Machine learning allows quantum mechanics to be efficiently applied to molecular simulations for drug development, detonation physics and more
New work from Los Alamos National Laboratory, the University of North Carolina at Chapel Hill, and the University of Florida is showing that artificial neural nets can be trained to encode quantum mechanical laws to describe the motions of molecules, supercharging simulations potentially across a broad range of fields.
"This means we can now model materials and molecular dynamics billions of times faster compared to conventional quantum methods, while retaining the same level of accuracy," said Justin Smith, Los Alamos physicist and Metropolis Fellow in the laboratory's Theoretical Division.
Understanding how molecules move is critical to tapping their potential value for drug development, protein simulations and reactive chemistry, for example, and both quantum mechanics and experimental (empirical) methods feed into the simulations.
The new technique, called the ANI-1ccx potential, promises to advance the capabilities of researchers in many fields and improve the accuracy of machine learning-based potentials in future studies of metal alloys and detonation physics.
Quantum mechanical (QM) algorithms, used on classical computers, can accurately describe the mechanical motions of a compound in its operational environment. But QM scales very poorly with varying molecular sizes, severely limiting the scope of possible simulations.
Even a slight increase in molecular size within a simulation can dramatically increase the computational burden. So practitioners often resort to using empirical information, which describes the motion of atoms in terms of classical physics and Newton's Laws, enabling simulations that scale to billions of atoms or millions of chemical compounds.
Traditionally, empirical potentials have had to strike a tradeoff between accuracy and transferability. When the many parameters of the potential are finely tuned for one compound, the accuracy decreases on other compounds.
Instead, the Los Alamos team, with the University of North Carolina at Chapel Hill and University of Florida, has developed a machine learning approach called transfer learning that lets them build empirical potentials by learning from data collected about millions of other compounds. The new approach with the machine learning empirical potential can be applied to new molecules in milliseconds, enabling research into a far greater number of compounds over much longer timescales.
Publication: J. S. Smith, B. T. Nebgen, R. Zubatyuk, N. Lubbers, C. Devereux, K. Barros, S. Tretiak, O. Isayev, A. E. Roitberg, "Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning," Nature Communications 10.1038/s41467-019-10827-4 (2019)
Funding: The Los Alamos authors acknowledge support of the U.S. Department of Energy (DOE) through the LANL LDRD Program. This work was performed, in part, at the Center for Integrated Nanotechnologies, an Office of Science User Facility operated for the U.S. DOE Office of Science. They also acknowledge the LANL Institutional Computing (IC) program and LANL ACL data team for providing computational resources. This research in part was done using resources provided by the Open Science Grid which is supported by the National Science Foundation award 1148698, and the U.S. DOE Office of Science.
About Los Alamos National Laboratory
Los Alamos National Laboratory, a multidisciplinary research institution engaged in strategic science on behalf of national security, is operated by Triad, a public service oriented, national security science organization equally owned by its three founding members: Battelle Memorial Institute (Battelle), the Texas A&M University System (TAMUS), and the Regents of the University of California (UC) for the Department of Energy's National Nuclear Security Administration.
Los Alamos enhances national security by ensuring the safety and reliability of the U.S. nuclear stockpile, developing technologies to reduce threats from weapons of mass destruction, and solving problems related to energy, environment, infrastructure, health, and global security concerns.
Nancy Ambrosiano | EurekAlert!
New method makes realistic water wave animations more efficient
03.07.2019 | Institute of Science and Technology Austria
Generation and sampling of quantum states of light in a silicon chip
02.07.2019 | University of Bristol
An interdisciplinary research team at the Technical University of Munich (TUM) has built platinum nanoparticles for catalysis in fuel cells: The new size-optimized catalysts are twice as good as the best process commercially available today.
Fuel cells may well replace batteries as the power source for electric cars. They consume hydrogen, a gas which could be produced for example using surplus...
The fly agaric with its red hat is perhaps the most evocative of the diverse and variously colored mushroom species. Hitherto, the purpose of these colors was...
Physicists at the Max Planck Institute for Nuclear Physics in Heidelberg report the first result of the new Alphatrap experiment. They measured the bound-electron g-factor of highly charged (boron-like) argon ions with unprecedented precision of 9 digits. In comparison with a new highly accurate quantum electrodynamic calculation they found an excellent agreement on a level of 7 digits. This paves the way for sensitive tests of QED in strong fields like precision measurements of the fine structure constant α as well as the detection of possible signatures of new physics. [Physical Review Letters, 27 June 2019]
Quantum electrodynamics (QED) describes the interaction of charged particles with electromagnetic fields and is the most precisely tested physical theory. It...
For the first time ever, experimental physicists have been able to influence the magnetic moment of materials in sync with their electronic properties. The coupled optical and magnetic excitation within one femtosecond corresponds to an acceleration by a factor of 200 and is the fastest magnetic phenomenon that has ever been observed.
Electronic properties of materials can be directly influenced via light absorption in under a femtosecond (10-15 seconds), which is regarded as the limit of...
From June 25th to 27th 2019, the Fraunhofer Institute for Digital Media Technology IDMT in Ilmenau (Germany) will be presenting a new solution for acoustic quality inspection allowing contact-free, non-destructive testing of manufactured parts and components. The method which has reached Technology Readiness Level 6 already, is currently being successfully tested in practical use together with a number of industrial partners.
Reducing machine downtime, manufacturing defects, and excessive scrap
24.06.2019 | Event News
29.04.2019 | Event News
17.04.2019 | Event News
03.07.2019 | Information Technology
03.07.2019 | Physics and Astronomy
03.07.2019 | Materials Sciences