AI can distinguish dark matter from cosmic noise

Dark matter is the invisible force that holds the universe together, or so it is believed. It makes up about 85% of all matter and about 27% of the contents of the universe, but since we can’t see it directly, we have to study its gravitational effects on galaxies and other cosmic structures. Despite decades of research, the true nature of dark matter remains one of the most intractable questions in science.

One leading theory is that dark matter might be a type of particle that barely interacts with anything else except gravity. But some scientists think these particles might occasionally interact with each other, a phenomenon known as self-interaction. Detecting such interactions would offer crucial clues about the properties of dark matter.

However, distinguishing the subtle signs of dark matter self-interactions from those of other cosmic effects, such as those caused by active galactic nuclei (AGNs) – the supermassive black holes at the centers of galaxies – is a major challenge. Feedback from AGNs can move matter in ways similar to the effects of dark matter, making it difficult to distinguish between the two.

Astronomer David Harvey of EPFL’s Laboratory of Astrophysics has developed a deep learning algorithm that can untangle these complex signals. This research is published in Astronomy of nature.

Their artificial intelligence-based method is designed to differentiate between the effects of dark matter self-interactions and AGN feedback by analyzing images of galaxy clusters—large collections of galaxies bound together by gravity. This innovation promises to dramatically improve the accuracy of dark matter studies.

Harvey trained a convolutional neural network (CNN), a type of AI that is particularly good at recognizing patterns in images, with images from the BAHAMAS-SIDM project, which models galaxy clusters under different scenarios of dark matter and AGN feedback. By being fed thousands of images of simulated galaxy clusters, the CNN learned to distinguish between signals caused by dark matter self-interactions and those caused by AGN feedback.

Of the various CNN architectures tested, the most complex, dubbed “Inception,” also proved to be the most accurate. The AI ​​was trained on two main dark matter scenarios, featuring different levels of self-interaction, and validated on additional models, including a more complex, velocity-dependent dark matter model.

Inception achieved an impressive 80% accuracy under ideal conditions, effectively identifying whether galaxy clusters were influenced by dark matter interacting with itself or by feedback from AGN. It maintained its high performance even when the researchers introduced realistic observation noise that mimics the kind of data we expect from future telescopes like Euclid.

This means that Inception, and the AI ​​approach in general, could prove incredibly useful for analyzing the massive amounts of data we collect from space. Additionally, AI’s ability to process invisible data indicates that it is adaptable and reliable, making it a promising tool for future dark matter research.

AI-powered approaches like Inception could have a huge impact on our understanding of what dark matter really is. As new telescopes collect unprecedented amounts of data, this method will help scientists analyze it quickly and accurately, potentially revealing the true nature of dark matter.