AI and extreme scale computing to learn and infer the physics of higher order gravitational wave modes of quasi-circular, spinning, non-precessing black hole mergers

• DOI: 10.1016/j.physletb.2022.137505
• Publication Date: 2022-10-15T03:33:05Z
• Authors: Asad Khan; E.A. Huerta; Prayush Kumar
• Keywords: FOS: Computer and information sciences; I.2; Higher-order waveform modes; Black holes; Computer Science - Artificial Intelligence; Physics; QC1-999; FOS: Physical sciences; General Relativity and Quantum Cosmology (gr-qc); 68T10, 85-08, 83C35, 83C57; 01 natural sciences; General Relativity and Quantum Cosmology; Artificial Intelligence (cs.AI); AI; 0103 physical sciences; High performance computing; Astrophysics - Instrumentation and Methods for Astrophysics; Instrumentation and Methods for Astrophysics (astro-ph.IM)

We use artificial intelligence (AI) to learn and infer the physics of higher order gravitational wave modes of quasi-circular, spinning, non precessing binary black hole mergers. We trained AI models using 14 million waveforms, produced with the surrogate model NRHybSur3dq8, that include modes up to $\ell \leq 4$ and $(5,5)$, except for $(4,0)$ and $(4,1)$, that describe binaries with mass-ratios $q\leq8$, individual spins $s^z_{\{1,2\}}\in[-0.8, 0.8]$, and inclination angle $θ\in[0,π]$.Our probabilistic AI surrogates can accurately constrain the mass-ratio, individual spins, effective spin, and inclination angle of numerical relativity waveforms that describe such signal manifold. We compared the predictions of our AI models with Gaussian process regression, random forest, k-nearest neighbors, and linear regression, and with traditional Bayesian inference methods through the PyCBC Inference toolkit, finding that AI outperforms all these approaches in terms of accuracy, and are between three to four orders of magnitude faster than traditional Bayesian inference methods. Our AI surrogates were trained within 3.4 hours using distributed training on 1,536 NVIDIA V100 GPUs in the Summit supercomputer.<br/>22 pages, 12 figures<br/>