Accelerated identification of equilibrium structures of multicomponent inorganic crystals using machine learning potentials

Abstract

The discovery of new multicomponent inorganic compounds can provide direct solutions to many scientific and engineering challenges, yet the vast size of the uncharted material space dwarfs current synthesis throughput. While the computational crystal structure prediction is expected to mitigate this frustration, the NP-hardness and steep costs of density functional theory (DFT) calculations prohibit material exploration at scale. Herein, we introduce SPINNER, a highly efficient and reliable structure-prediction framework based on exhaustive random searches and evolutionary algorithms, which is completely free from empiricism. Empowered by accurate neural network potentials, the program can navigate the configuration space faster than DFT by more than 10${}^2$-fold. In blind tests on 60 ternary compositions diversely selected from the experimental database, SPINNER successfully identifies experimental (or theoretically more stable) phases for ~80% of materials within 5000 generations, entailing up to half a million structure evaluations for each composition. When benchmarked against previous data mining or DFT-based evolutionary predictions, SPINNER identifies more stable phases in the majority of cases. By developing a reliable and fast structure-prediction framework, this work opens the door to large-scale, unbounded computational exploration of undiscovered inorganic crystals.

3 figures

References in corpus (9)

• Restoring the density-gradient expansion for exchange in solids and surfaces
• Generalized gradient approximation for solids and their surfaces
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Prediction and accelerated laboratory discovery of previously unknown 18-electron ABX compounds
• High-Dimensional Neural Network Potentials for Magnetic Systems Using Spin-Dependent Atom-Centered Symmetry Functions
• Training machine-learning potentials for crystal structure prediction using disordered structures
• Active Learning A Neural Network Model For Gold Clusters \& Bulk From Sparse First Principles Training Data
• Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials
• Large Scale Structure Prediction of Near-Stoichiometric Magnesium Oxide Based on a Machine-Learned Interatomic Potential: Novel Crystalline Phases and Oxygen-Vacancy Ordering

Cited by in corpus (3)

• How Graph Neural Network Interatomic Potentials Extrapolate: Role of the Message-Passing Algorithm
• Transferable empirical pseudopotenials from machine learning
• Machine learning search for stable binary Sn alloys with Na, Ca, Cu, Pd, and Ag