用于连续扫描空气等离子太赫兹光谱的自监督Noise2Noise增强去噪
Self-Supervised Noise2Noise-Enhanced Denoising for Continuous-Scan Air-Plasma THz Spectroscopy
- Institute of Digital Communication Systems, Ruhr University Bochum（鲁尔大学波鸿分校数字通信系统研究所）
- Photonics and Ultrafast Laser Science, Ruhr University Bochum（鲁尔大学波鸿分校光子学与超快激光科学研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对空气等离子太赫兹时域光谱的噪声问题，提出自监督Noise2Noise增强去噪方法，结合一维残差U-Net，可将测量时间缩减约5.4倍，无需硬件修改即可提升光谱测量速度。
AI中文摘要：
基于空气等离子体产生和平衡空气偏置相干检测的太赫兹时域光谱（THz-TDS）可实现无间隙宽带覆盖，但单个连续扫描轨迹受脉冲间波动和电子噪声影响严重。因此要达到有用的信噪比，需对多条轨迹取平均，这直接增加了测量时间。我们提出一种学习型去噪方法，可从少至一次完整的连续延迟扫描（此处称为单扫描轨迹）中恢复高质量太赫兹波形。采用两种互补策略训练紧凑的一维残差U-Net：一种是参考监督基线，将单个噪声轨迹映射到长平均参考波形；另一种是Noise2Noise方法，从独立采集的噪声轨迹对中学习，无需干净的训练目标。对两种模型的预测结果取平均可降低系统偏差，在K=1时轨迹缩减因子约为5.4×，即一条去噪轨迹可达到约五条原始轨迹取平均的重建精度；仅Noise2Noise模型的缩减因子为4.9×，优于参考监督基线（4.6×）和经典维纳滤波（3.2×）。这些结果表明，从重复的噪声测量中进行自监督学习，无需硬件修改即可支持更快的连续扫描THz-TDS。
英文摘要：
Terahertz time-domain spectroscopy (THz-TDS) based on air-plasma generation and balanced air-biased coherent detection offers gap-free broadband coverage, but individual continuous-scan traces are strongly affected by pulse-to-pulse fluctuations and electronic noise. Reaching a useful signal-to-noise ratio therefore requires averaging multiple traces, which directly increases measurement time. We propose a learned denoising approach that recovers high-quality THz waveforms from as few as one complete continuous delay sweep, referred to here as a single-scan trace. A compact one-dimensional residual U-Net is trained using two complementary strategies: a reference-supervised baseline that maps individual noisy traces to long-average reference waveforms, and a Noise2Noise approach that learns from pairs of independently acquired noisy traces without requiring a clean training target. Averaging the predictions of both models reduces systematic bias and yields a trace-reduction factor of approximately $5.4\times$ at $K=1$, meaning that one denoised trace achieves the reconstruction accuracy of averaging approximately five raw traces. The Noise2Noise model alone achieves $4.9\times$, outperforming both the reference-supervised baseline ($4.6\times$) and classical Wiener filtering ($3.2\times$). These results show that self-supervised learning from repeated noisy measurements can support faster continuous-scan THz-TDS without hardware modification.
