LIGO Hanford control room with monitoring displays

AI for Experimental Physics

Apply machine learning and control to complex experiments: faster lock acquisition, robust operation, automated diagnostics, and design optimization for precision instruments.

Image: Caltech/MIT/LIGO Lab

In 2025, a reinforcement-learning controller we designed was deployed at LIGO Livingston and reduced control noise by over 30× in the 10–30 Hz band — the frequency range critical for observing heavy black hole mergers. Published in Science, this result demonstrated that learned controllers can outperform decades of hand-tuned filter design on a running gravitational-wave detector.

This is one example of a broader program. We apply machine learning across the full instrument lifecycle: convolutional neural networks that clean nonlinear noise from detector data, compound neural networks that enable pre-merger early warning by mitigating non-stationary backgrounds, and a gradient-based design algorithm that autonomously discovers detector topologies no human would consider.

We emphasize deployability: our tools run in real time on detector hardware, not just in offline analysis. An AI controller that crashes during an observing run is worse than no AI at all, so we invest in validation, uncertainty quantification, and graceful degradation before any model touches the instrument.

Deep Loop Shaping (Science, 2025): Reinforcement-learning agents optimized the mirror stabilization controller at LIGO Livingston, reducing control noise by 30–100× in the 10–30 Hz band. The learned controller surpassed quantum-noise design goals and was demonstrated on the live detector in 2024.
Digital Discovery (Physical Review X, 2025): The Urania algorithm — gradient-based optimization over a universal interferometer model — autonomously discovered 50+ detector topologies that outperform human designs by up to 50-fold in observable volume, uncovering new physics ideas at their core.

Selected Publications

Key papers on AI-driven control, design optimization, and noise reduction for precision experiments.

View all publications →