Neural Networks Trained on Synthetically Generated Crystals can Extract Structural Information from ICSD Powder X-Ray Diffractograms

When and Where

Nov 28, 2023
3:45pm - 4:00pm

Sheraton, Third Floor, Fairfax B



Pascal Friederich1,Henrik Schopmans1,Patrick Reiser1

Karlsruhe Institute of Technology1


Pascal Friederich1,Henrik Schopmans1,Patrick Reiser1

Karlsruhe Institute of Technology1
Machine learning techniques have successfully been used to extract structural information such as the crystal space group from powder X-ray diffractograms, especially in self-driving lab settings [1,2]. However, training directly on simulated diffractograms from databases such as the ICSD is challenging due to its limited size, class-inhomogeneity, and bias toward certain structure types. We propose an alternative approach of generating synthetic crystals with random coordinates by using the symmetry operations of each space group [3]. Based on this approach, we demonstrate online training of deep ResNet-like models on up to a few million unique on-the-fly generated synthetic diffractograms per hour. For our chosen task of space group classification, we achieved a test accuracy of 79.9% on unseen ICSD structure types from most space groups. This surpasses the 56.1% accuracy of the current state-of-the-art approach of training on ICSD crystals directly. Our results demonstrate that synthetically generated crystals can be used to extract structural information from ICSD powder diffractograms, which makes it possible to apply very large state-of-the-art machine learning models in the area of powder X-ray diffraction. We further show first steps toward applying our methodology to experimental data, where automated XRD data analysis is crucial, especially in high-throughput settings. While we focused on the prediction of the space group, our approach has the potential to be extended to related tasks in the future.<br/><br/>[1] Velasco, L., Castillo, J.S., Kante, M.V., Olaya, J.J., Friederich, P. and Hahn, H., 2021. Phase–property diagrams for multicomponent oxide systems toward materials libraries. <i>Advanced Materials</i>, <i>33</i>(43), p.2102301.<br/>[2] Schweidler, S., Schopmans, H., Reiser, P., Boltynjuk, E., Olaya, J.J., Singaraju, S.A., Fischer, F., Hahn, H., Friederich, P. and Velasco, L., 2023. Synthesis and Characterization of High-Entropy CrMoNbTaVW Thin Films Using High-Throughput Methods. <i>Advanced Engineering Materials</i>, <i>25</i>(2), p.2200870.<br/>[3] Schopmans et al., 2023, https://arxiv.org/abs/2303.11699


high-entropy alloy | x-ray diffraction (XRD)

Symposium Organizers

Milad Abolhasani, North Carolina State University
Keith Brown, Boston University
B. Reeja Jayan, Carnegie Mellon University
Xiaonan Wang, Tsinghua University

Publishing Alliance

MRS publishes with Springer Nature


Symposium Support