Impact of training and validation data on the performance of neural network potentials: A case study on carbon using the CA-9 dataset

Impact of training and validation data on the performance of neural network potentials: A case study on carbon using the CA-9 dataset

The use of machine learning to accelerate computer simulations is on the rise. In atomistic simulations, the use of machine learning interatomic potentials (ML-IAPs) can significantly reduce computational costs while maintaining accuracy close to that of ab initio methods. To achieve this, ML-IAPs a...

Full description

Bibliographic Details
Main Authors: Daniel Hedman, Tom Rothe, Gustav Johansson, Fredrik Sandin, J. Andreas Larsson, Yoshiyuki Miyamoto
Format: Article
Language:English
Published: Elsevier 2021-04-01
Series:Carbon Trends
Subjects:
CA-9
Dataset
Machine learning
Interatomic potential
Carbon
Neural network potential
Online Access:http://www.sciencedirect.com/science/article/pii/S2667056921000043

Internet

http://www.sciencedirect.com/science/article/pii/S2667056921000043

Similar Items