New AI Could Uncover Hidden Physical Laws

New artificial intelligence (AI) technology that could uncover hidden physical laws has been developed by researchers at Kobe University and Osaka University. AI can extract hidden equations of motion from regular observational data, which are then used to create a model based on the laws of physics.

The new development could allow experts to uncover the hidden equations of motion behind inexplicable phenomena.

The research team included Associate Professor Yaguchi Takaharu and Ph.D. student Chen Yuhan from Kobe University, as well as Associate Professor Matsubara Takashi from Osaka University.

The research was presented last month at Thirty-fifth conference on neural information processing systems (NeurlPS2021).

Predict physical phenomena

To make predictions about physical phenomena, experts generally rely on simulations with supercomputers. The simulations use mathematical models based on the laws of physics, but the results can be unreliable if the model is questionable. This is why it is crucial to have a method for producing reliable models from the observation data of the phenomena.

The new research has developed a method of discovering new equations of motion in observational data. Previous research has focused on finding equations of motion from data, but some required the data to be in the correct format. The problem is, there are many cases where experts don’t know the best data format to use, so it is difficult to apply realistic data.

Illumination of unknown geometric properties

The researchers took up this challenge by shedding light on the unknown geometric properties behind the phenomena. This allowed them to develop an AI capable of finding these geometric properties in data. If AI can extract equations of motion from data, then the equations could be used to create models and simulations that follow the laws of physics.

Physical simulations take place in areas such as weather forecasting, drug discovery, and automotive design. However, they usually require extensive calculations. If AI can learn data from specific phenomena, as well as build small-scale models using the new method, then the calculations could be simplified, speeded up, and true to the laws of physics.

The method could also be applied to fields unrelated to physics, allowing investigations and simulations based on physical knowledge for phenomena previously considered impossible to explain. One such example is that it could be used to find a hidden equation of motion in animal population data that shows the change in the number of individuals, which could help provide information on the sustainability of ecosystems.

About Mariel Baker

Check Also

AMD Releases Latest Consistent Device Memory Mapping Linux Code – Designed for Frontier

Over the past year, we have seen various patches released by AMD engineers with a …