Tiong, Leslie Ching Ow Kim, Jeongrae Han, Sang Soo Kim, Donghun 2024-01-19T16:01:51Z 2024-01-19T16:01:51Z 2022-01-10 2020-12 2057-3960 https://pubs.kist.re.kr/handle/201004/117733 The robust and automated determination of crystal symmetry is of utmost importance in material characterization and analysis. Recent studies have shown that deep learning (DL) methods can effectively reveal the correlations between X-ray or electron-beam diffraction patterns and crystal symmetry. Despite their promise, most of these studies have been limited to identifying relatively few classes into which a target material may be grouped. On the other hand, the DL-based identification of crystal symmetry suffers from a drastic drop in accuracy for problems involving classification into tens or hundreds of symmetry classes (e.g., up to 230 space groups), severely limiting its practical usage. Here, we demonstrate that a combined approach of shaping diffraction patterns and implementing them in a multistream DenseNet (MSDN) substantially improves the accuracy of classification. Even with an imbalanced dataset of 108,658 individual crystals sampled from 72 space groups, our model achieves 80.12 +/- 0.09% space group classification accuracy, outperforming conventional benchmark models by 17-27 percentage points (%p). The enhancement can be largely attributed to the pattern shaping strategy, through which the subtle changes in patterns between symmetrically close crystal systems (e.g., monoclinic vs. orthorhombic or trigonal vs. hexagonal) are well differentiated. We additionally find that the MSDN architecture is advantageous for capturing patterns in a richer but less redundant manner relative to conventional convolutional neural networks. The proposed protocols in regard to both input descriptor processing and DL architecture enable accurate space group classification and thus improve the practical usage of the DL approach in crystal symmetry identification. English Nature Publishing Group | Shanghai Institute of Ceramics of the Chinese Academy of Sciences (SICCAS) Identification of crystal symmetry from noisy diffraction patterns by a shape analysis and deep learning Article 10.1038/s41524-020-00466-5 1 npj Computational Materials, v.6, no.1 npj Computational Materials 6 1 Y scie scopus 000601277000002 2-s2.0-85097643265 Chemistry, Physical Materials Science, Multidisciplinary Chemistry Materials Science Article RAY-POWDER DIFFRACTION CLASSIFICATION Crystal symmetry Diffraction pattern Deep learning Machine learning Artificial intelligence