FRTSearch: Unified Detection and Parameter Inference of Fast Radio Transients using Instance Segmentation

2026-04-14

AI Summary

This study addresses the high computational cost and susceptibility to radio frequency interference (RFI) of traditional single-pulse search algorithms, which lead to elevated false-alarm rates when processing the massive data volumes from modern radio telescopes. To overcome these limitations, the authors propose a novel “detection-as-inference” paradigm that formulates fast radio transient (FRT) detection as a time–frequency dynamic spectrogram pattern recognition task grounded in the cold plasma dispersion relation. By integrating Mask R-CNN for instance segmentation with a custom physics-driven algorithm, IMPIC, the framework enables end-to-end detection and parameter inference. Trained on the CRAFTS-FRT dataset, the model achieves a 98.0% recall rate on FAST-FREX, reduces false alarms by over 99.9% compared to PRESTO, accelerates processing by up to 13.9×, and generalizes to detect all 19 ASKAP FRBs without retraining.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Algorithm Configuration

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

The exponential growth of data from modern radio telescopes presents a significant challenge to traditional single-pulse search algorithms, which are computationally intensive and prone to high false-positive rates due to Radio Frequency Interference (RFI). In this work, we introduce FRTSearch, an end-to-end framework unifying the detection and physical characterization of Fast Radio Transients (FRTs). Leveraging the morphological universality of dispersive trajectories in time-frequency dynamic spectra, we reframe FRT detection as a pattern recognition problem governed by the cold plasma dispersion relation. To facilitate this, we constructed CRAFTS-FRT, a pixel-level annotated dataset derived from the Commensal Radio Astronomy FAST Survey (CRAFTS), comprising 2{,}392 instances across diverse source classes. This dataset enables the training of a Mask R-CNN model for precise trajectory segmentation. Coupled with our physics-driven IMPIC algorithm, the framework maps the geometric coordinates of segmented trajectories to directly infer the Dispersion Measure (DM) and Time of Arrival (ToA). Benchmarking on the FAST-FREX dataset shows that FRTSearch achieves a 98.0\% recall, competitive with exhaustive search methods, while reducing false positives by over 99.9\% compared to PRESTO and delivering a processing speedup of up to $13.9\times$. Furthermore, the framework demonstrates robust cross-facility generalization, detecting all 19 tested FRBs from the ASKAP survey without retraining. By shifting the paradigm from ``search-then-identify'' to ``detect-and-infer,'' FRTSearch provides a scalable, high-precision solution for real-time discovery in the era of petabyte-scale radio astronomy.

Problem

• Fast Radio Transients
• Radio Frequency Interference
• Single-pulse Search
• False-positive Rate
• Data Scalability

Innovation

• instance segmentation
• dispersion measure inference
• fast radio transients
• physics-informed machine learning
• RFI-robust detection