13–17 Sept 2021
Virtual event
Europe/Berlin timezone

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

14 Sept 2021, 19:00
2h
Virtual event

Virtual event

Speaker

Andreas Leitherer (Fritz Haber Institute of the Max Planck Society)

Description

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.

Primary author

Andreas Leitherer (Fritz Haber Institute of the Max Planck Society)

Co-authors

Dr Angelo Ziletti (Fritz Haber Institute of the Max Planck Society) Dr Luca M. Ghiringhelli (Fritz Haber Institute of the Max Planck Society)

Presentation materials

There are no materials yet.