Application of artificial neural networks for rigid lattice kinetic Monte Carlo studies of Cu surface diffusion

Kinetic Monte Carlo (KMC) is a powerful method for simulation of diffusion processes in various systems. The accuracy of the method, however, relies on the extent of details used for the parameterization of the model. Migration barriers are often used to describe diffusion on atomic scale, but the f...

Full description

Saved in:
Bibliographic Details
Published in:Computational materials science 2020-10, Vol.183, p.109789, Article 109789
Main Authors: Kimari, Jyri, Jansson, Ville, Vigonski, Simon, Baibuz, Ekaterina, Domingos, Roberto, Zadin, Vahur, Djurabekova, Flyura
Format: Article
Language:English
Subjects:
Artificial neural networks
Copper
Kinetic Monte Carlo
Machine learning
Migration barriers
Surface diffusion
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Kinetic Monte Carlo (KMC) is a powerful method for simulation of diffusion processes in various systems. The accuracy of the method, however, relies on the extent of details used for the parameterization of the model. Migration barriers are often used to describe diffusion on atomic scale, but the full set of these barriers may become easily unmanageable in materials with increased chemical complexity or a large number of defects. This work is a feasibility study for applying a machine learning approach for Cu surface diffusion. We train an artificial neural network on a subset of the large set of 226 barriers needed to correctly describe the surface diffusion in Cu. Our KMC simulations using the obtained barrier predictor show sufficient accuracy in modelling processes on the low-index surfaces and display the correct thermodynamical stability of these surfaces.
ISSN:0927-0256
1879-0801
DOI:10.1016/j.commatsci.2020.109789