A Semi-Supervised Approach for Automatic Crystal Structure Classification

Published

November 18, 2021

Author(s)

Satvik Lolla, Haotong Liang, Aaron Kusne, Ichiro Takeuchi, William D. Ratcliff

Abstract

The structural solution problem can be a daunting and time consuming task. Especially in the presence of impurity phases, current methods such as indexing become more unstable. In this work, we apply the novel approach of semi-supervised learning towards the problem of identifying the Bravais lattice and the space group of inorganic crystals. Our semi-supervised generative deep learning model can use both labeled and unlabeled data during training. This approach allows our models to take advantage of the troves of unlabeled data that current approaches cannot. This should result in a better transfer to real data. In this work, we classify powder diffraction patterns into all 14 Bravais lattices and 144 space groups (we limit the number due to sparse coverage in crystal structure databases), which covers more crystal classes than other studies. Our models also drastically outperform current deep learning approaches for both space group and Bravais Lattice classification using less training data.

Citation

Journal of Applied Crystallography

Pub Type

Journals

Keywords

neutron, artificial intelligence, crystallography

Neutron research

Citation

Lolla, S. , Liang, H. , Kusne, A. , Takeuchi, I. and Ratcliff, W. (2021), A Semi-Supervised Approach for Automatic Crystal Structure Classification, Journal of Applied Crystallography (Accessed January 26, 2022)