Inverse design of glass structure with deep graph neural networks

TL;DR

This paper introduces a novel inverse design method combining graph neural networks and swap Monte Carlo to improve the plastic resistance of Cu-Zr metallic glasses, revealing new stable configurations.

Contribution

It presents a data-driven approach integrating GNNs and Monte Carlo sampling for controllable inverse design of glass structures, a novel combination in this field.

Findings

Enhanced plastic resistance in Cu-Zr glasses achieved

Discovery of ultra-stable, geometrically stable glass configurations

Contradiction of traditional energy-resistance relationship

Abstract

Directly manipulating the atomic structure to achieve a specific property is a long pursuit in the field of materials. However, hindered by the disordered, non-prototypical glass structure and the complex interplay between structure and property, such inverse design is dauntingly hard for glasses. Here, combining two cutting-edge techniques, graph neural networks and swap Monte Carlo, we develop a data-driven, property-oriented inverse design route that managed to improve the plastic resistance of Cu-Zr metallic glasses in a controllable way. Swap Monte Carlo, as "sampler", effectively explores the glass landscape, and graph neural networks, with high regression accuracy in predicting the plastic resistance, serves as "decider" to guide the search in configuration space. Via an unconventional strengthening mechanism, a geometrically ultra-stable yet energetically meta-stable state is unraveled, contrary to the common belief that the higher the energy, the lower the plastic resistance. This demonstrates a vast configuration space that can be easily overlooked by conventional atomistic simulations. The data-driven techniques, structural search methods and optimization algorithms consolidate to form a toolbox, paving a new way to the design of glassy materials.