A Generative Diffusion Model for Amorphous Materials

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.

Main: 19 pages, 5 figures; SI: 22 pages, 16 figures

References in corpus (10)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Glass breaks like metals, but at the nanometer scale
• Cooling-Rate Effects in Sodium Silicate Glasses: Bridging the Gap between Molecular Dynamics Simulations and Experiments
• Perspective: Configurational entropy of glass-forming liquids
• Generative Models for Automatic Chemical Design
• The effects of cooling rate on particle rearrangement statistics: Rapidly cooled glasses are more ductile and less reversible
• The critical role of the interaction potential and simulation protocol for the structural and mechanical properties of sodosilicate glasses
• Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory
• Crystal structure prediction with host-guided inpainting generation and foundation potentials
• Dismai-Bench: Benchmarking and designing generative models using disordered materials and interfaces