Department of Energy Invests $16 Million in Data-Intensive Scientific Machine Learning Research and Analysis

WASHINGTON, D.C.—Today, the U.S. Department of Energy (DOE) announced $16 million for five collaborative research projects to develop artificial intelligence (AI) and machine learning (ML) algorithms for enabling scientific insights and discoveries from data generated by computational simulations, experiments, and observations.

The five projects are focused on developing reliable and efficient AI and ML methods for a broad range of science needs. Potential applications include: accurate forecasts for the dynamic behavior of the electric power grid; predictions of extreme climate and weather events; using data from computational models to draw conclusions about combustion, high-energy physics, and cosmology; and analysis of massive data from DOE scientific user facilities.

“Disruptive technology changes are occurring across science applications, algorithms, architectures, and high-performance computing ecosystems,” said Barbara Helland, Associate Director for Advanced Scientific Computing Research, DOE Office of Science. “These projects explore potentially high-impact approaches in AI and machine learning to assist and automate scientific discovery and data analysis for increasingly complex problems.”

These project awards are the latest in a series of Scientific Machine Learning and AI funding opportunities focused on uncertainty quantification, machine learning-enhanced modeling and simulation, and intelligent automation and decision-support for complex systems.

Projects were chosen by competitive peer review under DOE Funding Opportunity Announcement, “Data-Intensive Scientific Machine Learning and Analysis,” sponsored by the Office of Advanced Scientific Computing Research (ASCR) within DOE’s Office of Science.

The research projects range from single Principal Investigator (PI) to multi-PI, multi-institution efforts and include eight universities and four DOE National Laboratories. A list of awards can be found on the ASCR homepage under the heading, “What’s New.