Deep learning model on gravitational waveforms in merging and ringdown phases of binary black hole coalescences

The waveform templates of the matched filtering-based gravitational-wave search ought to cover wide range parameters for prosperous detection. Numerical relativity (NR) has been widely accepted as most accurate method modeling waveforms. Still, it is well-known that NR typically requires a tremendous amount computational costs. In this paper, we demonstrate proof-of-concept novel deterministic deep learning (DL) architecture can generate gravitational waveforms from merger and ringdown phases non-spinning binary black hole coalescence. Our model takes ${\cal O}$(1) seconds generating approximately $1500$ with 99.9\% match on average one state-of-the-art approximants, effective-one-body. We also perform filtering DL-waveforms find recover event time injected signals.