Ab initio quality neural-network potential for sodium

Abstract

An interatomic potential for high-pressure high-temperature (HPHT) crystalline and liquid phases of sodium is created using a neural-network (NN) representation of the ab initio potential energy surface. It is demonstrated that the NN potential provides an ab initio quality description of multiple properties of liquid sodium and bcc, fcc, cI16 crystal phases in the P-T region up to 120 GPa and 1200 K. The unique combination of computational efficiency of the NN potential and its ability to reproduce quantitatively experimental properties of sodium in the wide P-T range enables molecular dynamics simulations of physicochemical processes in HPHT sodium of unprecedented quality.

arXiv comment8 pages, 11 figures, 2 tables

References in corpus (6)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Predicting crystal structures: the Parrinello-Rahman method revisited
• Transparent dense sodium
• Langevin equation with colored noise for constant-temperature molecular dynamics simulations
• Representing molecule-surface interactions with symmetry-adapted neural networks
• Structure, elastic moduli and thermodynamics of sodium and potassium at ultra-high pressures

Cited by in corpus (30)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Machine-learning based interatomic potential for amorphous carbon
• Machine-learning interatomic potentials for materials science
• Nucleation mechanism for the direct graphite-to-diamond phase transition
• Physically-informed artificial neural networks for atomistic modeling of materials
• A neural network interatomic potential for the phase change material GeTe
• De novo exploration and self-guided learning of potential-energy surfaces
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• A sparse representation for potential energy surface
• Deep Learning of Accurate Force Field of Ferroelectric HfO${}_2$
• First-principles interatomic potentials for ten elemental metals via compressed sensing
• Stratified construction of neural network based interatomic models for multicomponent materials
• First-principles calculation of entropy for liquid metals
• Microscopic origins of the anomalous melting behaviour of high-pressure sodium
• Graph Neural Networks Accelerated Molecular Dynamics
• MAISE: Construction of neural network interatomic models and evolutionary structure optimization
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
• Development of a physically-informed neural network interatomic potential for tantalum
• Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo
• A slave mode expansion for obtaining ab-initio interatomic potentials
• Structure of the glass-forming metallic liquids by ab-initio and classical molecular dynamics, a case study: quenching the Cu60Ti20Zr20 alloy
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Large Scale Structure Prediction of Near-Stoichiometric Magnesium Oxide Based on a Machine-Learned Interatomic Potential: Novel Crystalline Phases and Oxygen-Vacancy Ordering
• Neural-networks model for force prediction in multi-principal-element alloys
• Critical assessment of machine-learned repulsive potentials for the Density Functional based Tight-Binding method: a case study for pure silicon
• Liquid metals: early contributions and some recent developments
• Scalable Training of Neural Network Potentials for Complex Interfaces Through Data Augmentation
• Pairwise interactions for Potential energy surfaces and Atomic forces with Deep Neural network
• Machine learning reveals orbital interaction in crystalline materials