What question did this study set out to answer?

This research aims to explore the application of graph neural networks in simulating interferometer models.

December 22, 20250 citationsOpen Access

Graph Neural Networks for Interferometer Simulations

SKS. KannanJohn Deere (United States)PGP. GoodarziUniversity of California, Riverside EPEvangelos E. PapalexakisUniversity of California, Riverside

Key Points

This research aims to explore the application of graph neural networks in simulating interferometer models.
Introduced graph neural networks for simulating instrumentation design.
Conducted simulations for the Laser Interferometer Gravitational-Wave Observatory (LIGO).
Developed a dataset of high-fidelity optical physics simulations for interferometer topologies.
GNNs achieved runtimes 815 times faster than state-of-the-art simulation packages.
Accurately captured complex optical physics involved in interferometer simulations.

Abstract

In recent years, graph neural networks (GNNs) have shown tremendous promise in solving problems in high energy physics, materials science, and fluid dynamics. In this work, we introduce a new application for GNNs in the physical sciences: instrumentation design. As a case study, we apply GNNs to simulate models of the Laser Interferometer Gravitational-Wave Observatory (LIGO) and show that they are capable of accurately capturing the complex optical physics at play, while achieving runtimes 815 times faster than state of the art simulation packages. We discuss the unique challenges this problem provides for machine learning models. In addition, we provide a dataset of high-fidelity optical physics simulations for three interferometer topologies, which can be used as a benchmarking suite for future work in this direction.

Ask AI

Helpful

Bookmark

View Full Paper