Rapid generation of fully relativistic extreme-mass-ratio-inspiral waveform templates for LISA data analysis

TL;DR

This paper introduces a novel method combining order-reduction and deep learning to rapidly generate highly accurate, fully relativistic gravitational waveforms for extreme-mass-ratio inspirals, enabling real-time data analysis for LISA.

Contribution

It presents the first efficient approach to produce full harmonic content waveforms in under one second, significantly advancing LISA data analysis capabilities.

Findings

Waveforms generated in under 1 second

Mismatch with reference waveforms is less than 5×10⁻⁴

Method enables real-time analysis for LISA data

Abstract

The future space mission LISA will observe a wealth of gravitational-wave sources at millihertz frequencies. Of these, the extreme-mass-ratio inspirals of compact objects into massive black holes are the only sources that combine the challenges of strong-field complexity with that of long-lived signals. Such signals are found and characterized by comparing them against a large number of accurate waveform templates during data analysis, but the rapid generation of such templates is hindered by computing the $\sim10^3$-$10^5$ harmonic modes in a fully relativistic waveform. We use order-reduction and deep-learning techniques to derive a global fit for these modes, and implement it in a complete waveform framework with hardware acceleration. Our high-fidelity waveforms can be generated in under $1\,\mathrm{s}$, and achieve a mismatch of $\lesssim 5\times 10^{-4}$ against reference waveforms that take $\gtrsim 10^4$ times longer. This marks the first time that analysis-length waveforms with full harmonic content can be produced on timescales useful for direct implementation in LISA analysis algorithms.