用神经网络快速生成高精度双黑洞引力波信号,兼顾速度与准确率。
A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms
- 两阶段训练:先用近似模型数据预训练,再用真实数值相对论数据微调。
- 在GPU上每秒生成百万个波形,平均失配度约10⁻⁴。
- 适合需要快速波形生成的引力波参数估计任务。
引力波近似模型对引力波天文学至关重要,可在无需昂贵数值相对论(NR)模拟的情况下覆盖双黑洞参数空间,用于推断或匹配滤波,但通常以牺牲一定精度换取计算效率。为减少这种权衡,可通过在NR波形空间内插构建数值相对论代理模型。本文提出一种基于神经网络的双阶段训练方法,即先在近似模型生成的波形上训练,再用真实NR数据进行微调,得到双阶段人工神经网络代理模型(DANSur)。该模型可实现快速且具有竞争力的波形生成,在单张GPU上生成数百万个波形耗时不足20毫秒,同时保持与真实NR波形的平均失配度约为10⁻⁴。该模型已集成至bilby框架,可用于参数估计任务。
原文摘要 · Abstract (English)
Gravitational-wave approximants are essential for gravitational-wave astronomy, allowing the coverage binary black hole parameter space for inference or match filtering without costly numerical relativity (NR) simulations, but generally trading some accuracy for computational efficiency. To reduce this trade-off, NR surrogate models can be constructed using interpolation within NR waveform space. We present a 2-stage training approach for neural network-based NR surrogate models. Initially trained on approximant-generated waveforms and then fine-tuned with NR data, these dual-stage artificial neural surrogate (\texttt{DANSur}) models offer rapid and competitively accurate waveform generation, generating millions in under 20ms on a GPU while keeping mean mismatches with NR around $10^{-4}$. Implemented in the \textsc{bilby} framework, we show they can be used for parameter estimation tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。