从后牛顿基线学习旋进-并合-铃振波形
Learning Inspiral-Merger-Ringdown Waveforms from a Post-Newtonian Baseline
浏览论文内容
中文总结 AI 辅助
提出一种机器学习驱动的波形建模方法，用Kolmogorov-Arnold网络从SXS波形学习残差修正，增强而非取代解析波形结构，在75个模拟上实现中位失配2.7×10⁻⁵。
中文摘要 AI 辅助
对完整的旋进-并合-铃振信号进行建模，需要将解析控制的旋进物理与数值相对论提供的非线性强场信息相结合。我们将超越解析旋进波形的数值相对论贡献表示为残差振幅和相位修正。保留前导阶频域振幅和3.5阶后牛顿TaylorF2相位，我们使用Kolmogorov-Arnold网络从SXS波形中学习这些残差修正。训练后，学习到的修正被存储为显式样条函数，因此波形评估不再需要网络本身。在从训练和模型选择中排除的75个模拟上，模型实现了中位平坦噪声失配为2.7×10⁻⁵。我们的结果展示了一种机器学习驱动的波形建模策略，其中数值相对论增强而非取代解析已知的波形结构。
英文摘要
Modeling the full inspiral-merger-ringdown signal requires combining analytically controlled inspiral physics with the nonlinear strong-field information supplied by numerical relativity. We represent the numerical relativity contribution beyond an analytic inspiral waveform as residual amplitude and phase corrections. Retaining the leading-order frequency-domain amplitude and the $3.5$ Post-Newtonian TaylorF2 phase, we use a Kolmogorov-Arnold network to learn these residual corrections from SXS waveforms. After training, the learned corrections are stored as explicit spline functions, so waveform evaluation no longer requires the network itself. On $75$ simulations excluded from training and model selection, the model achieves a median flat-noise mismatch of $2.7\times10^{-5}$. Our results demonstrate a machine learning driven waveform modeling strategy in which numerical relativity augments, rather than replaces, analytically known waveform structure.
发表机构
- University of Puerto Rico Mayagüez（波多黎各大学马亚圭兹分校）
- Saha Institute of Nuclear Physics（萨哈核物理研究所）
- Homi Bhabha National Institute（霍米·巴巴国立学院）
机构由 AI 辅助整理，请以论文原文为准。
