Astronomers use AI to precisely calculate cosmos’s ‘settings’

The standard model of the universe banks on just six numbers. Using a fresh approach driven by AI (artificial intelligence), scientists at the Flatiron Institute and their colleagues pulled out information hidden in the distribution of galaxies for approximation of the values of five of these so-called cosmological parameters with incredible accuracy.

The results were a substantial improvement over the values produced by earlier approaches. Compared to conventional methods employing the same galaxy data, the approach yielded < half the uncertainty for the parameter describing the clumpiness of the cosmos’s matter. The artificial intelligence powered method also closely agreed with approximations of the cosmological parameters based on observations of other phenomena, for instance the universe’s oldest light. The researchers present their approach, SimBIG (the Simulation-Based Inference of Galaxies), in a string of recent papers, including a fresh study published August 21 in Nature Astronomy.

Producing tighter constraints on the parameters while using the same data will be vital for studying everything from the composition of dark matter to the nature of the dark energy driving the cosmos apart, states study co-author Shirley Ho (a group leader at the Flatiron Institute’s Center for Computational Astrophysics in New York City). That’s particularly true as fresh surveys of the cosmos come online over the ensuing few years, she says.

“Each of these surveys costs hundreds of millions to billions of dollars,” Ho states. “The main reason these surveys exist is because we want to understand these cosmological parameters better. So if you think about it in a very practical sense, these parameters are worth tens of millions of dollars each. You want the best analysis you can to extract as much knowledge out of these surveys as possible and push the boundaries of our understanding of the universe.”

The six cosmological parameters describe the amount of ordinary matter, dark energy and dark matter in the cosmos and the conditions following the Big Bang, for instance the opacity of the newborn cosmos as it cooled and whether mass in the universe is spread out or in big clumps. The parameters “are essentially the ‘settings’ of the universe that determine how it operates on the largest scales,” states Liam Parker (co-author of the study and a research analyst at the Center for Computational Astrophysics).

One of the most central ways astrophysicists calculate the parameters is by studying the clustering of the cosmos’s galaxies. Earlier, these analyses only looked at the large-scale distribution of galaxies. “We haven’t been able to go down to small scales,” says ChangHoon Hahn (an associate research scholar at Princeton University and lead author of the study). “For a couple of years now, we’ve known that there’s additional information there; we just didn’t have a good way of extracting it.”