First demonstration of neural sensing and control in a kilometer-scale gravitational wave observatory

TL;DR

This paper demonstrates the first successful use of neural networks for sensing and control in a large-scale gravitational wave observatory, improving alignment and sensitivity through deep learning techniques.

Contribution

It introduces a neural network-based approach for real-time sensing and control in a gravitational wave detector, combining CNN-LSTM and reinforcement learning methods.

Findings

Successful low-frequency control of the signal recycling mirror at GEO 600

Enhanced sensitivity through neural network-based alignment correction

Real-time sensing and control achieved with deep learning methods

Abstract

Suspended optics in gravitational wave (GW) observatories are susceptible to alignment perturbations, particularly slow drifts over time, due to variations in temperature and seismic levels. Such misalignments affect the coupling of the incident laser beam into the optical cavities, degrade both circulating power and optomechanical photon squeezing and thus decrease the astrophysical sensitivity to merging binaries. Traditional alignment techniques involve differential wavefront sensing using multiple quadrant photodiodes but are often restricted in bandwidth and are limited by the sensing noise. We present the first-ever successful implementation of neural network-based sensing and control at a gravitational wave observatory and demonstrate low-frequency control of the signal recycling mirror at the GEO 600 detector. Alignment information for three critical optics is simultaneously extracted from the interferometric dark port camera images via a CNN-LSTM network architecture and is then used for MIMO control using soft actor-critic-based deep reinforcement learning. Overall sensitivity improvement achieved using our scheme demonstrates deep learning's capabilities as a viable tool for real-time sensing and control for current and next-generation GW interferometers.