Generative diffusion model for surface structure discovery

TL;DR

This paper introduces a novel generative diffusion model tailored for discovering surface structures, incorporating substrate registry, periodicity, and rotational equivariance to generate large and complex surface phase models.

Contribution

The work presents a new diffusion-based generative model with a specialized neural network architecture and data augmentation, enabling the discovery of large, complex surface structures beyond training data limitations.

Findings

Successfully generated large surface structure models including a new silver-oxide domain boundary.

Demonstrated the model's ability to explore and predict unknown surface phases.

Showcased the effectiveness of the approach across multiple surface systems.

Abstract

We present a generative diffusion model specifically tailored to the discovery of surface structures. The generative model takes into account substrate registry and periodicity by including masked atoms and $z$-directional confinement. Using a rotational equivariant neural network architecture, we design a method that trains a denoiser-network for diffusion alongside a force-field for guided sampling of low-energy surface phases. An effective data-augmentation scheme for training the denoiser-network is proposed to scale generation far beyond structure sizes represented in the training data. We showcase the generative model by investigating multiple surface systems and propose an atomistic structure model for a previously unknown silver-oxide domain-boundary of unprecedented size.