Compact Binary Systems Waveform Generation with Generative Pre-trained Transformer
This work addresses data processing and waveform complexity issues in space-based gravitational wave detection, offering a novel deep learning approach for the astrophysics community, though it is incremental as it applies an existing transformer method to a new domain.
The paper tackles the challenge of generating gravitational wave waveforms for compact binary systems, which is difficult due to detector response and time-delay interferometry complexity, by proposing CBS-GPT, a pre-trained transformer model that achieves prediction accuracies up to 99% for massive black hole binaries and galactic binaries, and 91% for extreme mass-ratio inspirals.
Space-based gravitational wave (GW) detection is one of the most anticipated GW detection projects in the next decade, which promises to detect abundant compact binary systems. At present, deep learning methods have not been widely explored for GW waveform generation and extrapolation. To solve the data processing difficulty and the increasing waveform complexity caused by the detector's response and second-generation time-delay interferometry (TDI 2.0), an interpretable pre-trained large model named CBS-GPT (Compact Binary Systems Waveform Generation with Generative Pre-trained Transformer) is proposed. For compact binary system waveforms, three models were trained to predict the waveforms of massive black hole binaries (MBHB), extreme mass-ratio inspirals (EMRIs), and galactic binaries (GB), achieving prediction accuracies of at most 99%, 91%, and 99%, respectively. The CBS-GPT model exhibits notable generalization and interpretability, with its hidden parameters effectively capturing the intricate information of waveforms, even with the complex instrument response and a wide parameter range. Our research demonstrates the potential of large models in the GW realm, opening up new opportunities and guidance for future researches such as complex waveforms generation, gap completion, and deep learning model design for GW science.