AS-Bridge: A Bidirectional Generative Framework Bridging Next-Generation Astronomical Surveys

2026-03-12

AI Summary

Ground-based and space-based astronomical surveys—such as LSST and Euclid—exhibit substantial differences in observational modalities, resolution, point spread functions, and scanning strategies, which hinder efficient joint analysis. This work proposes AS-Bridge, a bidirectional diffusion generative model grounded in stochastic Brownian bridge processes, to establish a conditional probabilistic mapping between the two surveys over their overlapping sky regions. AS-Bridge enables, for the first time, bidirectional translation of cross-modal astronomical images with high fidelity. The framework further supports probabilistic inpainting of missing data and facilitates collaborative detection of rare astrophysical objects. By demonstrating the feasibility of realistic cross-survey image synthesis, this approach establishes a novel paradigm for multi-survey data fusion in astronomy.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Diffusion Models for Vision

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

The upcoming decade of observational cosmology will be shaped by large sky surveys, such as the ground-based LSST at the Vera C. Rubin Observatory and the space-based Euclid mission. While they promise an unprecedented view of the Universe across depth, resolution, and wavelength, their differences in observational modality, sky coverage, point-spread function, and scanning cadence make joint analysis beneficial, but also challenging. To facilitate joint analysis, we introduce A(stronomical)S(urvey)-Bridge, a bidirectional generative model that translates between ground- and space-based observations. AS-Bridge learns a diffusion model that employs a stochastic Brownian Bridge process between the LSST and Euclid observations. The two surveys have overlapping sky regions, where we can explicitly model the conditional probabilistic distribution between them. We show that this formulation enables new scientific capabilities beyond single-survey analysis, including faithful probabilistic predictions of missing survey observations and inter-survey detection of rare events. These results establish the feasibility of inter-survey generative modeling. AS-Bridge is therefore well-positioned to serve as a complementary component of future LSST-Euclid joint data pipelines, enhancing the scientific return once data from both surveys become available. Data and code are available at \href{https://github.com/ZHANG7DC/AS-Bridge}{https://github.com/ZHANG7DC/AS-Bridge}.

Problem

• astronomical surveys
• joint analysis
• observational modality
• data integration
• cosmology

Innovation

• bidirectional generative model
• diffusion model
• Brownian Bridge
• multi-survey fusion
• astronomical image translation