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

Felipe Oviedo,Charles Settens,Noor Titan Putri Hartono,Aaron Gilad Kusne,Brian L Decost,Zhe Liu,Shijing Sun,Siyu I P Tian,Giuseppe Romano,Tonio Buonassisi,Zekun Ren,Savitha Ramasamy

doi:10.1038/s41524-019-0196-x

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 three dimensionalities and seven 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° 2θ, which enables an XRD pattern to be obtained and classified in 5.5 min or less.

Highlights

High-throughput material synthesis and rapid characterization are necessary ingredients for inverse design and accelerated material discovery.[1,2] X-ray diffraction (XRD) is a workhorse technique to determine crystallography and phase information, including lattice parameters, crystal symmetry, phase composition, density, space group, and dimensionality.[3]
The XRD patterns for each sample are obtained by using a parallel beam, X-ray powder diffraction Rigaku SmartLab system[53] with 2Θ angle from 5 to 60° with a step size of 0.04°
The simulated and labeled data that support the findings of this study is available from the Inorganic Crystalline Structure Database (ICSD), but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available

Summary

Introduction

High-throughput material synthesis and rapid characterization are necessary ingredients for inverse design and accelerated material discovery.[1,2] X-ray diffraction (XRD) is a workhorse technique to determine crystallography and phase information, including lattice parameters, crystal symmetry, phase composition, density, space group, and dimensionality.[3] This is achieved by comparing XRD patterns of candidate materials with the measured or simulated XRD patterns of known materials.[4] Despite its indispensable utility, XRD is a common bottleneck in materials characterization and screening loops: 1 hour is typically required for XRD data acquisition with high angular resolution, and another 1–2 hours are typically required for Rietveld refinement by an expert crystallographer, assuming the possible crystalline phases are known. The direct-space method, statistical methods, and the growth of single crystals have been used to obtain crystal symmetry information for novel materials,[7,11,12,13,14] but the significant iteration time, feature engineering, human expertise, and knowledge of specific material required makes these methods impractical for high-throughput experimentation, where sample characterization rates are of the order of one material per minute or faster,[2,15] explored over various material families

Methods

Results

Conclusion