THOR AI stuns scientists by solving century-old Physics problem in seconds

What took scientists a century to solve a 100-year-old Physics related mystery, AI has solved it in seconds.

Researchers from the University of New Mexico and Los Alamos National Laboratory have developed the THOR AI (Tensors for High-dimensional Object Representation) framework that solves the impossible tasks of calculating configurational integrals in statistical physics.

Configurational integrals are used to predict how different materials predict under various pressures and temperatures.

“Traditionally, solving the configurational integral directly has been considered impossible because the integral often involves dimensions on the order of thousands. Classical integration techniques would require computational times exceeding the age of the universe, even with modern computers,” Dimiter Petsev, a professor in the UNM Department of Chemical and Biological Engineering, said.

In a recent breakthrough, AI framework used tensor train cross interpolation to break massive and high-dimensional datasets into smaller and manageable pieces.

“Tensor network methods, however, offer a new standard of accuracy and efficiency against which other approaches can be benchmarked,” he added.

The researchers also developed a specialized version of the method, which specializes in detecting key crystal symmetries within materials in the matter of seconds.

The team tested THOR AI on several materials systems, including metals such as copper, noble gases under extreme pressure.

According to findings published in Physical Review Materials, THOR AI performed 400 times faster than traditional simulations without compromising accuracy.

THOR AI framework also combines tensor networks with modern machine learning models, allowing it to assess the materials under a wide variety of conditions.

Given its high efficiency, according to researchers the AI could become a valuable tool to solve mysteries related to physics and chemistry.

Duc Truong, Los Alamos scientist and lead author of the study, said “THOR AI opens the door to faster discoveries and a deeper understanding of materials.”