Mapping the universe with artificial intelligence

Researchers in Germany have developed an artificial intelligence (AI) algorithm to chart and explain the structure and dynamics of the Universe.

“Our model is a big step forward. With the help of AI, we can now model the Universe around us with unprecedented accuracy and study how the largest structures in the cosmos came into being,” said lead researcher, Dr Francisco Kitaura.

The algorithm, described in Monthly Notices of the Royal Astronomical Society, uses gravitation to determine the influence of the three constituents described in the Lambda Cold Dark Matter (LCDM) model for the cosmos: the ‘normal’ matter composed of planets, stars and nebular, as well as dark matter and dark energy.

The program can also detect the residual heat from the Big Bang called Cosmic Microwave Background Radiation (CMBR) which allows astronomers to determine the motion of the Local Group of galaxy clusters that includes the Milky Way. Astronomers try to explain this motion using the predicted distribution of matter and its gravitational force, but mapping dark matter in the same region is notoriously difficult.

“Finding the dark matter distribution corresponding to a galaxy catalogue is like trying to make a geographical map of Europe from a satellite image during the night that only shows the light coming from dense populated areas,” said Kitaura.

The new algorithm has enabled the explanation of the directions of motion and 80% of the speed of the galaxies that make up the Local Group and the gravitational forces that arise from matter up to 370 million light years away. The results of the AI algorithm are a close fit to the LCDM predictions.

However, the alogorithm does not as yet provide the whole picture for explaining galaxy speed;

“To explain the rest of the 20% of the speed, we need to consider the influence of matter up to about 460 million light years away, but at the moment the data are less reliable at such a large distance,” Kitaura explained.