Instructions and scripts for growing machine learning interatomic potentials (MLIPs) databases through adaptive sampling for gas-surface dynamics.
- High-error structure search using NQCDynamics.jl.
- Structure selection (clustering) for database reduction.
W. G. Stark, J. Westermayr, O. A. Douglas-Gallardo, J. Gardner, S. Habershon, R. J. Maurer, Importance of equivariant features in machine-learning interatomic potentials for reactive chemistry at metal surfaces, arXiv:2305.10873 [arxiv]
J. Gardner, O. A. Douglas-Gallardo, W. G. Stark, J. Westermayr, S. M. Janke, S. Habershon, R. J. Maurer, NQCDynamics.jl: A Julia package for nonadiabatic quantum classical molecular dynamics in the condensed phase, J. Chem. Phys. 156, 174801 (2022) [DOI]