Large Language Model-driven Analysis of General Coordinates Network (GCN) Circulars

Abstract

The General Coordinates Network (GCN) is NASA's time-domain and multimessenger alert system. GCN distributes two data products: automated "Notices" and human-generated "Circulars" that report the observations of high-energy and multimessenger astronomical transients. The flexible and nonstructured format of GCN Circulars, comprising more than 40,500 Circulars accumulated over three decades, makes it challenging to manually extract observational information, such as redshift or observed wave bands. In this work, we employ large language models (LLMs) to facilitate the automated parsing of transient reports. We develop a neural topic modeling pipeline with open-source tools for the automatic clustering and summarization of astrophysical topics in the Circulars archive. Using neural topic modeling and contrastive fine-tuning, we classify Circulars based on their observation wave bands and messengers. Additionally, we separate gravitational-wave event clusters and their electromagnetic counterparts from the Circulars archive. Finally, using the open-source Mistral model, we implement a system to automatically extract gamma-ray burst (GRB) redshift information from the Circulars archive, without the need for any training. Evaluation against the manually curated Neil Gehrels Swift Observatory GRB table shows that our simple system, with the help of prompt-tuning, output parsing, and retrieval augmented generation (RAG), can achieve an accuracy of 97.2% for redshift-containing Circulars. Our neural search-enhanced RAG pipeline accurately retrieved 96.8% of redshift Circulars from the manually curated archive. Our study demonstrates the potential of LLMs to automate and enhance astronomical text mining and provides a foundational work for future advances in transient alert analysis.

21 pages, 11 figures, 7 tables. Published in ApJS

References in corpus (29)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• The Large Area Telescope on the Fermi Gamma-ray Space Telescope Mission
• Multi-messenger Observations of a Binary Neutron Star Merger
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Nuclear Spectroscopic Telescope Array (NuSTAR) Mission
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The James Webb Space Telescope
• The Fermi Gamma-Ray Burst Monitor
• X-shooter, the new wide band intermediate resolution spectrograph at the ESO Very Large Telescope
• The IceCube Neutrino Observatory: Instrumentation and Online Systems
• ANTARES: the first undersea neutrino telescope
• ChatGPT Chemistry Assistant for Text Mining and Prediction of MOF Synthesis
• The Atacama Large Millimeter/submillimeter Array
• Accelerated Hierarchical Density Clustering
• The CHIME Fast Radio Burst Project: System Overview
• The Status of the H.E.S.S. Project
• The Australia Telescope Compact Array Broadband Backend (CABB)
• The Arcminute Microkelvin Imager
• Science with the Cherenkov Telescope Array
• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Fink, a new generation of broker for the LSST community
• A data science platform to enable time-domain astronomy
• Science objectives of the Einstein Probe mission
• The Chinese-French SVOM mission for GRBs studies
• The Astrophysical Multimessenger Observatory Network (AMON): Performance and Science Program
• YSE-PZ: A Transient Survey Management Platform that Empowers the Human-in-the-Loop
• Astronomy potential of KM3NeT/ARCA
• Astro-COLIBRI -- The COincidence LIBrary for Real-time Inquiry for multimessenger astrophysics
• Information Retrieval and Recommendation System for Astronomical Observatories