A Generative Diffusion Model for Amorphous Materials

Kai Yang, Daniel Schwalbe-Koda

Keywords: Amorphous materials, generative AI, diffusion models

TL;DR: A denoising diffusion framework enables fast, validated generation of diverse amorphous material structures across systems and processing conditions.

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 computational 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.

Submission Track: Paper Track (Full Paper)

Submission Category: AI-Guided Design

Institution Location: University of California, Los Angeles

AI4Mat RLSF: Yes

Submission Number: 19