Stefano Castruccio, Notre Dame Collegiate Associate Professor, is part of a 12-member team across three continents who won the 2024 ACM Gordon Bell Prize for Climate Modelling, the highest honor recognizing outstanding achievement in high-performance computing (HPC) applications.

Castruccio is the first researcher from Notre Dame to win the award, which many in the field consider the “Nobel Prize” of HPC applied to real-world systems. The Gordon Bell Prize is in its 37th year, with the prize specifically for climate modelling conferred for the first time in 2023.

Castruccio and his team harnessed the power of some of the world’s most advanced supercomputers to create high-resolution climate simulations, which reduce computational costs and data storage seen in typical climate models. They demonstrated their exascale climate emulator at the International Conference for High Performance Computing, Networking, Storage, and Analysis in Atlanta, where they received their award on Nov. 20, 2024.

Castruccio, a faculty member in the Department of Applied and Computational Mathematics and Statistics (ACMS) at the University of Notre Dame, led the statistical effort for the research.

“Right now, developing storage is becoming more and more expensive than computation,” Castruccio said. “So at some point, we’re going to run out of space; we are already running out of space for many applications in climate modeling.”

The award is the culmination of 10 years of work, Castruccio said, emphasizing that it involved a diverse and international team of climate scientists, machine learning experts, and high-performance computing specialists.

“This work not only pushes the boundaries of climate modeling technology but also underscores the importance of leveraging cutting-edge computational techniques and high-performance computing infrastructure to unlock new insights into climate dynamics and helps pave the way for a sustainable future for our planet,” said Sudipto Banerjee, senior associate dean for academic programs, University of California-Los Angeles (UCLA) Fielding School of Public Health, as well as professor of the Department of Biostatistics at UCLA.

Other team members include Sameh Abdulah, David E. Keyes, Zubair Khalid, Hatem Ltaief, Yan Song, Greorgiy L. Stenchikov and Ying Sun, all of King Abdullah University of Science and Technology, Saudi Arabia; Allison H. Baker, of the National Science Foundation’s National Center for Atmospheric Research in Boulder, Colorado; George Bosilca of NVIDIA Corp., Santa Clara, California and Qinglei Cao of St. Louis University, St. Louis, Missouri.

“I am thrilled to celebrate this outstanding achievement,” said Fang Liu, interim chair of the Department of Applied and Computational Mathematics and Statistics at Notre Dame. “This collaborative work represents a significant advance in using statistical models with the world's fastest supercomputers to address complex climate change challenges.

At the conference, Castruccio and team members shared an augmented reality visualization of their results using virtual reality glasses. Through the glasses, people could see the two spheres of the earth — the original simulator, and the version with their emulator, for comparison.

“Receiving this prestigious award—the first for Notre Dame faculty—highlights the growing prominence and impact of our department (ACMS) and Notre Dame in computational, statistical, and data science on the international stage,” Liu said.

Originally published by Deanna Csomo Ferrell at science.nd.edu on November 26, 2024.