Projects per year
Abstract
We develop a neuroevolution-potential (NEP) framework for generating neural network-based machine-learning potentials. They are trained using an evolutionary strategy for performing large-scale molecular dynamics (MD) simulations. A descriptor of the atomic environment is constructed based on Chebyshev and Legendre polynomials. The method is implemented in graphic processing units within the open-source gpumd package, which can attain a computational speed over atom-step per second using one Nvidia Tesla V100. Furthermore, per-atom heat current is available in NEP, which paves the way for efficient and accurate MD simulations of heat transport in materials with strong phonon anharmonicity or spatial disorder, which usually cannot be accurately treated either with traditional empirical potentials or with perturbative methods.
Original language | English |
---|---|
Article number | 104309 |
Number of pages | 15 |
Journal | Physical Review B |
Volume | 104 |
Issue number | 10 |
DOIs | |
Publication status | Published - 18 Sep 2021 |
MoE publication type | A1 Journal article-refereed |
Fingerprint
Dive into the research topics of 'Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Finnish Centre of Excellence in Quantum Technology
Alipour, S., Ala-Nissilä, T., Fan, Z., Tuorila, J. & Hirvonen, P.
01/01/2018 → 31/12/2020
Project: Academy of Finland: Other research funding