AI Unveils New Laws of Nature in Dusty Plasma Using Neural Network and 3D Particle Tracking

Physicists have taken a major step toward using AI not just to analyze data, but to uncover entirely new laws of nature. By combining a specially designed neural network with precise 3D tracking of particles in a dusty plasma—a strange “fourth state of matter” found from space to wildfires—the team revealed hidden patterns in how particles interact. Their model captured complex, one-way (non-reciprocal) forces with over 99% accuracy and even overturned long-held assumptions about how these forces behave.

The findings, published in PNAS, come from a collaboration between experimental and theoretical physicists at Emory University. Their approach uses a machine-learning method to identify surprising new twists on the non-reciprocal forces governing a many-body system. Unlike typical AI applications that serve as data processing or predictive tools, this method is designed to discover new physical laws governing the natural world.

Justin Burton, an Emory professor of experimental physics and senior co-author of the paper, said, “We showed that we can use AI to discover new physics. Our AI method is not a black box: we understand how and why it works. The framework it provides is also universal. It could potentially be applied to other many-body systems to open new routes to discovery.”

Ilya Nemenman, an Emory professor of theoretical physics and co-senior author of the paper, added, “We can describe these forces with an accuracy of more than 99%. What’s even more interesting is that we show that some common theoretical assumptions about these forces are not quite accurate. We’re able to correct these inaccuracies because we can now see what’s occurring in such exquisite detail.”

The Burton lab developed techniques to track the 3D motion of individual particles in a laboratory dusty plasma. Running experiments allowed the researchers to validate AI inferences. This combination of custom neural network architecture and laboratory data enabled the team to learn the external forces and unknown particle interactions directly from experimental observations.

Dusty plasma, consisting of ionized gas with suspended dust particles, is found in environments ranging from Saturn’s rings to Earth’s ionosphere and even in wildfires. By revealing previously hidden interaction patterns in this complex system, the research demonstrates how AI can serve as a tool for scientific discovery beyond traditional data analysis, with potential applications across physics and biology.