Our novel Deep Loop Shaping method improves the control of gravitational wave observatories, helping astronomers better understand the dynamics and formation of the Universe.
To help astronomers study the most powerful processes taking place in the universe, our teams are using artificial intelligence to stabilize one of the most sensitive observing instruments ever built.
In a paper published today in Science, we present Shaping a deep loopan innovative artificial intelligence method that will unlock the next generation of gravitational wave science. Deep Loop Shaping reduces noise and improves control in the observatory's feedback system by helping stabilize components used to measure gravitational waves – tiny ripples in the fabric of space and time.
These waves are created by events such as neutron star collisions and black hole mergers. Our method will help astronomers collect the data necessary to understand the dynamics and formation of the Universe and better test fundamental theories of physics and cosmology.
We developed Deep Loop Shaping in collaboration with LIGO (Laser Interferometer Gravitational Wave Observatory) operated by Caltech, and GSSI (Gran Sasso Science Institute) and proved our method at the Livingston Observatory in Louisiana.
LIGO measures the properties and origins of gravitational waves with incredible accuracy. However, the slightest vibrations can disturb the measurements, even caused by waves crashing 100 miles off the Persian Gulf coast. To function, LIGO relies on thousands of control systems to keep each part in near-perfect alignment and adapts to environmental disturbances based on continuous feedback.
Deep Loop Shaping reduces the noise level in LIGO's most unstable and difficult feedback loop by a factor of 30 to 100, improving the stability of the interferometer's highly sensitive mirrors. Applying our method to all LIGO mirror control loops could help astronomers detect and collect much more detailed data on hundreds of other events each year.
In the future, Deep Loop Shaping could also be applied to many other engineering problems, including vibration damping, noise cancellation, and highly dynamic or unstable systems important in aerospace, robotics, and structural engineering.
