AI finds new ways to observe the most extreme events in the universe

Researchers at the Max Planck Institute for the Science of Light (MPL) have been working on how an artificial intelligence system could explore an unimaginably vast space of possible designs to find entirely new solutions. The results were recently published in the journal Physical Review X.

More than a century ago, Einstein theoretically predicted gravitational waves. They could only be directly detected in 2016 because the development of the necessary detectors was extremely complex. Dr. Mario Krenn, head of the research group ›Artificial Scientist Lab‹ at MPL, in collaboration with the team of LIGO ("Laser Interferometer Gravitational-Wave Observatory"), who built those detectors successfully, has designed an AI-based algorithm called ›Urania‹ to design novel interferometric gravitational wave detectors. Interferometry describes a measurement method which uses the interference of waves, i.e. their superposition when they meet. Detector design requires optimizing both layout and parameters. The scientists have converted this challenge into a continuous optimization problem and solved it using methods inspired by modern machine learning. They have found many new experimental designs which outperform the best known next-generation detectors. These results have the potential to improve the range of detectable signals by more than an order of magnitude.

Nonconformist and creative: that's what Urania discovered

In the algorithm's solutions, the researchers rediscovered numerous known techniques. ›Urania‹ also proposed unorthodox designs which could reshape our understanding of detector technology. "After roughly two years of developing and running our AI algorithms, we discovered dozens of new solutions that seem to be better than experimental blueprints by human scientists. We asked ourselves what humans overlooked in comparison to the machine," says Krenn. The researchers expanded their scientific approach to understand the AI-discovered tricks, ideas, and techniques. Many of them are still completely alien to them. They have compiled 50 top-performing designs in a public ›Detector Zoo‹ and made them available to the scientific community for further research.

The recently published work shows that AI can uncover novel detector designs and inspire human researchers to explore new experimental and theoretical ideas. More broadly, it suggests that AI could play a major role in designing future tools for exploring the universe, from the smallest to the largest scales. "We are in an era where machines can discover new super-human solutions in science, and the task of humans is to understand what the machine has done. This will certainly become a very prominent part of the future of science," says Krenn.