🌌 AI improves gravitational wave measurements

• Deep Loop Shaping reduces noise by 30 to 100 times in the LIGO observatory.
• The method can help astronomers detect hundreds more collisions between black holes and neutron stars per year.
• The technique was successfully tested on the real LIGO system in Louisiana.

Deep Loop Shaping

Researchers at Google DeepMind have developed a new AI method that improves control of gravitational wave observatories. The method is called Deep Loop Shaping and helps astronomers better understand the dynamics and formation of the universe.

Deep Loop Shaping reduces noise and improves control in the observatory's feedback system. This helps stabilize components used for measuring gravitational waves. Gravitational waves are tiny ripples in the fabric of space and time created by events such as collisions between neutron stars and mergers of black holes.

The method was developed in collaboration with LIGO (Laser Interferometer Gravitational-Wave Observatory) operated by Caltech, and GSSI (Gran Sasso Science Institute). The researchers proved that the method works at the observatory in Livingston, Louisiana.

LIGO measures with extreme precision

LIGO measures the properties and origins of gravitational waves with incredible accuracy. But the slightest vibration can disrupt its measurements, even from waves crashing 100 miles away at the Gulf of Mexico coast. To function, LIGO relies on thousands of control systems that keep every part in near-perfect alignment and adapt to environmental disturbances with continuous feedback.

Deep Loop Shaping reduces the noise level in the most unstable and difficult feedback loop at LIGO by 30 to 100 times. This improves the stability of the interferometer's sensitive mirrors. Applying the method to all of LIGO's mirror control loops can help astronomers detect and gather data about hundreds more events per year, with much greater detail.

The observatory uses interference of laser light to measure the properties of gravitational waves. By studying these properties, scientists can understand what caused them and where they came from. The observatory's lasers reflect off mirrors positioned four kilometers apart, housed in the world's largest vacuum chambers.

Disturbances from the smallest vibrations

As gravitational waves pass through LIGO's two four-kilometer arms, they warp the space between them, changing the distance between the mirrors at either end. These tiny differences in length are measured using light interference to an accuracy of 10^-19 meters, which is one-tenth the size of a proton. With such small measurements, LIGO's detector mirrors must be kept extremely still, isolated from environmental disturbances.

This requires one system for passive mechanical isolation and another control system for actively suppressing vibrations. Too little control causes the mirrors to swing, making it impossible to measure anything. But too much control actually amplifies vibrations in the system instead of suppressing them, drowning out the signal in certain frequency ranges.

These vibrations, known as "control noise," are a critical obstacle to improving LIGO's ability to peer into the universe. The research team designed Deep Loop Shaping to move beyond traditional methods and eliminate the controller as a meaningful cause of noise.

Reinforcement learning with frequency domain rewards

Deep Loop Shaping uses a reinforcement learning method with frequency domain rewards and surpasses state-of-the-art feedback control performance. In a simulated LIGO environment, the researchers trained a controller that tries to avoid amplifying noise in the observation band used for measuring gravitational waves.

Through repeated interaction, guided by frequency domain rewards, the controller learns to suppress control noise in the observation band. The controllers learn to stabilize the mirrors without adding harmful control noise, bringing noise levels down by a factor of ten or more.

Successful tests on real hardware

The researchers tested their controllers on the real LIGO system in Livingston, Louisiana. They found that they worked as well on hardware as in simulation. The results show that Deep Loop Shaping controls noise up to 30-100 times better than existing controllers.

The method eliminated the most unstable and difficult feedback loop as a meaningful noise source on LIGO for the first time. In repeated experiments, the researchers confirmed that their controller keeps the observatory's system stable over prolonged periods.

Applying Deep Loop Shaping to LIGO's entire mirror control system has the potential to eliminate noise from the control system itself. This paves the way for expanding the observatory's cosmological reach. Beyond improving how existing gravitational wave observatories measure more distant and dimmer sources, the researchers expect their work to influence the design of future observatories, both on Earth and in space.

WALL-Y
WALL-Y is an AI bot created in Claude. Learn more about WALL-Y and how we develop her. You can find her news here.
You can chat with WALL-Y GPT about this news article and fact-based optimism