Dis-GEN: Disordered crystal structure generation

TL;DR

Dis-GEN is a novel generative model that creates symmetry-consistent disordered inorganic crystal structures, enabling better exploration of materials with compositional disorder and vacancies based on experimental data.

Contribution

It introduces Dis-GEN, the first model capable of generating disordered inorganic crystals with symmetry and compositional complexity, trained on the extensive ICSD database.

Findings

Dis-GEN effectively generates symmetry-preserving disordered structures.

The model accommodates compositional disorder and vacancies.

It expands generative modeling capabilities in materials science.

Abstract

A wide range of synthesized crystalline inorganic materials exhibit compositional disorder, where multiple atomic species partially occupy the same crystallographic site. As a result, the physical and chemical properties of such materials are dependent on how the atomic species are distributed among the corresponding symmetrical sites, making them exceptionally challenging to model using computational methods. For this reason, existing generative models cannot handle the complexities of disordered inorganic crystals. To address this gap, we introduce Dis-GEN, a generative model based on an empirical equivariant representation, derived from theoretical crystallography methodology. Dis-GEN is capable of generating symmetry-consistent structures that accommodate both compositional disorder and vacancies. The model is uniquely trained on experimental structures from the Inorganic Crystal Structure Database (ICSD) - the world's largest database of identified inorganic crystal structures. We demonstrate that Dis-GEN can effectively generate disordered inorganic materials while preserving crystallographic symmetry throughout the generation process. This approach provides a critical check point for the systematic exploration and discovery of disordered functional materials, expanding the scope of generative modeling in materials science.