancing our understanding of galaxy morphology and evolution.

Problem

• Galaxy Image Conversion
• Multi-Spectral Imaging
• Incomplete Information Inference

Innovation

• Generative Deep Learning
• Multi-spectral Image Conversion
• Astrophysical Data Understanding