Machine learning forces trained by Gaussian process in liquid states: Transferability to temperature and pressure

Abstract

We study a generalization performance of the machine learning (ML) model to predict the atomic forces within the density functional theory (DFT). The targets are the Si and Ge single component systems in the liquid state. To train the machine learning model, Gaussian process regression is performed with the atomic fingerprints which express the local structure around the target atom. The training and test data are generated by the molecular dynamics (MD) based on DFT. We first report the accuracy of ML forces when both test and training data are generated from the DFT-MD simulations at a same temperature. By comparing the accuracy of ML forces at various temperatures, it is found that the accuracy becomes the lowest around the phase boundary between the solid and the liquid states. Furthermore, we investigate the transferability of ML models trained in the liquid state to temperature and pressure. We demonstrate that, if the training is performed at a high temperature and if the volume change is not so large, the transferability of ML forces in the liquid state is high enough, while its transferability to the solid state is very low.

21 pages, 8 figures

References in corpus (20)

• The SIESTA method for ab initio order-N materials simulation
• Efficient index handling of multidimensional periodic boundary conditions
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Machine Learning Unifies the Modelling of Materials and Molecules
• By-passing the Kohn-Sham equations with machine learning
• Machine-learning based interatomic potential for amorphous carbon
• Finding Density Functionals with Machine Learning
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Discovery of low thermal conductivity compounds with first-principles anharmonic lattice dynamics calculations and Bayesian optimization
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Recent progress with large-scale ab initio calculations: the CONQUEST code
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Designing nanostructures for interfacial phonon transport via Bayesian optimization
• Machine Learning for Atomic Forces in a Crystalline Solid: Transferability to Various Temperatures
• Bayesian optimization for computationally extensive probability distributions
• Method for Estimating Spin-Spin Interactions from Magnetization Curves
• Size and Temperature Transferability of Direct and Local Deep Neural Networks for Atomic Forces
• Canonical-ensemble extended Lagrangian Born-Oppenheimer molecular dynamics for the linear scaling density functional theory

Cited by in corpus (4)

• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Machine Learning Directed Optimization of Classical Molecular Modeling Force Fields
• Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations
• Data-driven determination of the spin Hamiltonian parameters and their uncertainties: The case of the zigzag-chain compound KCu${}_4$P${}_3$O${}_{12}$