2025-09-04 カリフォルニア工科大学（Caltech）
Closeup photograph of LIGO, which uses strong lasers and mirrors to detect gravitational waves in the universe, generated by events like collisions and mergers of black holes.Credit: Caltech/MIT/LIGO Lab
＜関連情報＞
- https://www.caltech.edu/about/news/artificial-intelligence-helps-boost-ligo
- https://www.science.org/doi/10.1126/science.adw1291
ディープ・ループ・シェーピングを用いた重力波観測所の宇宙論的到達範囲の向上 Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping
Jonas Buchli, Brendan Tracey, Tomislav Andric, Christopher Wipf, […] , and The LIGO Instrument Team
Science Published:4 Sep 2025
DOI:https://doi.org/10.1126/science.adw1291
Editor’s summary
Gravitational wave detectors have revolutionized astrophysics by detecting black holes and neutron stars. Most signals are captured in the 30- to 2000-Hz range, and the lower 10- to 30-Hz band remains largely unexplored because of persistent low-frequency control noise that limits sensitivity. Enhancing this sensitivity could increase cosmological reach. Using nonlinear optimal control through reinforcement learning with a frequency-domain reward, Buchli et al. developed a method that effectively reduces control noise in the low-frequency band. This method was successfully implemented at the Laser Interferometer Gravitational-Wave Observatory (LIGO) in Livingston and the Caltech 40 Meter Prototype, achieving control noise levels on LIGO’s most demanding feedback control loop below the quantum noise, thus removing a critical obstacle to increased detector sensitivity. —Yury Suleymanov
Abstract
Improved low-frequency sensitivity of gravitational wave observatories would unlock study of intermediate-mass black hole mergers and binary black hole eccentricity and provide early warnings for multimessenger observations of binary neutron star mergers. Today’s mirror stabilization control injects harmful noise, constituting a major obstacle to sensitivity improvements. We eliminated this noise through Deep Loop Shaping, a reinforcement learning method using frequency domain rewards. We proved our methodology on the LIGO Livingston Observatory (LLO). Our controller reduced control noise in the 10- to 30-hertz band by over 30x and up to 100x in subbands, surpassing the design goal motivated by the quantum limit. These results highlight the potential of Deep Loop Shaping to improve current and future gravitational wave observatories and, more broadly, instrumentation and control systems.
