A new cosmic map, made with the help of machine learning, has uncovered hidden structures that connect the Milky Way galaxy, hoe to our solar system and our neighbouring galaxy, the Andromeda. This new map can help scientists create a model to predict a possible collision between the two galaxies. This collision is supposed to occur in the next 4.5 billion years. The map mapped the dark-matter filaments that bridge two galaxies and may affect the merger. 

The map was created using machine learning. The scientists trained a model using a large set of galaxy simulations, called IllustrisTNG. The learning set included galaxies similar to our own, the Milky Way, with an aim to better understand what galactic properties best predict the distribution of dark matter.

The map may also help give clarity on dark matter's influence in the evolution of our universe, participating scientists said in a statement from Pennsylvania State University. 

In the universe, 80% of the matter is represented by dark matter. However, dark matter and dark energy are poorly understood. While dark matter is invisible in telescopes, scientists can chart the influence of dark matter's gravity on large cosmic structures, such as galaxies.

"Because dark matter dominates the dynamics of the universe, it basically determines our fate," study co-author Donghui Jeong, an associate professor of astronomy and astrophysics at Penn State, said in the statement. "We can ask a computer to evolve the map for billions of years to see what will happen in the local universe. And we can evolve the model back in time to understand the history of our cosmic neighbourhood."

"Ironically, it's easier to study the distribution of dark matter much further away [from Earth] because it reflects the very distant past, which is much less complex," Jeong said. "Over time, as the large-scale structure of the universe has grown, the complexity of the universe has increased, so it is inherently harder to make measurements about dark matter locally."

Once the model was calibrated, the scientists started feeding real-life data from the Cosmicflows-3 galaxy catalogue to create the map. This catalogue includes information about the distributions and movements of 17,000 galaxies lying in 200 megaparsecs of the Milky Way. (One parsec is roughly 3.26 light-years, which is about 19.2 trillion miles or 30.9 trillion kilometres.)

The model accurately recreated the Local Group of galaxies, the neighbouring galaxies around the Milky Way. This area is also known as the local void since it includes vast empty space regions. 

Further, the map chartered our newer filaments which need to be studied. A few of these filaments connect to the Milky Way to Andromeda. The map can become more accurate as NASA's $9.8 billion James Webb Space Telescope, which is expected to launch later this year, will send back data that will allow researchers to see even fainter, faraway galaxies, the researchers said.

"Having a local map of the cosmic web opens up a new chapter of the cosmological study," Jeong said. "We can study how the distribution of dark matter relates to other emission data, which will help us understand the nature of dark matter."

The paper was published in May, in the Astrophysical Journal by the researcher group led by Sungwook Hong, who has dual affiliations with the University of Seoul and the Korea Astronomy and Space Science Institute.