Hyrax: An Extensible Framework for Rapid ML Experimentation and Unsupervised Discovery in the Era of Rubin, Roman, and Euclid

2026-05-18

AI Summary

This work addresses the infrastructure bottleneck in machine learning for next-generation astronomical surveys—such as Rubin, Roman, and Euclid—whose massive multimodal data streams overwhelm conventional analysis pipelines. We present the first open-source, astronomy-oriented, end-to-end machine learning framework featuring GPU acceleration, which integrates multimodal data processing, unsupervised representation learning, vector database indexing, density-based clustering, and interactive latent space exploration. Operating without labeled data, the framework enables systematic experimental comparison and scientific discovery. Validated across five real-world survey tasks, it successfully identifies novel galaxy mergers, low-surface-brightness objects, and gravitational lens candidates, while improving the accuracy of transient classification and exoplanet detection, thereby demonstrating its generality and computational efficiency.

Abstract

The NSF-DOE Vera C. Rubin Observatory, Roman Space Telescope, Euclid, and other next-generation surveys will deliver imaging, spectroscopic, and time-domain data at scales that increasingly shift the bottleneck in astronomical machine learning (ML) projects from model design to infrastructure. We present Hyrax, an open-source, modular, GPU-enabled Python framework that supports the full ML lifecycle in astronomy: from data acquisition and training to inference and experiment comparison, with capabilities including multimodal dataset support, integrated vector databases for similarity search, and interactive two- and three-dimensional latent-space exploration for unsupervised discovery. We demonstrate Hyrax's versatility through five representative applications on real survey data: (i) unsupervised representation learning on $\sim 4\times10^5$ Rubin Legacy Survey of Space and Time (LSST) Data Preview 1 (DP1) galaxies, surfacing new merger and low-surface-brightness candidates missing from reference Euclid and Dark Energy Survey catalogs, while also isolating imaging artifacts -- all without labeled training data; (ii) hybrid density-based clustering for identifying cluster-scale gravitational lens candidates in DP1 data; (iii) multimodal early-time transient classification in the Zwicky Transient Facility leveraging light curves, spectra, images, and metadata; (iv) supervised false-positive filtering in shift-and-stack searches for distant solar system objects in the Dark Energy Camera Ecliptic Exploration Project survey; and (v) supervised detection of semi-resolved dwarf galaxies in Hyper Suprime-Cam and LSST-like imaging using synthetic source injection. Together, these results demonstrate that Hyrax provides astronomy-specific ML infrastructure that enables systematic discovery and rapid methodological iteration across next-generation astronomical surveys.

Problem

• astronomical machine learning
• next-generation surveys
• ML infrastructure
• unsupervised discovery
• multimodal data

Innovation

• multimodal astronomy
• unsupervised discovery
• latent-space exploration
• GPU-accelerated ML framework
• vector database for similarity search