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

Training data selection for accuracy and transferability of interatomic potentials

Journal Article · · npj Computational Materials

Abstract

Advances in machine learning (ML) have enabled the development of interatomic potentials that promise the accuracy of first principles methods and the low-cost, parallel efficiency of empirical potentials. However, ML-based potentials struggle to achieve transferability, i.e., provide consistent accuracy across configurations that differ from those used during training. In order to realize the promise of ML-based potentials, systematic and scalable approaches to generate diverse training sets need to be developed. This work creates a diverse training set for tungsten in an automated manner using an entropy optimization approach. Subsequently, multiple polynomial and neural network potentials are trained on the entropy-optimized dataset. A corresponding set of potentials are trained on an expert-curated dataset for tungsten for comparison. The models trained to the entropy-optimized data exhibited superior transferability compared to the expert-curated models. Furthermore, the models trained to the expert-curated set exhibited a significant decrease in performance when evaluated on out-of-sample configurations.

Sponsoring Organization:
USDOE
OSTI ID:
1885072
Alternate ID(s):
OSTI ID: 1888547
OSTI ID: 1974929
Journal Information:
npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 8; ISSN 2057-3960
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (52)

Principal Component Analysis book January 2005
Materials informatics journal January 2018
Key computational modeling issues in Integrated Computational Materials Engineering journal January 2013
Analysis on block chain financial transaction under artificial neural network of deep learning journal December 2020
Physics-informed neural networks for high-speed flows journal March 2020
A physics-informed operator regression framework for extracting data-driven continuum models journal January 2021
Active learning of linearly parametrized interatomic potentials journal December 2017
Considerations for choosing and using force fields and interatomic potentials in materials science and engineering journal December 2013
LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales journal February 2022
Data-driven modeling and learning in science and engineering journal November 2019
Machine learning guided association of adverse drug reactions with in vitro target-based pharmacology journal July 2020
Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials journal March 2015
Thermodynamically consistent physics-informed neural networks for hyperbolic systems journal January 2022
Using deep neural network with small dataset to predict material defects journal January 2019
Synergistic target combination prediction from curated signaling networks: Machine learning meets systems biology and pharmacology journal October 2017
Physics-Inspired Structural Representations for Molecules and Materials journal July 2021
Explicit Multielement Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems journal May 2020
Performance and Cost Assessment of Machine Learning Interatomic Potentials journal October 2019
Large-scale prediction and testing of drug activity on side-effect targets journal June 2012
Deep learning journal May 2015
Probing the limits of metal plasticity with molecular dynamics simulations journal September 2017
Anomalous collapses of Nares Strait ice arches leads to enhanced export of Arctic sea ice journal January 2021
Discovering the building blocks of atomic systems using machine learning: application to grain boundaries journal August 2017
De novo exploration and self-guided learning of potential-energy surfaces journal October 2019
On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events journal March 2020
Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon journal June 2021
Machine learning for molecular and materials science journal July 2018
Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis journal September 2019
Machine learning molecular dynamics for the simulation of infrared spectra journal January 2017
Development of interatomic potential for Al–Tb alloys using a deep neural network learning method journal January 2020
Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations journal January 2011
Discovering governing equations from data by sparse identification of nonlinear dynamical systems journal March 2016
Evaluating variability with atomistic simulations: the effect of potential and calculation methodology on the modeling of lattice and elastic constants journal May 2018
Using convolutional neural networks to identify gravitational lenses in astronomical images journal May 2019
Ab initiomolecular dynamics for liquid metals journal January 1993
Projector augmented-wave method journal December 1994
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set journal October 1996
From ultrasoft pseudopotentials to the projector augmented-wave method journal January 1999
Neural network interatomic potential for the phase change material GeTe journal May 2012
On representing chemical environments journal May 2013
Accuracy and transferability of Gaussian approximation potential models for tungsten journal September 2014
Atomic cluster expansion for accurate and transferable interatomic potentials journal January 2019
Data-driven material models for atomistic simulation journal May 2019
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons journal April 2010
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces journal April 2007
Intelligent Optimal Control With Critic Learning for a Nonlinear Overhead Crane System journal July 2018
Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials journal January 2016
Quantum Theory of Angular Momentum book October 1988
Trillion-Atom Molecular Dynamics Becomes a Reality journal September 2008
Billion atom molecular dynamics simulations of carbon at extreme conditions and experimental time and length scales
  • Nguyen-Cong, Kien; Willman, Jonathan T.; Moore, Stan G.
  • Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis https://doi.org/10.1145/3458817.3487400
conference November 2021
Computational aspects of many-body potentials journal May 2012
The application of Principal Component Analysis to materials science data journal January 2002

Similar Records

An Entropy-Maximization Approach to Automated Training Set Generation for Interatomic Potentials
Journal Article · Mon Sep 07 00:00:00 EDT 2020 · Journal of Chemical Physics · OSTI ID:1813845

Related Subjects