Identifying Gems from Roman RAPIDly

2026-06-03

AI Summary

This work addresses the challenge of limited real observational data in the early phase of the Nancy Grace Roman Space Telescope by proposing RuBR, a machine learning model designed to automatically distinguish genuine signals from spurious detections among transients and variable sources. The approach integrates image differencing with locally injected data and simulations from OpenUniverse2024, augmented by a domain adaptation mechanism to enable unsupervised model transfer across domains. Through three innovative training strategies, RuBR demonstrates robust performance across diverse training–testing configurations, offering a scalable and effective technical pathway for reliable and efficient transient identification in the Roman era.

Abstract

The Nancy Grace Roman Space Telescope (Roman), set for launch as early as September 2026, will conduct wide-field infrared imaging surveys with unprecedented spatial resolution and cadence, enabling the discovery of millions of astronomical transients. Hence, it is necessary to have automated pipelines for generating alerts in place so that the telescope can begin discovering reliable transients and variable objects soon after it is launched. However, no real Roman data currently exist, making the development of such pipelines difficult. In this work, we present a machine learning model $RuBR$ and a general methodology for distinguishing genuine transient and variable detections from spurious (bogus) detections within the RAPID pipeline. In particular, we present three models using this methodology: $RuBR_{comb}$ trained and tested on combined locally injected and OpenUniverse2024 transients, $RuBR_{loc}$ trained on locally injected transients and tested on OpenUniverse2024 transients, and $RuBR_{DA}$ that combines locally injected transients with a fraction of OpenUniverse2024 transients in domain-adaptation mode for training. This paves the way for strategies to adapt the $RuBR_{comb}$ model to real observations in the absence of any ground-truth labels during the early phases of the Roman mission. While the image differencing pipeline continues to be improved, our experimental results demonstrate the effectiveness of the proposed approach and its promise for robust real-bogus classification in the Roman era.

Problem

• transient detection
• real-bogus classification
• Roman Space Telescope
• automated alert pipeline
• domain adaptation

Innovation

• machine learning
• domain adaptation
• real-bogus classification
• transient detection
• Roman Space Telescope