MARS：用于射电天文掩模引导抑制的轻量级形态感知RFI分割网络
MARS: A Lightweight Morphology-Aware RFI Segmentation Network for Mask-Guided Mitigation in Radio Astronomy
浏览论文内容
中文总结 AI 辅助
本文提出基于GPU的轻量级RFI抑制流程MARS，采用形态感知U-Net网络，通过加入天体信号保留损失提升信号保护效果，在精度、信号保留率和计算速度上均优于现有CPU工具。
中文摘要 AI 辅助
下一代射电望远镜生成的滤波器组数据速率极高，导致存储所有观测数据以供后续离线抑制变得不切实际，因此抑制操作必须在搜索流程中实时或近实时进行，同时保留弥散的天体物理信号。CPU工具难以适配以GPU为中心的搜索流程，而神经网络替代方案的计算量往往较大。本文提出MARS，一种基于GPU的RFI抑制流程，核心为轻量级形态感知RFI分割网络。该模型是宽度缩减、全分辨率的U-Net，其瓶颈层包含局部、水平和垂直滤波器，以捕捉频时平面内紧凑和拉长的RFI结构；归一化、补丁构建、掩模重建、替换、基线去除及输出重缩放也均在GPU上实现。训练过程中加入了天体信号保留损失，以避免错误标记弥散脉冲。在受控补丁级测试中，MARS的RFI掩模F1分数达$0.978$，精确率达$0.995$；在干净补丁中保留了注入弥散信号通量的$97.6\%$，在包含混合注入RFI的补丁中保留了非重叠信号通量的$96.4\%$。消融实验表明，天体信号保留损失尤其提升了对紧凑、低色散量（DM）、高信噪比（S/N）脉冲的保护。在滤波器组层面，经MARS抑制后恢复的周期匹配PRESTO候选体，相对于filtool的中位数显著性比率为$0.90$至$0.99$；两种方法均在两次真实GMRT观测中恢复了已知脉冲星。在NVIDIA GH200 GPU上，MARS的纯计算加速比相对于AMD EPYC 9825 CPU上测试的最快多线程filtool配置达$6.2$至$7.0$倍。
英文摘要
Next-generation radio telescopes generate filterbank data at rates that make storing all observations for later offline mitigation impractical. Mitigation must therefore operate in real or near-real time within the search pipeline while preserving dispersed astrophysical signals. CPU tools fit GPU-centred search pipelines poorly, while neural alternatives can be computationally heavy. We present MARS, a GPU-based RFI mitigation pipeline centred on a lightweight Morphology-Aware RFI Segmentation Network. The model is a reduced-width, full-resolution U-Net with a bottleneck containing local, horizontal, and vertical filters to capture compact and elongated RFI structures in the frequency-time plane. Normalisation, patch construction, mask reconstruction, replacement, baseline removal, and output rescaling are also implemented on GPU. Training includes an astronomical-signal preservation loss that discourages false flagging of dispersed pulses. In controlled patch-level tests, MARS achieves an RFI-mask F1 score of $0.978$ and a precision of $0.995$. It retains $97.6\%$ of the injected dispersed-signal fluence in clean patches and $96.4\%$ of the non-overlapping signal fluence in patches containing mixed injected RFI. Ablation experiments show that the astronomical-signal preservation loss particularly improves the protection of compact, low-DM, high-S/N pulses. At filterbank level, period-matched PRESTO candidates recovered after MARS mitigation have median significance ratios of $0.90$--$0.99$ relative to filtool. Both methods also recover the known pulsars in two real GMRT observations. On an NVIDIA GH200 GPU, MARS achieves a compute-only speedup of $6.2\times$--$7.0\times$ over the fastest tested multi-threaded filtool configurations on an AMD EPYC 9825 CPU.
