Neural Posterior Estimation for Cataloging Astronomical Images from the Legacy Survey of Space and Time

2025-10-17

AI Summary

To address statistical inconsistency in traditional deterministic methods and low efficiency or poor generalizability of existing probabilistic approaches for multi-band stacked-image cataloging in the Legacy Survey of Space and Time (LSST), this paper introduces the first neural posterior estimation (NPE) framework tailored to astronomical image cataloging. Our method reformulates the ill-posed deterministic modeling task as Bayesian posterior inference via deep neural networks, enabling end-to-end joint estimation of source positions, fluxes, and galaxy morphologies. Trained on simulation-driven data, the framework is validated on the DC2 simulated dataset. Results demonstrate superior performance over the standard LSST pipeline across detection completeness, photometric accuracy, galaxy classification, and shape measurement. Crucially, it yields well-calibrated, statistically consistent posterior distributions while maintaining both high precision and computational efficiency—establishing a scalable, probabilistic paradigm for large-scale time-domain survey catalogs.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

The Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will commence full-scale operations in 2026, yielding an unprecedented volume of astronomical images. Constructing an astronomical catalog, a table of imaged stars, galaxies, and their properties, is a fundamental step in most scientific workflows based on astronomical image data. Traditional deterministic cataloging methods lack statistical coherence as cataloging is an ill-posed problem, while existing probabilistic approaches suffer from computational inefficiency, inaccuracy, or the inability to perform inference with multiband coadded images, the primary output format for LSST images. In this article, we explore a recently developed Bayesian inference method called neural posterior estimation (NPE) as an approach to cataloging. NPE leverages deep learning to achieve both computational efficiency and high accuracy. When evaluated on the DC2 Simulated Sky Survey -- a highly realistic synthetic dataset designed to mimic LSST data -- NPE systematically outperforms the standard LSST pipeline in light source detection, flux measurement, star/galaxy classification, and galaxy shape measurement. Additionally, NPE provides well-calibrated posterior approximations. These promising results, obtained using simulated data, illustrate the potential of NPE in the absence of model misspecification. Although some degree of model misspecification is inevitable in the application of NPE to real LSST images, there are a variety of strategies to mitigate its effects.

Problem

• Traditional cataloging methods lack statistical coherence for astronomical images
• Existing probabilistic approaches are computationally inefficient or inaccurate
• Current methods cannot effectively process LSST multiband coadded images

Innovation

• Neural posterior estimation for astronomical cataloging
• Deep learning enables efficient probabilistic inference
• Outperforms standard pipeline on simulated LSST data