A Generative Diffusion Model for Amorphous Materials

TL;DR

This paper introduces a diffusion model that efficiently generates realistic amorphous material structures, enabling faster design and simulation of complex materials like silica and metallic glasses, with validated structural and property accuracy.

Contribution

A novel diffusion-based generative model for amorphous materials that significantly accelerates structure generation and enables conditional sampling of diverse, realistic amorphous structures.

Findings

Generated structures match experimental and simulated properties.

Model achieves up to 1000x faster structure generation.

Successfully reproduces local and macroscopic properties of silica and metallic glasses.

Abstract

Generative models show great promise for the inverse design of molecules and inorganic crystals, but remain largely ineffective within more complex structures such as amorphous materials. Here, we present a diffusion model that reliably generates amorphous structures up to 1000 times faster than conventional simulations across processing conditions, compositions, and data sources. Generated structures recovered the short- and medium-range order, sampling diversity, and macroscopic properties of silica glass, as validated by simulations and an information-theoretical strategy. Conditional generation allowed sampling large structures at low cooling rates of 10$^{-2}$ K/ps to uncover a ductile-to-brittle transition and mesoporous silica structures. Extension to metallic glassy systems accurately reproduced local structures and properties from both computational and experimental datasets, demonstrating how synthetic data can be generated from characterization results. Our methods provide a roadmap for the design and simulation of amorphous materials previously inaccessible to computational methods.