Prediction of the space group and cell volume by training a convolutional neural network with primitive `ideal' diffraction profiles and its application to `real' experimental data
Open Access
- 25 April 2025
- journal article
- research article
- Published by International Union of Crystallography (IUCr) in Journal of Applied Crystallography
- Vol. 58 (3) , 718-730
Abstract
This study describes a deep learning approach to predict the space group and unit-cell volume of inorganic crystals from their powder X-ray diffraction profiles. Using an inorganic crystallographic database, convolutional neural network (CNN) models were successfully constructed with the δ-function-like `ideal' X-ray diffraction profiles derived solely from the intrinsic properties of the crystal structure, which are dependent on neither the incident X-ray wavelength nor the line shape of the profiles. We examined how the statistical metrics ( e.g. the prediction accuracy, precision and recall) are influenced by the ensemble averaging technique and the multi-task learning approach; six CNN models were created from an identical data set for the former, and the space group classification was coupled with the unit-cell volume prediction in a CNN architecture for the latter. The CNN models trained in the `ideal' world were tested with `real' X-ray profiles for eleven materials such as TiO 2 , LiNiO 2 and LiMnO 2 . While the models mostly fared well in the `real' world, the cases at odds were scrutinized to elucidate the causes of the mismatch. Specifically for Li 2 MnO 3 , detailed crystallographic considerations revealed that the mismatch can stem from the state of the specific material and/or from the quality of the experimental data, and not from the CNN models. The present study demonstrates that we can obviate the need for emulating experimental diffraction profiles in training CNN models to elicit structural information, thereby focusing efforts on further improvements.Keywords
This publication has 25 references indexed in Scilit:
- CrystalMELA: a new crystallographic machine learning platform for crystal system determinationJournal of Applied Crystallography, 2023
- A semi-supervised deep-learning approach for automatic crystal structure classificationJournal of Applied Crystallography, 2022
- Using a machine learning approach to determine the space group of a structure from the atomic pair distribution functionActa Crystallographica Section A Foundations and Advances, 2019
- Insightful classification of crystal structures using deep learningNature Communications, 2018
- Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material PropertiesPhysical Review Letters, 2018
- Classification of crystal structure using a convolutional neural networkIUCrJ, 2017
- The atomic simulation environment—a Python library for working with atomsJournal of Physics: Condensed Matter, 2017
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Crystallography Open Database – an open-access collection of crystal structuresJournal of Applied Crystallography, 2009
- Improved peak detection in mass spectrum by incorporating continuous wavelet transform-based pattern matchingBioinformatics, 2006