Predicting the motion of a high-Q pendulum subject to seismic perturbations using machine learning
arXiv:2301.07694 · doi:10.1063/5.0144593
Abstract
The seismically excited motion of high-Q pendula 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 1.4Hz that is driven by natural seismic activity. We achieve a reduction of the displacement power spectral density of 40dB at the resonant frequency 1.4Hz and 6dB at 11Hz. 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.
arXiv comment10 pages, 7 figures
References in corpus (20)
- Adam: A Method for Stochastic Optimization
- Recent Advances in Physical Reservoir Computing: A Review
- Time Series Forecasting With Deep Learning: A Survey
- Characterization of the LIGO detectors during their sixth science run
- Seismic isolation of Advanced LIGO: Review of strategy, instrumentation and performance
- Enhancing Gravitational-Wave Science with Machine Learning
- Machine-learning non-stationary noise out of gravitational wave detectors
- Subtraction of Newtonian Noise Using Optimized Sensor Arrays
- Image-based deep learning for classification of noise transients in gravitational wave detectors
- Terrestrial Gravity Fluctuations
- Noise Reduction in Gravitational-wave Data via Deep Learning
- Statistical Gravitational Waveform Models: What to Simulate Next?
- Active noise cancellation in a suspended interferometer
- Suspensions Thermal Noise in the LIGO Gravitational Wave Detector
- Global Feed-Forward Vibration Isolation in a km scale Interferometer
- Machine learning for gravitational-wave detection: surrogate Wiener filtering for the prediction and optimized cancellation of Newtonian noise at Virgo
- BAMBI: blind accelerated multimodal Bayesian inference
- Multivariate Classification with Random Forests for Gravitational Wave Searches of Black Hole Binary Coalescence
- Machine Learning Potential of a Single Pendulum
- A lower limit for Newtonian-noise models of the Einstein Telescope