On-the-fly machine learning force field generation: Application to melting points
By Ryosuke Jinnouchi, Ferenc Karsai, Georg Kresse. Physical review B, 2019
386 citations recorded by the source corpus.
An on-the-fly force field generation method is developed and applied to liquid-solid phase transitions. The method allows the machine to automatically self-learn interatomic potentials during molecular dynamics simulations and to generate force fields with the distinctive chemical precision of first-principles methods. Applications show that more than 99% of the expensive first-principles calculations are bypassed, and molecular dynamics simulations are accelerated by more than two orders of magnitude already during learning, with many more orders during production runs.
Subfields: Computational Mechanics, Materials Chemistry, Molecular Biology
View Paper: https://www.semanticscholar.org/paper/6ded71db6b6fbab0dfa53217ef9df7f92d379d1c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
In Materials Chemistry
- Yuri Mishin
- Evgeny V. Podryabinkin
- Konstantin Gubaev
- Ivan S. Novikov
- Alexander V. Shapeev
- Gábor Csányi
- Xianglin Liu
- Jiaxin Zhang
In Molecular Biology
Citations in the corpus
- Machine-Learning Interatomic Potentials for Materials Science (2021, methodology): “It has been shown, however, DFT melting point calculations can be accelerated by constructing a ML on-the-fly potential using the Bayesian inference approach [118].”
- The MLIP package: moment tensor potentials with MPI and active learning (2020, methodology): “Gaussian process-based potentials have another natural query strategy—predictive variance [32, 76].”