Training machine-learning potentials for crystal structure prediction using disordered structures

Abstract

Prediction of the stable crystal structure for multinary (ternary or higher) compounds with unexplored compositions demands fast and accurate evaluation of free energies in exploring the vast configurational space. The machine-learning potential such as the neural network potential (NNP) is poised to meet this requirement but a dearth of information on the crystal structure poses a challenge in choosing training sets. Herein we propose constructing the training set from densityfunctional-theory (DFT) based dynamical trajectories of liquid and quenched amorphous phases, which does not require any preceding information on material structures except for the chemical composition. To demonstrate suitability of the trained NNP in the crystal structure prediction, we compare NNP and DFT energies for Ba2AgSi3, Mg2SiO4, LiAlCl4, and InTe2O5F over experimental phases as well as low-energy crystal structures that are generated theoretically. For every material, we find strong correlations between DFT and NNP energies, ensuring that the NNPs can properly rank energies among low-energy crystalline structures. We also find that the evolutionary search using the NNPs can identify low-energy metastable phases more efficiently than the DFTbased approach. By proposing a way to developing reliable machine-learning potentials for the crystal structure prediction, this work will pave the way to identifying unexplored multinary phases efficiently.

arXiv comment8 pages, 5 figures

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms
• Crystal Structure Prediction via Particle Swarm Optimization
• Ab initio Random Structure Searching
• Predicting crystal structures: the Parrinello-Rahman method revisited
• High-pressure phases of silane
• Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
• Pressure-induced decomposition of solid hydrogen sulfide
• Data-driven learning of total and local energies in elemental boron
• Constrained evolutionary algorithm for structure prediction of molecular crystals: methodology and applications
• Accelerating CALYPSO Structure Prediction by Data-driven Learning of Potential Energy Surface
• Prediction of High-Tc conventional Superconductivity in the Ternary Lithium Borohydride System
• Atomic energy mapping of neural network potential
• Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction

Cited by in corpus (5)

• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Tuning Chemical Precompression: Theoretical Design and Crystal Chemistry of Novel Hydrides in the Quest for Warm and Light Superconductivity at Ambient Pressures
• Accelerated identification of equilibrium structures of multicomponent inorganic crystals using machine learning potentials
• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials