General-purpose machine-learned potential for 16 elemental metals and their alloys

TL;DR

This paper introduces UNEP-v1, a general-purpose machine-learned potential for 16 elemental metals and their alloys, achieving high accuracy and efficiency for diverse physical properties and large-scale simulations.

Contribution

The paper presents a novel approach to constructing a unified MLP applicable to multiple elements and alloys, demonstrating its effectiveness across various physical properties and large-scale simulations.

Findings

UNEP-v1 outperforms traditional potentials in accuracy

Effective representation of chemical space with minimal systems

Successful large-scale simulations of alloy behavior

Abstract

Machine-learned potentials (MLPs) have exhibited remarkable accuracy, yet the lack of general-purpose MLPs for a broad spectrum of elements and their alloys limits their applicability. Here, we present a feasible approach for constructing a unified general-purpose MLP for numerous elements, demonstrated through a model (UNEP-v1) for 16 elemental metals and their alloys. To achieve a complete representation of the chemical space, we show, via principal component analysis and diverse test datasets, that employing one-component and two-component systems suffices. Our unified UNEP-v1 model exhibits superior performance across various physical properties compared to a widely used embedded-atom method potential, while maintaining remarkable efficiency. We demonstrate our approach's effectiveness through reproducing experimentally observed chemical order and stable phases, and large-scale simulations of plasticity and primary radiation damage in MoTaVW alloys. This work represents a significant leap towards a unified general-purpose MLP encompassing the periodic table, with profound implications for materials science.