One of the biggest challenges scientists face is to understand how our universe came to be and what it’s final resting state would be. Within that challenge is the more awe-inspiring topic of some gravity is the concept of dark matter and dark energy. This is the more complicated puzzle, because this is what we cannot see, at least not directly.

As dark matter pulls the universe together, but dark energy causes it to expand faster, cosmologists are always trying to figure out exactly how much of the both are out there in order to refine their models.

Scientists from the Department of Physics and the Department of Computer Science at ETH Zurich have now joined forces to improve the standard methods that are used to estimate the dark matter content of the universe. They are using artificial intelligence—cutting-edge machine learning algorithms for cosmological data analysis that have a lot in common with those used for facial recognition by Facebook and other social media—to unlock this particular secret of the universe.

Their results were recently published in the scientific journal Physical Review D.

Facial recognition for cosmology

Tomasz Kacprzak, a researcher in the group of Alexandre Refregier at the Institute of Particle Physics and Astrophysics, explained: “Facebook uses its algorithms to find eyes, mouths or ears in images; we use ours to look for the tell-tale signs of dark matter and dark energy.”

As dark matter cannot be seen directly in telescope images, physicists rely on the fact that all matter—even dark matter—slightly bends the light rays from distant galaxies arriving on Earth. This effect, known as “weak gravitational lensing”, distorts the images of those galaxies very subtly, much like far-away objects appear blurred on a hot day as light passes through layers of air at different temperatures.

Cosmologists can use that distortion to work backwards and create mass maps of the sky showing where dark matter is located. They then compare the said dark matter maps to theoretical predictions to find which cosmological model matches the data most closely. Traditionally, this has been done using human-designed statistics—such as so-called correlation functions that describe how different parts of the maps are related to each other—which are, however, limiting in their ability to find complex patterns in the matter maps.

Neural networks teach themselves

Alexandre Refregier, however, says he has used a whole new methodology. “Instead of inventing the appropriate statistical analysis ourselves, we let computers do the job.” This is where Aurelien Lucchi and his colleagues from the Data Analytics Lab at the Department of Computer Science come in. Together with Janis Fluri, a PhD student in Refregier’s group and lead author of the study, they used machine learning algorithms called deep artificial neural networks and taught them to extract the largest possible amount of information from the dark matter maps.

In the first step, the scientists trained the neural networks by feeding them computer-generated data that simulates the universe. This way, they knew what the correct answer for a given cosmological parameter—let’s say the ratio between the total amount of dark matter and dark energy—should be for each simulated dark matter map.

By repeatedly analysing the dark matter maps, the neural network taught itself to look for the right kind of features in them and to extract more and more of the desired information. To make the Facebook face recognition analogy, it got better at distinguishing random oval shapes from eyes or mouths.

More accurate than human-made analysis

The results of that training were encouraging: the neural networks came up with values that were 30% more accurate than those obtained by traditional methods based on human-made statistical analysis. For cosmologists, that is a huge improvement as reaching the same accuracy by increasing the number of telescope images would require twice as much observation time, which is expensive.

Finally, the scientists used their fully trained neural network to analyse actual dark matter maps from the KiDS-450 dataset. “This is the first time such machine learning tools have been used in this context,” says Fluri, “and we found that the deep artificial neural network enables us to extract more information from the data than previous approaches. We believe that this usage of machine learning in cosmology will have many future applications.” As a next step, he and his colleagues are planning to apply their method to bigger image sets such as the Dark Energy Survey. Also, more cosmological parameters and refinements such as details about the nature of dark energy will be fed to the neural networks.