News from Argonne National Laboratory

New AI-based tool for modeling materials at the atomic and molecular scale

New AI-based tool for modeling materials at the atomic and molecular scale Lynch, Dominic… Fri, 05/13/2022 - 09:49
In a study published in Nature Communications, researchers report a reinforcement learning-based algorithm for developing molecular models that predict potential energy surfaces of elemental nanoclusters and bulk systems.
A graphical summary of the discrete Monte Carlo tree search reinforcement learning approach, extended to continuous action space (c-MCTS).

Scientific Achievement

Bond-order potentials were predicted and applied to cluster structure and dynamical stability for 54 different elemental systems and their alloys. This was made possible through reinforcement learning to develop a continuous action space Monte Carlo tree search algorithm (c-MCTS).

Significance and Impact

Similar modeling goals have relied heavily on human intuition and expertise, requiring years of efforts. This algorithm approach yields high quality data in just days and hours, with impact on many materials science and technology challenges.

Research Details

•This approach was benchmarked against other global optimization schemes.
 
•The calculations were primarily performed on the Carbon cluster of computers in CNM, Argonne Leadership Computing Facility, and National Energy Research Scientific Computing Center.

 

DOI: https://doi.org/10.1038/s41467-021-27849-6

Download this highlight

Work was performed in part at the Center for Nanoscale Materials

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation’s first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America’s scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, 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.

About Argonne’s Center for Nanoscale Materials
The Center for Nanoscale Materials is one of the five DOE Nanoscale Science Research Centers, premier national user facilities for interdisciplinary research at the nanoscale supported by the DOE Office of Science. Together the NSRCs comprise a suite of complementary facilities that provide researchers with state-of-the-art capabilities to fabricate, process, characterize and model nanoscale materials, and constitute the largest infrastructure investment of the National Nanotechnology Initiative. The NSRCs are located at DOE’s Argonne, Brookhaven, Lawrence Berkeley, Oak Ridge, Sandia and Los Alamos National Laboratories. For more information about the DOE NSRCs, please visit https://​sci​ence​.osti​.gov/​U​s​e​r​-​F​a​c​i​l​i​t​i​e​s​/​U​s​e​r​-​F​a​c​i​l​i​t​i​e​s​-​a​t​-​a​-​G​lance.

CONTACT US

For More Information or Media Related Inquiries

+1-630-252-5580 [email protected]

Related people

Related Organizations

Science & Technology Topics