Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

TL;DR

This paper introduces a deep learning approach with physics-informed data augmentation for rapid, accurate classification of small XRD datasets, improving interpretability and reducing data acquisition time for novel thin-film materials.

Contribution

It presents a novel combination of convolutional neural networks and physics-informed data augmentation for classifying XRD data with high accuracy from limited samples.

Findings

Achieved 93% accuracy in dimensionality classification

Achieved 89% accuracy in space-group classification

Reduced XRD data acquisition time to under 5.5 minutes

Abstract

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{\deg}, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.