DeepMind's Deep Loop Shaping cuts LIGO control noise 30–100×
In Science (Sept 2025), DeepMind, LIGO/Caltech and GSSI reported an RL control method trained with frequency-domain rewards. Tested on hardware at LIGO Livingston, it reduced control noise in the 10–30 Hz band by more than 30×, and up to 100× in sub-bands, beating the design goal.
Key facts
- >30× noise reduction in the 10–30 Hz observation band (up to 100× in sub-bands)
- Demonstrated on LIGO Livingston hardware
- Could let LIGO detect more and heavier black-hole mergers and intermediate-mass black holes
Science result
- Field
- physics / gravitational-wave detection / control
- Problem
- Low-frequency control noise limiting LIGO's sensitivity
- Result
- Learned mirror-control policy reducing control noise by one to two orders of magnitude on real hardware.
- AI system
- Deep Loop Shaping (RL)
- Human role
- Human-designed; tested with LIGO engineers
- Verification
- Peer-reviewed in Science; hardware demonstration
- Status
- confirmed
What happened
An RL controller learned to stabilise LIGO's mirrors while injecting far less noise into the frequencies where gravitational waves are measured.
Why it matters
It extends the reach of one of physics' most sensitive instruments without new hardware.
Changelog
- 2026-09-29: created
Related events
Sources (2)
- paperImproving cosmological reach of a gravitational wave observatory using Deep Loop Shaping (Science)
- pressCaltech: Artificial intelligence helps boost LIGO
id: 2025-09-04-deepmind-ligo-deep-loop-shaping · updated 2026-09-29 · open in the interactive timeline