high performance computing (Gorodenkoff/Shutterstock.com)

DOE turns to AI to transform science

To better manage the exponentially increasing amount of scientific data at the Department of Energy's high-end research facilities, the agency announced plans to invest up to $40 million to research how artificial intelligence and machine learning can spur transformative advances across scientific disciplines.

DOE’s Data, Artificial Intelligence, and Machine Learning at DOE Scientific User Facilities Program aims to use AI/ML to develop optimization, modeling and data analytics tools that address technical challenges in data acquisition and management, facilities and instrumentation optimization.  The effort spans 18 scientific facilities working on basic energy sciences, high energy physics and nuclear physics.

Recent AI/ML advances suggest that the technology “can greatly accelerate the quest to probe and understand fundamental phenomena across a vast range of lengths and timescales, potentially leading to transformative advances across scientific disciplines,” DOE said in its funding announcement.

The facilities and their partners are invited to submit proposals that support development of AI/ML-enabled facilities that maximize the DOE’s scientific impact. Proposals should address the following research priorities:

  • Extracting critical and strategic information from large complex datasets, thereby reducing the processing and analysis burden and unmasking complexities elusive to human observations.
  • Developing real-time autonomous controls for large, complex scientific user facilities and experiments that predict the health and failure of instruments and scientific equipment.
  • Enabling virtual laboratory environments of experimental facilities -- such as digital twins or labs in a computational cloud -- to achieve new scientific goals.
  • Making improvements in data sharing, curation, workflow and analysis to leverage the wealth of diverse and complementary data from across the facilities, create data standards and develop training sets for new AI/ML methods.
  • Implementing AI/ML techniques to optimize and automate operations of large accelerator complexes.

“Artificial intelligence’s ability to analyze and divine insights from massive datasets has the power to transform the world around us,” said Cheryl Ingstad, director of DOE’s Artificial Intelligence and Technology Office. “DOE is determined to lead by example in AI application by turning this power on ourselves to optimize the way we operate facilities and push the boundaries of scientific discovery.”

Applications are due May 1.

About the Author

Susan Miller is executive editor at GCN.

Over a career spent in tech media, Miller has worked in editorial, print production and online, starting on the copy desk at IDG’s ComputerWorld, moving to print production for Federal Computer Week and later helping launch websites and email newsletter delivery for FCW. After a turn at Virginia’s Center for Innovative Technology, where she worked to promote technology-based economic development, she rejoined what was to become 1105 Media in 2004, eventually managing content and production for all the company's government-focused websites. Miller shifted back to editorial in 2012, when she began working with GCN.

Miller has a BA and MA from West Chester University and did Ph.D. work in English at the University of Delaware.

Connect with Susan at [email protected] or @sjaymiller.

Featured

  • automated processes (Nikolay Klimenko/Shutterstock.com)

    How the Army’s DORA bot cuts manual work for contracting professionals

    Thanks to robotic process automation, the time it takes Army contracting professionals to determine whether prospective vendors should receive a contract has been cut from an hour to just five minutes.

  • Russia prying into state, local networks

    A Russian state-sponsored advanced persistent threat actor targeting state, local, territorial and tribal government networks exfiltrated data from at least two victims.

Stay Connected