Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Machine learning interatomic potential for silicon-nitride (Si3N4) by active learning

Journal Article · · Journal of Chemical Physics
DOI:https://doi.org/10.1063/5.0146753· OSTI ID:2404406
 [1];  [1];  [1];  [1];  [2];  [1]
  1. Vienna Univ. of Technology (Austria)
  2. Argonne National Laboratory (ANL), Argonne, IL (United States)
+ Show Author Affiliations
Silicon nitride (Si3N4) is an extensively used material in the automotive, aerospace, and semiconductor industries. However, its widespread use is in contrast to the scarce availability of reliable interatomic potentials that can be employed to study various aspects of this material on an atomistic scale, particularly its amorphous phase. In this work, we developed a machine learning interatomic potential, using an efficient active learning technique, combined with the Gaussian approximation potential (GAP) method. Our strategy is based on using an inexpensive empirical potential to generate an initial dataset of atomic configurations, for which energies and forces were recalculated with density functional theory (DFT); thereafter, a GAP was trained on these data and an iterative re-training algorithm was used to improve it by learning on-the-fly. When compared to DFT, our potential yielded a mean absolute error of 8 meV/atom in energy calculations for a variety of liquid and amorphous structures and a speed-up of molecular dynamics simulations by 3–4 orders of magnitude, while achieving a first-rate agreement with experimental results. Our potential is publicly available in an open-access repository.
Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); European Union (EU)
Grant/Contract Number:
AC02-06CH11357
OSTI ID:
2404406
Journal Information:
Journal of Chemical Physics, Journal Name: Journal of Chemical Physics Journal Issue: 19 Vol. 158; ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)Copyright Statement
Country of Publication:
United States
Language:
English

References (27)

Development and testing of a general amber force field journal January 2004
Constructing high-dimensional neural network potentials: A tutorial review journal March 2015
An X-ray diffraction study of the amorphous structure of chemically vapor-deposited silicon nitride journal June 1979
Quickstep: Fast and accurate density functional calculations using a mixed Gaussian and plane waves approach journal April 2005
Amp: A modular approach to machine learning in atomistic simulations journal October 2016
DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics journal July 2018
PANNA: Properties from Artificial Neural Network Architectures journal November 2020
Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide journal July 2020
A machine-learned interatomic potential for silica and its relation to empirical models journal April 2022
Hydrogen role on the properties of amorphous silicon nitride journal August 1999
Representing potential energy surfaces by high-dimensional neural network potentials journal April 2014
QuantumATK: an integrated platform of electronic and atomic-scale modelling tools journal October 2019
f90wrap: an automated tool for constructing deep Python interfaces to modern Fortran codes journal May 2020
Ab initio derived augmented Tersoff potential for silicon oxynitride compounds and their interfaces with silicon journal April 2006
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces journal April 2007
Separable dual-space Gaussian pseudopotentials journal July 1996
Effect of topological disorder on structural, mechanical, and electronic properties of amorphous silicon nitride: An atomistic study journal May 2012
On representing chemical environments journal May 2013
Machine learning based interatomic potential for amorphous carbon journal March 2017
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons journal April 2010
Unified Approach for Molecular Dynamics and Density-Functional Theory journal November 1985
Generalized Gradient Approximation Made Simple journal October 1996
Machine Learning a General-Purpose Interatomic Potential for Silicon journal December 2018
Silicon Nitride and Related Materials journal February 2000
Modification of the nonlinear optical absorption and optical Kerr response exhibited by nc-Si embedded in a silicon-nitride film journal June 2009
Silicon nitride as antireflection coating to enhance the conversion efficiency of silicon solar cells journal August 2018
A Combined Machine Learning and High-Energy X-ray Diffraction Approach to Understanding Liquid and Amorphous Metal Oxides journal September 2022

Similar Records

A deep learning interatomic potential developed for atomistic simulation of carbon materials
Journal Article · Fri Oct 01 00:00:00 EDT 2021 · Carbon · OSTI ID:1833551

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY