Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning
Leitherer A, Ziletti A, Ghiringhelli LM (2021)
Publication Type: Journal article
Publication year: 2021
Journal
Book Volume: 12
Article Number: 6234
Journal Issue: 1
DOI: 10.1038/s41467-021-26511-5
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.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Leitherer, A., Ziletti, A., & Ghiringhelli, L.M. (2021). Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning. Nature Communications, 12(1). https://doi.org/10.1038/s41467-021-26511-5
MLA:
Leitherer, Andreas, Angelo Ziletti, and Luca M. Ghiringhelli. "Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning." Nature Communications 12.1 (2021).
BibTeX: Download