Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements

TL;DR

This paper introduces PreFerred Potential (PFP), a universal neural network potential capable of modeling any combination of 45 elements, facilitating broad material discovery applications.

Contribution

The paper presents a novel universal neural network potential, PFP, trained on diverse virtual structures to handle arbitrary element combinations for material discovery.

Findings

Successfully modeled lithium diffusion in LiFeSO4F

Predicted molecular adsorption in metal-organic frameworks

Simulated order-disorder transition in Cu-Au alloys

Abstract

Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. To overcome this issue, we have developed a universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, which include a diverse set of virtual structures used to attain the universality. We demonstrated the applicability of PFP in selected domains: lithium diffusion in LiFeSO${}_4$F, molecular adsorption in metal-organic frameworks, an order-disorder transition of Cu-Au alloys, and material discovery for a Fischer-Tropsch catalyst. They showcase the power of PFP, and this technology provides a highly useful tool for material discovery.