Nine-element machine-learned interatomic potentials for multiphase refractory alloys

TL;DR

This paper introduces two new machine-learned interatomic potentials, tabGAP and NEP, for simulating multiphase refractory alloys with high accuracy and efficiency, supporting diverse compositions and phases.

Contribution

The authors developed a comprehensive refractory alloy database and two general-purpose machine-learned potentials with a novel cross-sampling strategy for improved training.

Findings

Successfully reproduced phase transitions under various conditions

Simulated grain boundary segregation accurately

Modeled radiation damage in metallic glass

Abstract

New refractory alloys are being continuously designed and characterised for applications requiring good high-temperature mechanical properties and stability. Computational design from atomistic simulations is limited by interatomic potentials missing key elements, being too inaccurate, or computationally too slow for large-scale simulations. Here we present development of a refractory alloy database and two computationally efficient and general-purpose machine-learned potentials (tabGAP and NEP). We also design a cross-sampling strategy for effective sampling of training data using predictions from two potentials with completely different underlying architecture. The potentials support arbitrary alloy compositions of elements in groups four to six in the periodic table (Ti, Zr, Hf, V, Nb, Ta, Cr, Mo, W). The database is diverse yet multitargeted to enable simulations of refractory metals and alloys across different pure-metal, solid-solution, intermetallic, and glassy phases. We demonstrate the usefulness of the potentials by reproducing known pressure-, temperature-, and solute-induced phase transitions, grain boundary segregation, and simulations of radiation damage in the WTaCrVHf metallic glass.