BYLINE: Lea Radick

Newswise — The U.S. National Science Foundation and Simons Foundation have selected a group of institutions, including Argonne, to receive funding to establish an AI and astronomy institute called the NSF-Simons AI Institute for the Sky (SkAI).

Part of a groundbreaking effort to harness artificial intelligence (AI) to unlock the mysteries of the cosmos, the U.S. Department of Energy’s (DOE) Argonne National Laboratory is a key collaborator in the newly launched NSF-Simons AI Institute for the Sky (SkAI, pronounced ​“sky”), led by Northwestern University. 

Jointly funded by a $20 million grant from the U.S. National Science Foundation (NSF) and the Simons Foundation, SkAI aims to revolutionize how researchers explore the universe by developing innovative AI technologies capable of handling the vast data generated by astronomical surveys.

“Our lab’s advanced computational capabilities are ideally suited for the challenges posed by the enormous datasets from astronomical surveys. By developing AI-driven solutions, we are accelerating discoveries that will reshape our understanding of the universe.” — Katrin Heitmann, Argonne physicist and computational scientist 

Renowned for its expertise in computational science and artificial intelligence, Argonne will help develop quantitatively trustworthy foundational AI approaches. These AI tools will be able to process the immense datasets from upcoming projects like the NSF-DOE Vera C. Rubin Observatory’s Legacy Survey of Space and Time. Funded by the NSF and the DOE’s Office of Science (DOE/SC), Rubin Observatory is a Program of NSF NOIRLab, which jointly operates Rubin with SLAC National Accelerator Laboratory.

Argonne’s impacts in computational cosmology will also play an important role in the SkAI institute. World-leading simulations carried out on DOE’s exascale supercomputers will be a crucial input to understanding the universe from the largest to the smallest scales.

Together, these tools and capabilities will enable researchers to analyze data more efficiently, revealing insights into astrophysical phenomena such as the formation of black holes and the evolution of galaxies. They will also be used to investigate dark matter and dark energy, which drive the evolution of the universe and how structure forms within it. 

“Argonne is proud to be at the forefront of this transformative project,” said physicist and computational scientist Katrin Heitmann, deputy director of Argonne’s High Energy Physics division. Heitmann is also part of the SkAI team working on computational cosmology. 

“Our lab’s advanced computational capabilities are ideally suited for the challenges posed by the enormous datasets from astronomical surveys. By developing AI-driven solutions, we are accelerating discoveries that will reshape our understanding of the universe.”

Led by Northwestern University and supported by Argonne and other partners, SkAI brings together a diverse team of over 80 researchers across 25 institutions. These institutions include the University of Chicago, University of Illinois Urbana-Champaign, the National Center for Supercomputing Applications, DOE’s Fermi National Accelerator Laboratory, University of Illinois Chicago, the Adler Planetarium and the University of Wisconsin-Madison, as well as several undergraduate education and research institutions, and industry and art organizations. 

As part of its commitment to fostering the next generation of scientists, the SkAI team will also train a diverse and inclusive STEM workforce through its inclusion of the SkAI Satellite Network. This network comprises a set of 16 regional and national college partners that include 13 minority-serving institutions and two institutions participating in the NSF Established Program to Stimulate Competitive Research initiative.

Additionally, the tools and techniques developed by the SkAI team will be made available to the global research community, ensuring that the impact of SkAI extends far beyond its initial participants.

SkAI is one of two National AI Research Institutes in Astronomy recently announced. The other institute, the NSF-Simons CosmicAI Institute, is being led by the University of Texas at Austin. Established in 2020, the National AI Research Institutes represent the U.S. government’s cornerstone commitment to fostering long-term, fundamental research in AI

Besides Heitmann, other Argonne researchers on the SkAI team are Argonne Distinguished Fellow Salman Habib, director of Argonne’s Computational Science division, who has joint appointments at the UChicago and Northwestern University; Sandeep Madireddy, computer scientist at Argonne and Consortium for Advanced Science and Engineering (CASE) affiliate at the UChicago; Michael Papka, deputy associate laboratory director for the Computing, Environment and Life Sciences directorate and director of the Argonne Leadership Computing Facility (ALCF); and Argonne Distinguished Fellow Valerie Taylor, director of the Mathematics and Computer Science division. The ALCF is a DOE Office of Science user facility located at Argonne. 

The Argonne Leadership Computing Facility provides supercomputing capabilities to the scientific and engineering community to advance fundamental discovery and understanding in a broad range of disciplines. Supported by the U.S. Department of Energy’s (DOE’s) Office of Science, Advanced Scientific Computing Research (ASCR) program, the ALCF is one of two DOE Leadership Computing Facilities in the nation dedicated to open science.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology by conducting leading-edge basic and applied research in virtually every scientific discipline. Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.

The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://​ener​gy​.gov/​s​c​ience.