Energy-free machine learning force field for aluminum
Open Access
- 17 August 2017
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 7 (1) , 1-7
Abstract
We used the machine learning technique of Liet al. (PRL 114, 2015) for molecular dynamics simulations. Atomic configurations were described by feature matrix based on internal vectors, and linear regression was used as a learning technique. We implemented this approach in the LAMMPS code. The method was applied to crystalline and liquid aluminum and uranium at different temperatures and densities, and showed the highest accuracy among different published potentials. Phonon density of states, entropy and melting temperature of aluminum were calculated using this machine learning potential. The results are in excellent agreement with experimental data and results of full ab initio calculations.Keywords
This publication has 44 references indexed in Scilit:
- CHARMM general force field: A force field for drug‐like molecules compatible with the CHARMM all‐atom additive biological force fieldsJournal of Computational Chemistry, 2009
- A thermodynamic approach to determine accurate potentials for molecular dynamics simulations: thermoelastic response of aluminumModelling and Simulation in Materials Science and Engineering, 2009
- Metadynamics Simulations of the High-Pressure Phases of Silicon Employing a High-Dimensional Neural Network PotentialPhysical Review Letters, 2008
- Entropy Driven Stabilization of Energetically Unstable Crystal Structures Explained from First Principles TheoryPhysical Review Letters, 2008
- Phonons in aluminum at high temperatures studied by inelastic neutron scatteringPhysical Review B, 2008
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- Angular-dependent interatomic potential for tantalumActa Materialia, 2006
- ReaxFF: A Reactive Force Field for HydrocarbonsThe Journal of Physical Chemistry A, 2001
- Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis setPhysical Review B, 1996
- Analytic embedded atom method model for bcc metalsJournal of Materials Research, 1989