Generating Higher Order Modes from Binary Black Hole mergers with Machine Learning

• DOI: 10.48550/arxiv.2402.06587
• Publication Date: 2024-02-09
• Authors: Tim Grimbergen; S. Schmidt; C. V. Kalaghatgi; Chris Van Den Broeck
• Keywords: 0103 physical sciences; FOS: Physical sciences; General Relativity and Quantum Cosmology (gr-qc); 01 natural sciences; General Relativity and Quantum Cosmology

We introduce a machine learning model designed to rapidly and accurately predict the time domain gravitational wave emission of non-precessing binary black hole coalescences, incorporating effects higher order modes multipole expansion waveform. Expanding on our prior work, we decompose each mode by amplitude phase reduce dimensionality using principal component analysis. An ensemble artificial neural networks is trained learn relationship between orbital parameters low-dimensional representation mode. train $\sim 10^5$ signals with mass ratio $q \in [1,10]$ dimensionless spins $\chi_i [-0.9, 0.9]$, generated state-of-the-art approximant SEOBNRv4HM. find that it achieves median faithfulness $10^{-4}$ averaged across parameter space. show generates single waveform two orders magnitude faster than training model, speed up increasing when waveforms are in batches. This framework entirely general can be applied any other capable generating from aligned spin circular binaries, possibly modes.