Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
Top Cited Papers
- 2 April 2007
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 98 (14), 146401
- https://doi.org/10.1103/physrevlett.98.146401
Abstract
The accurate description of chemical processes often requires the use of computationally demanding methods like density-functional theory (DFT), making long simulations of large systems unfeasible. In this Letter we introduce a new kind of neural-network representation of DFT potential-energy surfaces, which provides the energy and forces as a function of all atomic positions in systems of arbitrary size and is several orders of magnitude faster than DFT. The high accuracy of the method is demonstrated for bulk silicon and compared with empirical potentials and DFT. The method is general and can be applied to all types of periodic and nonperiodic systems.Keywords
This publication has 17 references indexed in Scilit:
- Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networksChemical Physics Letters, 2004
- Effective force fields for condensed phase systems from ab initio molecular dynamics simulation: A new method for force-matchingThe Journal of Chemical Physics, 2004
- High-pressure phases of group-IV, III–V, and II–VI compoundsReviews of Modern Physics, 2003
- Physics of Iron at Earth's Core ConditionsScience, 2000
- Neural network models of potential energy surfacesThe Journal of Chemical Physics, 1995
- Hybrid Monte Carlo: An efficient algorithm for condensed matter simulationJournal of Computational Chemistry, 1994
- Interatomic Potentials from First-Principles Calculations: The Force-Matching MethodEurophysics Letters, 1994
- Soft self-consistent pseudopotentials in a generalized eigenvalue formalismPhysical Review B, 1990
- Hybrid Monte CarloPhysics Letters B, 1987
- Self-Consistent Equations Including Exchange and Correlation EffectsPhysical Review B, 1965