In the CAMELS project, coders simulated thousands of universes with diverse compositions, arrayed at the end of this video as cubes.Video: Kaze Wong/CAMELS collaboration
A group of scientists may have stumbled upon a radical new way to do cosmology.
Cosmologists usually determine the composition of the universe by observing as much of it as possible. But these researchers have found that a machine learning algorithm can scrutinize a single simulated galaxy and predict the overall makeup of the digital universe in which it existsâa feat analogous to analyzing a random grain of sand under a microscope and working out the mass of Eurasia. The machines appear to have found a pattern that might someday allow astronomers to draw sweeping conclusions about the real cosmos merely by studying its elemental building blocks.
âThis is a completely different idea,â said Francisco Villaescusa-Navarro, a theoretical astrophysicist at the Flatiron Institute in New York and lead author of the work. âInstead of measuring these millions of galaxies, you can just take one. Itâs really amazing that this works.â
To view this video please enable JavaScript, and consider upgrading to a web browser that supports HTML5 video WATCH What Happens to Your Data After You Die? Share Tweet Email More... EMBED URL<script async src="//player-backend.cnevids.com/script/video/61eae51d1d75db66d3a61a5b.js?iu=/3379/conde.wired/partner"></script> VIDEO URLhttps://www.wired.com/video/watch/what-happens-to-your-data-after-you-die Our bad! It looks like we're experiencing playback issues. The live event has ended. Please check back again soon for the recorded video. LIVEVIDEO TO BEGIN AFTER ADLoaded: 0%Progress: 0% UnmuteVolume 0% Back Caption Options Close Settings Language ⢠English Font Size ⢠Small ⢠Medium ⢠Large Position ⢠Auto ⢠Bottom ⢠Top Sample Caption TextCurrent Time 0:00Duration 0:00Remaining Time -0:00
It wasnât supposed to. The improbable find grew out of an exercise Villaescusa-Navarro gave to Jupiter Ding, a Princeton University undergraduate: Build a neural network that, knowing a galaxyâs properties, can estimate a couple of cosmological attributes. The assignment was meant merely to familiarize Ding with machine learning. Then they noticed that the computer was nailing the overall density of matter.
âI thought the student made a mistake,â Villaescusa-Navarro said. âIt was a little bit hard for me to believe, to be honest.â
The results of the investigation that followed appeared in a January 6 preprint that has been submitted for publication. The researchers analyzed 2,000 digital universes generated by the Cosmology and Astrophysics with Machine Learning Simulations (CAMELS) project. These universes had a range of compositions, containing between 10 percent and 50 percent matter with the rest made up of dark energy, which drives the universe to expand faster and faster. (Our actual cosmos consists of roughly one-third dark and visible matter and two-thirds dark energy.) As the simulations ran, dark matter and visible matter swirled together into galaxies. The simulations also included rough treatments of complicated events like supernovas and jets that erupt from supermassive black holes.
Dingâs neural network studied nearly 1 million simulated galaxies within these diverse digital universes. From its godlike perspective, it knew each galaxyâs size, composition, mass, and more than a dozen other characteristics. It sought to relate this list of numbers to the density of matter in the parent universe.
It succeeded. When tested on thousands of fresh galaxies from dozens of universes it hadnât previously examined, the neural network was able to predict the cosmic density of matter to within 10 percent. âIt doesnât matter which galaxy you are considering,â Villaescusa-Navarro said. âNo one imagined this would be possible.â
âThat one galaxy can get [the density to] 10 percent or so, that was very surprising to me,â said Volker Springel, an expert in simulating galaxy formation at the Max Planck Institute for Astrophysics who was not involved in the research.
The algorithmâs performance astonished researchers because galaxies are inherently chaotic objects. Some form all in one go, and others grow by eating their neighbors. Giant galaxies tend to hold onto their matter, while supernovas and black holes in dwarf galaxies might eject most of their visible matter. Still, every galaxy had somehow managed to keep close tabs on the overall density of matter in its universe.
One interpretation is âthat the universe and/or galaxies are in some ways much simpler than we had imagined,â said Pauline Barmby, an astronomer at Western University in Ontario. Another is that the simulations have unrecognized flaws.
The team spent half a year trying to understand how the neural network had gotten so wise. They checked to make sure the algorithm hadnât just found some way to infer the density from the coding of the simulation rather than the galaxies themselves. âNeural networks are very powerful, but they are super lazy,â Villaescusa-Navarro said.
Through a series of experiments, the researchers got a sense of how the algorithm was divining the cosmic density. By repeatedly retraining the network while systematically obscuring different galactic properties, they zeroed in on the attributes that mattered most.
Near the top of the list was a property related to a galaxyâs rotation speed, which corresponds to how much matter (dark and otherwise) sits in the galaxyâs central zone. The finding matches physical intuition, according to Springel. In a universe overflowing with dark matter, youâd expect galaxies to grow heavier and spin faster. So you might guess that rotation speed would correlate with the cosmic matter density, although that relationship alone is too rough to have much predictive power.
The neural network found a much more precise and complicated relationship between 17 or so galactic properties and the matter density. This relationship persists despite galactic mergers, stellar explosions and black hole eruptions. âOnce you get to more than [two properties], you canât plot it and squint at it by eye and see the trend, but a neural network can,â said Shaun Hotchkiss, a cosmologist at the University of Auckland in New Zealand.
While the algorithmâs success raises the question of how many of the universeâs traits might be extracted from a thorough study of just one galaxy, cosmologists suspect that real-world applications will be limited. When Villaescusa-Navarroâs group tested their neural network on a different propertyâcosmic clumpinessâit found no pattern. And Springel expects that other cosmological attributes, such as the accelerating expansion of the universe due to dark energy, have little effect on individual galaxies.
The research does suggest that, in theory, an exhaustive study of the Milky Way and perhaps a few other nearby galaxies could enable an exquisitely precise measurement of our universeâs matter. Such an experiment, Villaescusa-Navarro said, could give clues to other numbers of cosmic import such as the sum of the unknown masses of the universeâs three types of neutrinos.
But in practice, the technique would have to first overcome a major weakness. The CAMELS collaboration cooks up its universes using two different recipes. A neural network trained on one of the recipes makes bad density guesses when given galaxies that were baked according to the other. The cross-prediction failure indicates that the neural network is finding solutions unique to the rules of each recipe. It certainly wouldnât know what to do with the Milky Way, a galaxy shaped by the real laws of physics. Before applying the technique to the real world, researchers will need to either make the simulations more realistic or adopt more general machine learning techniquesâa tall order.
âIâm very impressed by the possibilities, but one needs to avoid being too carried away,â Springel said.
But Villaescusa-Navarro takes heart that the neural network was able to find patterns in the messy galaxies of two independent simulations. The digital discovery raises the odds that the real cosmos may be hiding a similar link between the large and the small.
âItâs a very beautiful thing,â he said. âIt establishes a connection between the whole universe and a single galaxy.â
Editorâs note: A number of the authors on this study are affiliated with the Flatiron Institute, a scientific institution funded by the Simons Foundation, which also funds this editorially independent magazine. One co-author is David Spergel, the president of the Simons Foundation. Simons Foundation funding decisions have no influence on our coverage.
Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research developments and trends in mathematics and the physical and life sciences.
- đŠ The latest on tech, science, and more: Get our newsletters!
- Driving while baked? Inside the high-tech quest to find out
- You (might) need a patent for that woolly mammoth
- Sony's AI drives a race car like a champ
- Crypto is funding Ukraine's defense and hacktivists
- đď¸ Explore AI like never before with our new database
- đđ˝ââď¸ Want the best tools to get healthy? Check out our Gear teamâs picks for the best fitness trackers, running gear (including shoes and socks), and best headphones