Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning

TL;DR

ARISE employs Bayesian deep learning for robust, uncertainty-aware recognition of crystal structures, effectively analyzing noisy data and revealing structural features in materials science.

Contribution

This work introduces ARISE, a novel Bayesian deep learning method capable of identifying over 100 crystal structures robustly from noisy data, with interpretable insights.

Findings

ARISE accurately characterizes perturbed crystal systems.

Uncertainty estimates correlate with crystalline order.

Unsupervised analysis reveals grain boundaries.

Abstract

Due to their ability to recognize complex patterns, neural networks can drive a paradigm shift in the analysis of materials science data. Here, we introduce ARISE, a crystal-structure identification method based on Bayesian deep learning. As a major step forward, ARISE is robust to structural noise and can treat more than 100 crystal structures, a number that can be extended on demand. While being trained on ideal structures only, ARISE correctly characterizes strongly perturbed single- and polycrystalline systems, from both synthetic and experimental resources. The probabilistic nature of the Bayesian-deep-learning model allows to obtain principled uncertainty estimates, which are found to be correlated with crystalline order of metallic nanoparticles in electron tomography experiments. Applying unsupervised learning to the internal neural-network representations reveals grain boundaries and (unapparent) structural regions sharing easily interpretable geometrical properties. This work enables the hitherto hindered analysis of noisy atomic structural data from computations or experiments.