2020/11/30 by Heming Xia, Lijing Shao, Junjie Zhao +1
Computer Science · Earth and Planetary Sciences · Mathematics · Physics and Astronomy · #Artificial intelligence #Computer science #Convolutional neural network #Deep learning #Dropout (neural networks) #Gravitational wave #Machine learning #Normalization (sociology) #Pattern recognition (psychology) #Physics #Pulsars and Gravitational Waves Research #Seismic Imaging and Inversion Techniques #Seismic Waves and Analysis #Signal processing #Waveform #astro-ph.HE #cs.LG #gr-qc #stat.ML
paper · pdf · doi:10.1103/physrevd.103.024040
published as Phys. Rev. D 103, 024040 (2021) · 13 pages, 11 figures; accepted by PRD
arxiv created 2020/12/23 · openalex publication_date 2021/01/21 · arxiv updated 2021/01/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
In recent years, convolutional neural network (CNN) and other deep learning models have been gradually introduced into the area of gravitational-wave (GW) data processing. Compared with the traditional matched-filtering techniques, CNN has significant advantages in efficiency in GW signal detection tasks. In addition, matched-filtering techniques are based on the template bank of the existing theoretical waveform, which makes it difficult to find GW signals beyond theoretical expectation. In this paper, based on the task of GW detection of binary black holes, we introduce the optimization techniques of deep learning, such as batch normalization and dropout, to CNN models. Detailed studies of model performance are carried out. Through this study, we recommend to use batch normalization and dropout techniques in CNN models in GW signal detection tasks. Furthermore, we investigate the generalization ability of CNN models on different parameter ranges of GW signals. We point out that CNN models are robust to the variation of the parameter range of the GW waveform. This is a major advantage of deep learning models over matched-filtering techniques.