论文标题
使用贝叶斯神经网络检测引力波
Detection of Gravitational Waves Using Bayesian Neural Networks
论文作者
论文摘要
我们提出了一个新的贝叶斯神经网络模型，不仅在重力波（GW）的观察数据中检测紧凑型二元合并的事件，而且还确定了包括灵感阶段的事件持续时间的全长。这是通过将贝叶斯方法纳入CLDNN分类器来实现的，CLDNN分类器将卷积神经网络（CNN）和长期短期记忆复发性神经网络（LSTM）集成在一起。我们的模型成功地检测了Ligo Livingston O2数据中的所有七个BBH事件，其GW波形的周期正确标记了。贝叶斯方法进行不确定性估计的能力使新定义的“意识”状态可以识别出可能存在未知类型的信号，否则在非山地模型中被拒绝。这样的数据块标记为意识状态，就可以进一步研究而不是忽略。具有40,960个培训样本的性能测试，与512个8秒的真实噪声和各种最佳信号信号的模拟信号$ 0 \ leqρ_\ text {opt} \ leq 18 $混合在一起，我们的型号表明我们的型号表明我们的型号在$ρ_\ pext} $ pext} $ $ pext}时识别90％的事件，$ 5 $（$）$（100 $）\ $（100 $）当$ρ_\ text {opt}> 8 $时，标签超过95％的波形周期。峰信号的到来和使用标记的相关波形周期生成警报之间的延迟仅为中等GPU的个人计算机上的未优化代码约20秒。这使我们的模型成为了几乎实时检测的可能性，并在使用最先进的HPC上对更大的数据集进行了更深入的培训时，可以预测合并事件。
We propose a new model of Bayesian Neural Networks to not only detect the events of compact binary coalescence in the observational data of gravitational waves (GW) but also identify the full length of the event duration including the inspiral stage. This is achieved by incorporating the Bayesian approach into the CLDNN classifier, which integrates together the Convolutional Neural Network (CNN) and the Long Short-Term Memory Recurrent Neural Network (LSTM). Our model successfully detect all seven BBH events in the LIGO Livingston O2 data, with the periods of their GW waveforms correctly labeled. The ability of a Bayesian approach for uncertainty estimation enables a newly defined `awareness' state for recognizing the possible presence of signals of unknown types, which is otherwise rejected in a non-Bayesian model. Such data chunks labeled with the awareness state can then be further investigated rather than overlooked. Performance tests with 40,960 training samples against 512 chunks of 8-second real noise mixed with mock signals of various optimal signal-to-noise ratio $0 \leq ρ_\text{opt} \leq 18$ show that our model recognizes 90% of the events when $ρ_\text{opt} >7$ (100% when $ρ_\text{opt} >8.5$) and successfully labels more than 95% of the waveform periods when $ρ_\text{opt} >8$. The latency between the arrival of peak signal and generating an alert with the associated waveform period labeled is only about 20 seconds for an unoptimized code on a moderate GPU-equipped personal computer. This makes our model possible for nearly real-time detection and for forecasting the coalescence events when assisted with deeper training on a larger dataset using the state-of-art HPCs.
