Artificial intelligence discovers alternative physics

Latent nestings of our frame colored by physical state variables. Credit: Boyuan Chen/Columbia Engineering

A new[{” attribute=””>Columbia University AI program observed physical phenomena and uncovered relevant variables—a necessary precursor to any physics theory. But the variables it discovered were unexpected.

Energy, Mass, Velocity. These three variables make up Einstein’s iconic equation E=MC2. But how did Albert Einstein know about these concepts in the first place? Before understanding physics you need to identify relevant variables. Not even Einstein could discover relativity without the concepts of energy, mass, and velocity. But can variables like these be discovered automatically? Doing so would greatly accelerate scientific discovery.

This is the question that Columbia Engineering researchers posed to a new artificial intelligence program. The AI program was designed to observe physical phenomena through a video camera and then try to search for the minimal set of fundamental variables that fully describe the observed dynamics. The study was published in the journal Nature Computational Science on July 25.


The image shows a chaotic dynamic swing system in motion. Our work aims to identify and extract the minimum number of state variables needed to describe such a system directly from high-dimensional video sequences. Credit: Yinuo Qin/Columbia Engineering

The scientists began by feeding the system raw video footage of physical phenomena whose solution they already knew. For example, they fed a video of a swinging double pendulum known to have exactly four “state variables” – the angle and angular velocity of each of the two arms. After several hours of analysis, the AI ​​released its answer: 4.7.

“We thought that answer was close enough,” said Hod Lipson, director of the Mechanical Engineering Department’s Creative Machines Lab, where the work was primarily done. “Especially since all the AI ​​had access to raw video footage, without any knowledge of physics or geometry. But we wanted to know what the variables really were, not just how many.”

Next, the researchers proceeded to visualize the actual variables identified by the program. Extracting the variables themselves was difficult because the program cannot describe them in an intuitive way that would be understandable to humans. After some research, it turned out that two of the variables chosen by the program correspond loosely to the angles of the arms, but the other two remain a mystery.

“We tried to correlate the other variables with everything we could think of: angular and linear velocities, kinetic and potential energy, and various combinations of known quantities,” explained Boyuan Chen PhD ’22, now assistant professor at Duke University, which led the work. “But nothing seemed to fit perfectly.” The team was confident that the AI ​​had found a valid set of four variables because it made good predictions, “but we don’t yet understand the mathematical language it speaks,” he explained.


Boyuan Chen explains how a new AI program observed physical phenomena and discovered relevant variables, a necessary precursor to any physical theory. Credit: Boyuan Chen/Columbia Engineering

After validating a number of other physical systems with known solutions, the scientists grabbed videos of systems for which they did not know the explicit answer. One such video featured an “air dancer” waving in front of a local used car park. After several hours of analysis, the program returned 8 variables. Similarly, a video of a lava lamp also produced 8 eight variables. When they provided a video clip of the flames from a holiday fireplace loop, the program returned 24 variables.

A particularly interesting question was whether the set of variables was unique for each system or whether a different set was produced each time the program restarted. “I always wondered if we encountered an intelligent extraterrestrial race, would they have discovered the same physical laws as us, or could they describe the universe in a different way?” said Lipson. “Perhaps some phenomena seem enigmatically complex because we are trying to understand them using the wrong set of variables.”

In the experiments, the number of variables was the same each time the AI ​​restarted, but the specific variables were different each time. So yes, there are indeed alternative ways of describing the universe and it is quite possible that our choices are not perfect.

According to the researchers, this type of AI can help scientists uncover complex phenomena for which theoretical understanding does not keep up with the deluge of data – fields ranging from biology to cosmology. “Although we used video data in this work, any type of array data source could be used – radar arrays or[{” attribute=””>DNA arrays, for example,” explained Kuang Huang PhD ’22, who coauthored the paper.

The work is part of Lipson and Fu Foundation Professor of Mathematics Qiang Du’s decades-long interest in creating algorithms that can distill data into scientific laws. Past software systems, such as Lipson and Michael Schmidt’s Eureqa software, could distill freeform physical laws from experimental data, but only if the variables were identified in advance. But what if the variables are yet unknown?


Hod Lipson explains how the AI ​​program was able to discover new physical variables. Credit: Hod Lipson/Columbia Engineering

Lipson, who is also the James and Sally Scapa Professor of Innovation, argues that scientists can misinterpret or misunderstand many phenomena simply because they don’t have a good set of variables to describe the phenomena. “For millennia, people knew about fast or slow moving objects, but it was not until the notion of speed and acceleration was formally quantified that Newton was able to discover his famous law of motion F = MA”, noted Lipson. The variables describing temperature and pressure had to be identified before the laws of thermodynamics could be formalized, and so on for all corners of the scientific world. Variables are a precursor to any theory. “What other laws are we missing just because we don’t have the variables?” asked Du, who co-directed the work.

The article was also co-authored by Sunand Raghupathi and Ishaan Chandratreya, who helped collect the data for the experiments. Since July 1, 2022, Boyuan Chen has been an assistant professor at Duke University. Work is part of a joint[{” attribute=””>University of Washington, Columbia, and Harvard NSF AI institute for dynamical systems, aimed to accelerate scientific discovery using AI.

Reference: “Automated discovery of fundamental variables hidden in experimental data” by Boyuan Chen, Kuang Huang, Sunand Raghupathi, Ishaan Chandratreya, Qiang Du and Hod Lipson, 25 July 2022, Nature Computational Science.
DOI: 10.1038/s43588-022-00281-6

Leave a Comment