Research output: Contribution to journal › Article › peer-review

**Calculation of proper energy barriers for atomistic kinetic Monte Carlo simulations on rigid lattice with chemical and strain field long-range effects using artificial neural networks.** / Castin, Nicolas; Malerba, Lorenzo; Terentyev, Dmitry (Peer reviewer); Bonny, Giovanni (Peer reviewer).

Research output: Contribution to journal › Article › peer-review

Castin, N, Malerba, L, Terentyev, D & Bonny, G 2010, 'Calculation of proper energy barriers for atomistic kinetic Monte Carlo simulations on rigid lattice with chemical and strain field long-range effects using artificial neural networks', *The Journal of Chemical Physics*, vol. 132, no. 7, pp. 074507-074507. https://doi.org/10.1063/1.3298990

Castin, N., Malerba, L., Terentyev, D., & Bonny, G. (2010). Calculation of proper energy barriers for atomistic kinetic Monte Carlo simulations on rigid lattice with chemical and strain field long-range effects using artificial neural networks. *The Journal of Chemical Physics*, *132*(7), 074507-074507. https://doi.org/10.1063/1.3298990

Castin N, Malerba L, Terentyev D, Bonny G. Calculation of proper energy barriers for atomistic kinetic Monte Carlo simulations on rigid lattice with chemical and strain field long-range effects using artificial neural networks. The Journal of Chemical Physics. 2010 Feb 21;132(7):074507-074507. https://doi.org/10.1063/1.3298990

@article{91e9c3e5c44f4ddf881dd1fc4e28c836,

title = "Calculation of proper energy barriers for atomistic kinetic Monte Carlo simulations on rigid lattice with chemical and strain field long-range effects using artificial neural networks",

abstract = "In this paper we take a few steps further in the development of an approach based on the use of an artificial neural network ANN to introduce long-range chemical effects and zero temperature relaxation elastic strain effects in a rigid lattice atomistic kinetic Monte Carlo AKMC model. The ANN is trained to predict the vacancy migration energies as calculated given an interatomic potential with the nudged elastic band method, as functions of the local atomic environment. The kinetics of a single-vacancy migration is thus predicted as accurately as possible, within the limits of the given interatomic potential. The detailed procedure to apply this method is described and analyzed in detail. A novel ANN training algorithm is proposed to deal with the necessarily large number of input variables to be taken into account in the mathematical regression of the migration energies. The application of the ANN-basedAKMC method to the simulation of a thermal annealing experiment in Fe–20%Cr alloy is reported. The results obtained are found to be in better agreement with experiments, as compared to already published simulations, where no atomic relaxation was taken into account and chemical effects were only heuristically allowed for.",

keywords = "Artificial Neural Networks, vacancy migration, Atomistic Kinetic Monte Carlo, thermal annealing",

author = "Nicolas Castin and Lorenzo Malerba and Dmitry Terentyev and Giovanni Bonny",

note = "Score = 10",

year = "2010",

month = feb,

day = "21",

doi = "10.1063/1.3298990",

language = "English",

volume = "132",

pages = "074507--074507",

journal = "The Journal of Chemical Physics",

issn = "1089-7690",

publisher = "AIP - American Institute of Physics",

number = "7",

}

TY - JOUR

T1 - Calculation of proper energy barriers for atomistic kinetic Monte Carlo simulations on rigid lattice with chemical and strain field long-range effects using artificial neural networks

AU - Castin, Nicolas

AU - Malerba, Lorenzo

A2 - Terentyev, Dmitry

A2 - Bonny, Giovanni

N1 - Score = 10

PY - 2010/2/21

Y1 - 2010/2/21

N2 - In this paper we take a few steps further in the development of an approach based on the use of an artificial neural network ANN to introduce long-range chemical effects and zero temperature relaxation elastic strain effects in a rigid lattice atomistic kinetic Monte Carlo AKMC model. The ANN is trained to predict the vacancy migration energies as calculated given an interatomic potential with the nudged elastic band method, as functions of the local atomic environment. The kinetics of a single-vacancy migration is thus predicted as accurately as possible, within the limits of the given interatomic potential. The detailed procedure to apply this method is described and analyzed in detail. A novel ANN training algorithm is proposed to deal with the necessarily large number of input variables to be taken into account in the mathematical regression of the migration energies. The application of the ANN-basedAKMC method to the simulation of a thermal annealing experiment in Fe–20%Cr alloy is reported. The results obtained are found to be in better agreement with experiments, as compared to already published simulations, where no atomic relaxation was taken into account and chemical effects were only heuristically allowed for.

AB - In this paper we take a few steps further in the development of an approach based on the use of an artificial neural network ANN to introduce long-range chemical effects and zero temperature relaxation elastic strain effects in a rigid lattice atomistic kinetic Monte Carlo AKMC model. The ANN is trained to predict the vacancy migration energies as calculated given an interatomic potential with the nudged elastic band method, as functions of the local atomic environment. The kinetics of a single-vacancy migration is thus predicted as accurately as possible, within the limits of the given interatomic potential. The detailed procedure to apply this method is described and analyzed in detail. A novel ANN training algorithm is proposed to deal with the necessarily large number of input variables to be taken into account in the mathematical regression of the migration energies. The application of the ANN-basedAKMC method to the simulation of a thermal annealing experiment in Fe–20%Cr alloy is reported. The results obtained are found to be in better agreement with experiments, as compared to already published simulations, where no atomic relaxation was taken into account and chemical effects were only heuristically allowed for.

KW - Artificial Neural Networks

KW - vacancy migration

KW - Atomistic Kinetic Monte Carlo

KW - thermal annealing

UR - http://ecm.sckcen.be/OTCS/llisapi.dll/open/ezp_104123

UR - http://knowledgecentre.sckcen.be/so2/bibref/6790

U2 - 10.1063/1.3298990

DO - 10.1063/1.3298990

M3 - Article

VL - 132

SP - 74507

EP - 74507

JO - The Journal of Chemical Physics

JF - The Journal of Chemical Physics

SN - 1089-7690

IS - 7

ER -

ID: 382639