Projects will integrate AI into flexible data and computer processing systems to support scientific progress
WASHINGTON, D.C.—Today, the U.S. Department of Energy (DOE) announced $15.1 million for three collaborative research projects, at five universities, to advance the development of a flexible multi-tiered data and computational infrastructure to support a diverse collection of on-demand scientific data processing tasks and computationally intensive simulations. The projects will accelerate research in the fields of environmental and materials science and enhance simulation capabilities.
Modern science depends on a geographically distributed devices such as specialized instruments, sensors, detectors, computers, storage systems, and visualization systems that are interconnected via high performance networks. Science workflow systems, like those supported by these projects, automatically combines a unique group of these distributed devices and orchestrates how they are used to create a unique on-demand scientific tool for discovery. Computational scientists create instruments to execute and visualize detailed simulations while experimental scientists create instruments to observe and analyze physical events, like simulations of the expanding universe and detailed understanding of subatomic particles.
“Collaborations between scientific disciplines, like those created through this program, pave the way for the future of scientific discovery by combining diverse knowledge, skills and tools in new ways to approach a variety of critical problems.” said Barbara Helland, DOE Associate Director of Science for Advanced Scientific Computing Research. “These projects can revolutionize the scientific productivity of our facilities while working towards solving some of America’s big problems.”
Projects selected in today’s announcement cover a range of topics at the frontiers of the DOE Office of Science’s mission. The projects are:
- A collaborative team of scientists from The University of Texas – Austin, the University of Notre Dame, Louisiana State University, and Pacific Northwest National Laboratory will address mitigation strategies for gulf coastal flooding events due to extreme weather with artificial intelligence and machine learning (AI/ML) techniques that combine experimental data with computer simulations.
- A collaborative team of scientists from the University of Connecticut and Lawrence Berkeley National Laboratory will couple experimental data with simulations using AI/ML techniques to design, manufacture, and test new materials with uniquely designed properties for potential applications in batteries, sensors, and energy storage.
- A collaborative team of scientists from the University of Southern California, Argonne National Laboratory, and Lawrence Berkeley National Laboratory will develop AI/ML based methods to simulate and experimentally verify the performance of large, distributed computing infrastructures.
The projects were selected by competitive peer review under a DOE Funding Opportunity Announcement and are managed by the Office of Advanced Scientific Computing Research within the DOE Office of Science.
Total funding is $15.1 million for projects lasting up to 3 years in duration, with $5.76 million in Fiscal Year 2021 dollars and outyear funding contingent on congressional appropriations.