A new AI-powered method is changing how scientists measure the universe. Developed by researchers at the Flatiron Institute and their partners, this technique offers a far more accurate way to determine the cosmos’ key properties.

The approach, known as Simulation-Based Inference of Galaxies (SimBIG), pulls hidden clues from galaxy patterns. It goes beyond older techniques by uncovering information that was previously out of reach.

Using AI, the team cut uncertainty in critical parameters—like how clumpy matter is in the universe—to less than half. These results match closely with other cosmic measurements, including the light from the universe’s earliest moments.