Microseismic Noise Mitigation with Machine Learning for Advanced LIGO
LIGO Laboratory, Massachusetts Institute of Technology(麻省理工学院LIGO实验室);Department of Physics, MIT(麻省理工学院物理系);Department of Physics, Stanford University(斯坦福大学物理系);Trinity College(三一学院);LIGO Laboratory, California Institute of Technology(加州理工学院LIGO实验室);School of Physics and Astronomy, Tel Aviv University(特拉维夫大学物理与天文学学院)
Christina Reissel, Devin Lai, Shivanshu Dwivedi, Edgard Bonilla, Claudia Geer, Christopher Wipf, Richard Mittleman, Philip Harris, Eyal Schwartz, Dovi Poznanski… 展开作者
Christina Reissel, Devin Lai, Shivanshu Dwivedi, Edgard Bonilla, Claudia Geer, Christopher Wipf, Richard Mittleman, Philip Harris, Eyal Schwartz, Dovi Poznanski, Brian Lantz, Erik Katsavounidis
The unprecedented sensitivity of the Laser Interferometer Gravitational-Wave Observatory, which enables the detection of distant astrophysical sources, also renders the detectors highly susceptible to low-frequency ground motion. Persistent microseisms in the 0.1-0.3 Hz band couple into the instruments, degrade lock stability, and contribute substantially to detector downtime during observing runs. The multi-stage seismic isolation system has achieved remarkable success in mitigating such disturbances through active feedback control, yet residual platform motion remains a key factor limiting low-frequency sensitivity and duty cycle. Further reduction of this residual motion is therefore critical for improving the long-term stability and overall astrophysical reach of the observatories.
In this work, we develop a data-driven approach that uses machine learning to model and suppress residual seismic motion within the isolation system. Ground and platform sensor data from the detectors are used to train a neural network that predicts platform motion driven by microseismic activity. When incorporated into the control scheme, the network's predictions yield up to an order-of-magnitude reduction in residual motion compared to conventional linear filtering methods, revealing that nonlinear couplings play a significant role in limiting current isolation performance. These results demonstrate that machine-learning-based control can provide a powerful new pathway for enhancing active seismic isolation, improving lock robustness, and extending the low-frequency observational capabilities of gravitational-wave detectors.
GW-YOLO: Multi-transient segmentation in LIGO using computer vision
LIGO Laboratory, Massachusetts Institute of Technology(麻省理工学院 LIGO 实验室);University of California, Riverside(加州大学河滨分校);Inter-University Centre for Astronomy and Astrophysics(天文与天体物理跨大学中心)
GSpyNetTreeS: a machine learning solution for glitch localization in time and frequency
The University of British Columbia(不列颠哥伦比亚大学);Indian Institute of Technology Kharagpur(印度理工学院卡拉格普尔分校);Massachusetts Institute of Technology(麻省理工学院);University of British Columbia(不列颠哥伦比亚大学)
GSpyNetTreeS基于You Only Look Once算法,实现探测器噪声瞬变的自动检测、分类与时频定位,提升引力波事件验证效率。