Identifying Gems from Roman RAPIDly
2026-06-03 • Machine Learning
Machine LearningComputer Vision and Pattern Recognition
AI summaryⓘ
The authors present a machine learning method called RuBR to help the upcoming Roman Space Telescope quickly tell real space events from false alarms. Since no real data from the telescope exists yet, they trained and tested their models using simulated data and data from another source. They created three versions of RuBR to handle different training situations and prepared strategies to adapt these models once real data arrives. Their results show that this approach can reliably detect real astronomical changes, which is important for the telescope's mission to find millions of space events.
Nancy Grace Roman Space Telescopeastronomical transientsmachine learningimage differencingreal-bogus classificationautomated pipelinesdomain adaptationinfrared imagingvariable objectssimulated data
Authors
Karan Gandhi, Ashish A. Mahabal, Jacob E. Jencson, Russ R. Laher, Ben Rusholme, Lin Yan, Ryan M. Lau, Schuyler D. Van Dyk, Mansi M. Kasliwal
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.