arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.05958astro-ph.GAastro-ph.HEastro-ph.IM
收藏

SwinYNet:一种基于Transformer的多任务模型,用于准确且高效的FRB搜索

SwinYNet: A Transformer-based Multi-Task Model for Accurate and Efficient FRB Search

Zhejiang Lab(浙江实验室);Hangzhou Dianzi University(杭州电子科技大学);National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);Beijing Normal University(北京师范大学)

Yunchuan Chen, Shulei Ni, Chan Li, Jianhua Fang, Dengke Zhou, Huaxi Chen, Yi Feng, Pei Wang, Chenwu Jin, Han Wang, Bijuan Huang, Xuerong Guo, Donghui Quan, Di Li

AI总结:

SwinYNet通过基于Transformer的多任务模型实现高效准确的FRB搜索,无需预处理,且在精度和速度上优于传统方法和AI基线。

摘要:

在本研究中,我们提出了一种基于Transformer的多任务模型,用于从时频数据中直接进行快速射电暴(FRB)检测、信号分割和参数估计,而无需计算成本高昂的去分散预处理。为克服标记观测数据稀缺的问题,我们开发了FRB模拟器和基于规则的自动注释流程,使模型仅在模拟数据上进行训练。在FAST-FREX数据集上的评估显示,我们的模型在F1分数上达到了97.8%,召回率为95.7%,精确率为100%,在准确性和推理速度上均优于传统工具(如PRESTO、Heimdall)和最近的AI基线(如RaSPDAM、DRAFTS)。该模型支持像素级信号分割,并能提供可靠的色散测量(DM)和到达时间(ToA)估计。在CRAFTS数据上的大规模盲搜进一步证明了其鲁棒性,平均假阳性率为0.28%,且需要极少量的人工验证。此次搜索已成功识别出两个脉冲星候选者,两者均被确认为已知脉冲星。处理基准表明,该模型能够在单个消费级GPU上实现实时搜索,使百亿字节级的盲搜成为可能。代码已公开在GitHub上,且该模型可轻松集成到现有工具中,以自动化和简化无线电数据分析,不仅限于FRB或脉冲星搜索。

英文摘要:

In this study, we present a transformer-based multi-task model for Fast Radio Burst (FRB) detection, signal segmentation, and parameter estimation directly from time-frequency data, without requiring computationally expensive de-dispersion preprocessing. To overcome the scarcity of labeled observational data, we develop an FRB simulator and a rule-based automatic annotation pipeline, enabling training exclusively on simulated data. Evaluations on the FAST-FREX dataset show that our model achieves an F1 score of 97.8%, recall of 95.7%, and precision of 100%, outperforming both conventional tools (e.g., PRESTO, Heimdall) and recent AI-based baselines (e.g., RaSPDAM, DRAFTS) in both accuracy and inference speed. The model supports pixel-level signal segmentation and yields reliable estimates for dispersion measure (DM) and time of arrival (ToA). Large-scale blind searches on CRAFTS data further demonstrate robustness, with an average false positive rate of 0.28% and minimal human verification required. This search has already led to the identification of two pulsar candidates, both confirmed as known pulsars. Processing benchmarks indicate that the model enables real-time searches on a single consumer-grade GPU, making petabyte-scale blind searches feasible. The code is publicly available on GitHub, and the model can be easily integrated with existing tools to automate and streamline radio data analysis beyond FRB or pulsar searches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑