Semi and Self Supervised approaches to Space Group and Bravais Lattice Determination

ORAL

Abstract

During this talk, I will discuss our work [1] to use neural networks to automatically classifiy Bravais lattices and space-groups from neutron powder diffraction data. Our work classifies 14 Bravais lattices and 144 space groups. The novelty of our approach is to use semi-supervised and self-supervised learning to allow for training on data sets with unlabelled data as is common at user facilities. We achieve state of the art results with a semi-supervised approach. Our accuracy for our self-supervised training is comparable to that with a supervised approach.

*Support for Satvik Lolla was provided by the Center for High Resolution Neutron Scattering, a partnership between the National Institute of Standards and Technology and the National Science Foundation under Agreement No. DMR-2010792.

–

Publication: "A semi-supervised deep-learning approach for automatic crystal structure classification"
Satvik Lolla Et al, Journal of Applied Crystallography 55 (2022)
https://doi.org/10.1107/S1600576722006069

Presenters

  • William Ratcliff

    • National Institute of Standards and Technology
    • National Institute of Standards and Technology; University of Maryland

Authors

  • William Ratcliff

    • National Institute of Standards and Technology
    • National Institute of Standards and Technology; University of Maryland

  • Satvik S Lolla

    • State of Maryland

  • Ichiro Takeuchi

    • University of Maryland, College Park
    • 1. Department of Materials Science and Engineering, University of Maryland, College Park, Maryland

  • Aaron Kusne

    • National Institute of Standards and Technology

  • Haotong Liang

    • University of Maryland, College Park