Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks
This work addresses a time-consuming bottleneck in materials science for researchers developing novel thin-film materials, though it is incremental as it applies existing deep learning methods to a specific domain problem.
The authors tackled the problem of slow X-ray diffraction (XRD) analysis for thin-film materials by developing a machine learning approach that classifies crystallographic properties from limited datasets, achieving 93% accuracy for dimensionality and 89% for space-group classification, and reducing acquisition and classification time to 5.5 minutes or less.
X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials. We propose a machine-learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns. We overcome the scarce-data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. As a test case, 115 thin-film metal halides spanning 3 dimensionalities and 7 space-groups are synthesized and classified. After testing various algorithms, we develop and implement an all convolutional neural network, with cross validated accuracies for dimensionality and space-group classification of 93% and 89%, respectively. We propose average class activation maps, computed from a global average pooling layer, to allow high model interpretability by human experimentalists, elucidating the root causes of misclassification. Finally, we systematically evaluate the maximum XRD pattern step size (data acquisition rate) before loss of predictive accuracy occurs, and determine it to be 0.16°, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.