Predicting the motion of a high-Q pendulum subject to seismic perturbations using machine learning

• Published in: Applied physics letters Vol. 122; no. 25
• Main Authors: Heimann, Nicolas, Petermann, Jan, Hartwig, Daniel, Schnabel, Roman, Mathey, Ludwig
• Format: Journal Article
• Language: English
• Published: Melville American Institute of Physics 19.06.2023
• Subjects: Applied physics; Gravitational waves; Machine learning; Observatories; Pendulums; Perturbation; Power spectral density; Resonant frequencies; Seismic activity
• ISSN: 0003-6951; 1077-3118
• DOI: 10.1063/5.0144593

The seismically excited motion of a high-Q pendulum in gravitational-wave observatories sets a sensitivity limit to sub-audio gravitational-wave frequencies. Here, we report on the use of machine learning to predict the motion of a high-Q pendulum with a resonance frequency of 1.4 Hz that is driven by natural seismic activity. We achieve a reduction in the displacement power spectral density of 40 dB at the resonant frequency 1.4 Hz and 6 dB at 11 Hz. Our result suggests that machine learning is able to significantly reduce seismically induced test mass motion in gravitational-wave detectors in combination with corrective feed-forward techniques.