{"id":180448,"date":"2022-01-06T09:35:25","date_gmt":"2022-01-06T14:35:25","guid":{"rendered":"https:\/\/today.uconn.edu\/?p=180448"},"modified":"2022-02-23T08:18:39","modified_gmt":"2022-02-23T13:18:39","slug":"the-largest-suite-of-cosmic-simulations-for-ai-training-is-now-free-to-download-already-spurring-discoveries","status":"publish","type":"post","link":"https:\/\/today.uconn.edu\/2022\/01\/the-largest-suite-of-cosmic-simulations-for-ai-training-is-now-free-to-download-already-spurring-discoveries\/","title":{"rendered":"The Largest Suite of Cosmic Simulations for AI Training Is Now Free to Download; Already Spurring Discoveries"},"content":{"rendered":"<p>Totaling 4,233 universe simulations, millions of galaxies and 350 terabytes of data, a new release from the CAMELS project is a treasure trove for cosmologists. CAMELS \u2014 which stands for Cosmology and Astrophysics with MachinE Learning Simulations \u2014 aims to use those simulations <a href=\"https:\/\/www.simonsfoundation.org\/2021\/07\/07\/record-breaking-suite-of-cosmic-simulations-aims-to-identify-universes-parameters\/\">to train artificial intelligence models<\/a> to decipher the universe\u2019s properties.<\/p>\n<p>Scientists are already using the data, <a href=\"https:\/\/camels.readthedocs.io\/en\/latest\/\">which is free to download<\/a>, to power new research, says project co-leader Francisco Villaescusa-Navarro, a research scientist with the Simons Foundation\u2019s CMB (Cosmic Microwave Background) Analysis and Simulation group.<\/p>\n<p>Villaescusa-Navarro leads the project with associate research scientists at the Flatiron Institute\u2019s Center for Computational Astrophysics (CCA) Shy Genel and <a href=\"https:\/\/physics.uconn.edu\/person\/daniel-angles-alcazar\/\">Daniel Angl\u00e9s-Alc\u00e1zar, who is also a UConn Associate Professor of Physics<\/a>.<\/p>\n<p>\u201cMachine learning is revolutionizing many areas of science, but it requires a huge amount of data to exploit,\u201d says Angl\u00e9s-Alc\u00e1zar. \u201cThe CAMELS public data release, with thousands of simulated universes covering a broad range of plausible physics, will provide the galaxy formation and cosmology communities with a unique opportunity to explore the potential of new machine-learning algorithms to solve a variety of problems.\u201d<\/p>\n<p><iframe title=\"Unraveling Mysteries of the Universe with Machine Learning\" width=\"500\" height=\"281\" src=\"https:\/\/www.youtube.com\/embed\/rFxLkeJ75dM?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/p>\n<p>The CAMELS team generated the simulations using code taken from the <a href=\"https:\/\/www.tng-project.org\/\">IllustrisTNG<\/a> and <a href=\"http:\/\/simba.roe.ac.uk\/\">Simba<\/a> projects. The CAMELS team includes members of both projects, with Genel a part of the core team of IllustrisTNG and Angl\u00e9s-Alc\u00e1zar on the team that developed Simba.<\/p>\n<p>About half of the simulations combine the physics of the cosmos with the smaller-scale physics essential for galaxy formation. Each simulation is run with slightly different assumptions about the universe \u2014 for instance, regarding how much of the universe is invisible dark matter versus the dark energy pulling the cosmos apart, or how much energy supermassive black holes inject into the space between galaxies.<\/p>\n<p>The researchers designed the simulations to feed machine-learning models, which will then be able to extract information from observations of the real, observable universe. With 4,233 universe simulations, CAMELS is the largest ever suite of detailed cosmological simulations designed to train machine-learning algorithms.<\/p>\n<p>\u201cThe data will enable new discoveries and connect cosmology with astrophysics through machine learning,\u201d says Villaescusa-Navarro. \u201cThere has never been anything similar to this, with this many universe simulations.\u201d<\/p>\n<p>The CAMELS dataset is already powering research projects, with a wide range of papers utilizing the data in the works.<\/p>\n<p>Pablo Villanueva-Domingo of the University of Valencia in Spain led <a href=\"https:\/\/arxiv.org\/abs\/2109.10915\">one such paper<\/a>. He and his colleagues leveraged the CAMELS simulations to train an artificial intelligence model to measure the mass of our Milky Way galaxy plus its surrounding dark matter halo, and the nearby Andromeda galaxy and its halo. The measurements \u2014 the first ever done using AI \u2014 put our galaxy\u2019s heft at 1 trillion to 2.6 trillion times the sun\u2019s mass. Those estimates are roughly in line with those made by other methods, demonstrating the AI approach\u2019s accuracy.<\/p>\n<p>Meanwhile, Villaescusa-Navarro headed an effort to use the CAMELS data to estimate the value of two parameters that govern the fundamental properties of the universe: what fraction of the universe is matter, and how evenly mass is distributed throughout the cosmos. First, he and his colleagues used CAMELS to generate maps such as the distribution of dark matter, gas and different properties of stars. Then, using the maps, they trained a machine-learning tool called a neural network to predict the values of the two parameters.<\/p>\n<p>\u201cThis is the same kind of algorithm used to tell the difference between a cat and a dog from the pixels of an image,\u201d says Genel, who co-authored the paper. \u201cThe human eye can\u2019t determine how much dark matter there is in a simulation, but a neural network can do that.\u201d<\/p>\n<p>The results showed the promise of leveraging CAMELS to precisely estimate such parameters in the future based on new observations of the universe, says Villaescusa-Navarro.<\/p>\n<p>\u201cIt\u2019s exciting to see what other new discoveries this will enable,\u201d he says.<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The CAMELS project uses machine learning and thousands of simulations to extract secrets from the cosmos<\/p>\n","protected":false},"author":58,"featured_media":180593,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_crdt_document":"","wds_primary_category":0,"wds_primary_series":0,"wds_primary_attribution":0,"footnotes":""},"categories":[2226,88,2076,2235],"tags":[],"magazine-issues":[],"coauthors":[117],"class_list":["post-180448","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-clas","category-global-affairs","category-research","category-today-homepage"],"pp_statuses_selecting_workflow":false,"pp_workflow_action":"current","pp_status_selection":"publish","acf":[],"publishpress_future_action":{"enabled":false,"date":"2026-05-30 01:58:33","action":"change-status","newStatus":"draft","terms":[],"taxonomy":"category","extraData":[]},"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/posts\/180448","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/users\/58"}],"replies":[{"embeddable":true,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/comments?post=180448"}],"version-history":[{"count":3,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/posts\/180448\/revisions"}],"predecessor-version":[{"id":180600,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/posts\/180448\/revisions\/180600"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/media\/180593"}],"wp:attachment":[{"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/media?parent=180448"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/categories?post=180448"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/tags?post=180448"},{"taxonomy":"magazine-issue","embeddable":true,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/magazine-issues?post=180448"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/today.uconn.edu\/wp-rest\/wp\/v2\/coauthors?post=180448"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}