Training data selection for accuracy and transferability of interatomic potentials
Open Access
- 1 September 2022
- journal article
- research article
- Published by Springer Nature in npj Computational Materials
- Vol. 8 (1) , 1-9
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.Keywords
All Related Versions
Funding Information
- DOE | SC | Fusion Energy Sciences (20-023149, 20-023149, 20-023149, 20-023149, 20-023149, 20-023149)
- DOE | Office of Science (17-SC-20-SC, 17-SC-20-SC, 17-SC-20-SC)
- DOE | National Nuclear Security Administration (17-SC-20-SC, 17-SC-20-SC, 17-SC-20-SC, 17-SC-20-SC)
This publication has 52 references indexed in Scilit:
- Large-scale prediction and testing of drug activity on side-effect targetsNature, 2012
- Computational aspects of many-body potentialsMRS Bulletin, 2012
- Neural network potential-energy surfaces in chemistry: a tool for large-scale simulationsPhysical Chemistry Chemical Physics, 2011
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- Principal Component Analysis2005
- The application of Principal Component Analysis to materials science dataData Science Journal, 2002
- From ultrasoft pseudopotentials to the projector augmented-wave methodPhysical Review B, 1999
- Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis setPhysical Review B, 1996
- Projector augmented-wave methodPhysical Review B, 1994
- Ab initiomolecular dynamics for liquid metalsPhysical Review B, 1993