Scientists have harnessed the power of artificial intelligence to unlock secrets hidden within the densest objects in the universe.
They can now infer the quantum interactions of protons and neutrons directly from space-based observations.
It can happen through the data analyses of “multimessenger” events, such as gravitational waves from colliding neutron stars and X-ray emissions captured by NASA’s NICER telescope.
These algorithms act as high-speed stand-ins, quickly translating star data into a clear picture of how subatomic particles interact.
“This research represents the first time in the field that we’ve been able to robustly connect the macroscopic and microscopic realms and infer the interactions among neutrons and protons directly from astrophysical data,” said Ingo Tews, Los Alamos physicist.
“Using artificial intelligence and machine learning, our framework made it possible to take data from remarkable astrophysical phenomena and infer the complicated physics of nuclear forces,” Tews added.
The AI advantage
Imagine matter so dense that a teaspoon would weigh billions of tons. This is the reality inside a neutron star.
Despite their immense mass — often twice that of the Sun — these stellar remnants are no bigger than a city, making them the ultimate laboratory for studying matter under extreme pressure.
Here, the fundamental force known as the strong force, which binds protons and neutrons together in atomic nuclei, rules supreme.
But understanding how this force behaves at such crushing densities has long been a “computationally intractable” puzzle for physicists. Standard models could require thousands of processing hours just to reach a single solution.
This is where the innovative application of artificial intelligence changes the game.
The research team built an AI framework that acts as a “superfast surrogate” for these complex calculations.
This AI uses an understanding of underlying quantum physics to deliver solutions for dense-matter properties almost instantaneously.
Analyzing gravitational waves from colliding stars and X-ray emissions from NASA’s telescopes, the team can pinpoint the exact strength of the strong nuclear force that binds protons and neutrons together.
“Our approach opens a new window into the strong-force physics of neutrons and protons and its effects on neutron stars,” said Isak Svensson, scientist at the Technical University of Darmstadt and a co-lead author. “Our framework allows us to go from neutron star observations to the interactions in dense matter.”
Solving complex calculations
This dual-algorithm approach uses one model grounded in quantum physics to solve for dense-matter properties and a neural network to predict the star’s physical characteristics, such as size and squishiness (tidal deformations).
“The tools we developed performed remarkably well — much better than we anticipated,” said Rahul Somasundaram, Los Alamos scientist and a co-lead author.
“For astrophysical data from recent events, our framework offers constraints that are consistent with what we know from terrestrial experiments, albeit with larger uncertainties. For future observations by next-generation detectors, such as Cosmic Explorer, our approach will provide even better constraints that will be really powerful,” Somasundaram explained.
The team can now go directly from observing the universe’s grandest spectacles to inferring the complex physics of interactions at the quantum level.
This could allow scientists to hunt for exotic matter, such as “soups” of quarks and gluons, and to provide rare insight into three-body forces — the mysterious interactions that occur only when three or more particles are squeezed tightly together.
Essentially, these cosmic giants are helping us solve the most complex puzzles of the subatomic world that cannot be tested on Earth.
The findings were published in Nature Communications.