Identification of Lensed Gravitational Waves with Deep Learning

Similar to light, gravitational waves (GWs) can be lensed. Such lensing phenomena magnify the waves, create multiple images observable as repeated events, and superpose several waveforms together, inducing potentially discernible patterns on waves. In particular, when lens is small, ≲105 M⊙, it produce lensed with time delays shorter than typical gravitational-wave signal length that conspire together form "beating patterns." We present a proof-of-principle study utilizing deep learning for identification of such signature. bring excellence state-of-the-art models at recognizing foreground objects from background noise identifying GWs noisy spectrograms. assume mass around 103–105 which order milliseconds between two GWs. discuss feasibility distinguishing unlensed ones estimating physical parameters. The suggested method may interest more complicated configurations we do not have accurate waveform templates.