2026-10-14T05:49:50Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34027397 2026-09-29T19:08:06Z category_7 category_21 category_45 category_734 category_931 portal_63 item_type_6 month_year_09_2026

The Role of Deep Learning and High-Throughput Dynamical Simulations in Space Group Determination from Kikuchi Patterns Alfred Yan (22958294) M. N. Talha Kilic (25138649) Gert Nolze (2618635) Ankit Agrawal (1354770) Alok Choudhary (3618293) Roberto dos Reis (2899919) Vinayak Dravid (1418890) Medicine Biotechnology Sociology Biological Sciences not elsewhere classified Information Systems not elsewhere classified train neural networks throughput nanomaterials discovery short time frame scanning electron microscope crystal symmetry determination true space group throughput dynamical simulations space group information space group determination novel material samples throughput symmetry classification unsupervised deep learning novel materials hinges developing working models experimental training data cubic kikuchi patterns space group symmetry classification deep learning experimental data kikuchi patterns material phases dynamical scattering data based kikuchi diffraction recent times rapid methods promising technique low number low diversity limitations imposed large number especially needed diffraction physics The design of novel materials hinges on the understanding of structure–property relationships. However, in recent times, our capability to synthesize a large number of materials has outpaced our speed of characterizing them, and thorough crystal structure analysis of newly synthesized samples remains a bottleneck in high-throughput nanomaterials discovery. Thus, rapid methods for crystal symmetry determination that can analyze many material samples within a short time frame are especially needed. Kikuchi diffraction in the scanning electron microscope (SEM) is a promising technique for this due to its sensitivity to dynamical scattering, which may provide space group information. In this study, we train neural networks to classify the space group from cubic Kikuchi patterns to enable its use for high-throughput symmetry classification of novel material samples. Due to the low number of material phases in the experimental training data, an unsupervised deep learning-based domain adaptation method was utilized to train neural networks on both simulated and experimental data. This helped to remedy the low diversity of the experimental training data. Additionally, instead of predicting the true space group, we relabel the data based on space group information that is realistically obtainable given physical limitations of Kikuchi diffraction, which enables our models to achieve accuracy scores higher than 95% for simulated and experimental data. This suggests that adapting to limitations imposed by diffraction physics is crucial for developing working models for symmetry classification. 2026-09-29T00:00:00Z Text Journal contribution 10.1021/acs.jpcc.6c01689.s001 https://figshare.com/articles/journal_contribution/The_Role_of_Deep_Learning_and_High-Throughput_Dynamical_Simulations_in_Space_Group_Determination_from_Kikuchi_Patterns/34027397 CC BY-NC 4.0