5–8 May 2026
CERN
Europe/Zurich timezone

From Post Hoc Subtraction to Source Suppression: ML Noise Mitigation in Advanced LIGO

7 May 2026, 15:20
20m
40/S2-A01 - Salle Anderson (CERN)

40/S2-A01 - Salle Anderson

CERN

95
Show room on map
Talk AI for Detector Operations AI for detector operations

Speaker

Christina Reissel (Massachusetts Inst. of Technology (US))

Description

We present our work on machine learning for noise mitigation in Advanced LIGO that moves from software denoising of the strain channel to suppression of disturbances at their source within the detector control system.
Using Coherence DeepClean, we perform coherence-based witness-channel selection followed by machine-learning regression to subtract linear and nonlinear noise couplings from the gravitational-wave readout after they enter the strain data. This software denoising approach has yielded measurable sensitivity gains, including a 4.3% improvement in astrophysical sensitive volume.
We extend the same data-driven philosophy upstream to the seismic isolation system, where neural-network models predict residual platform motion induced by persistent microseismic activity in the 0.1–0.3 Hz band. In contrast to post hoc subtraction, this method targets the disturbance before it propagates through the instrument, enabling direct suppression of motion at the source. Our results suggest that, if integrated into the control system, the method could offer up to an order-of-magnitude reduction in residual motion compared to conventional linear filtering.
Looking ahead, we are exploring reinforcement learning for increasingly autonomous control architectures. Together, our results outline a path toward autonomous machine-learning systems for improving detector stability, low-frequency sensitivity, and astrophysical reach.

Author

Christina Reissel (Massachusetts Inst. of Technology (US))

Co-authors

Brian Lantz (Stanford University) Christopher Wipf (Caltech) Claudia Geer (Trinity College) Devin Lai (Stanford University) Dovi Poznanski (Tel Aviv University) Edgard Bonilla (Stanford University) Erik Katsavounidis (MIT) Eyal Schwartz (Trinity College) Michael Coughlin (University of Minnesota) Muhammed Saleem (University of Texas, Austin) Philip Coleman Harris (Massachusetts Inst. of Technology (US)) Richard Mittleman (MIT) Shivanshu Dwivedi (Trinity College) Siddharth Soni (University of California, Riverside)

Presentation materials