Score-based denoising for atomic structure identification

TL;DR

This paper introduces a novel score-based denoising method that effectively removes thermal vibrations from atomistic simulation data, enhancing structural analysis and classification accuracy across diverse materials.

Contribution

The proposed denoising approach is geometric, agnostic to interatomic potentials, and trained without explicit simulation inputs, enabling broad applicability and improved structural classification.

Findings

Achieves perfect classification accuracy on benchmark datasets.

Improves existing analysis methods like common neighbor analysis.

Effective across various atomistic simulation contexts.

Abstract

We propose an effective method for removing thermal vibrations that complicate the task of analyzing complex dynamics in atomistic simulation of condensed matter. Our method iteratively subtracts thermal noises or perturbations in atomic positions using a denoising score function trained on synthetically noised but otherwise perfect crystal lattices. The resulting denoised structures clearly reveal underlying crystal order while retaining disorder associated with crystal defects. Purely geometric, agnostic to interatomic potentials, and trained without inputs from explicit simulations, our denoiser can be applied to simulation data generated from vastly different interatomic interactions. The denoiser is shown to improve existing classification methods such as common neighbor analysis and polyhedral template matching, reaching perfect classification accuracy on a recent benchmark dataset of thermally perturbed structures up to the melting point. Demonstrated here in a wide variety of atomistic simulation contexts, the denoiser is general, robust, and readily extendable to delineate order from disorder in structurally and chemically complex materials.