Neural network based classification of crystal symmetries from x-ray diffraction patterns

M., Vecsei, Pascal; Choo, Kenny; Chang, J.; Neupert, Titus

doi:10.1103/physrevb.99.245120

Cited by 79 publications

(89 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN is implemented in Keras 2.2.1 with the Tensorflow background.Figure 1b)contains a schematic of the proposed a-CNN architecture.Our a-CNN architecture, in contrast with other convolutional neural networks, does not have a max pooling layers in between convolutional layers, and also lack of a set of dense layers in the final softmax classification layer. These modifications, in contrast with the architectures used in10,18 , significantly reduces the number of parameters in the neural network and allows faster and simpler training, and are less prone to overfitting. Another advantage of our implementation is the possibility to extract class activation maps using global average pooling layer.…”

mentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

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° 2, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.

show abstract

mentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

show abstract

“… 171 The Fourier transform of the RDF also is directly related to the XRD pattern which has found widespread use in ML models for the classification of crystal symmetries. 131 , 218 , 219 …”

Section: What To Learn From: Translating Structures Into Feature Vectmentioning

confidence: 99%

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

et al. 2020

View full text Add to dashboard Cite

By combining metal nodes with organic linkers we can potentially synthesize millions of possible metal–organic frameworks (MOFs). The fact that we have so many materials opens many exciting avenues but also create new challenges. We simply have too many materials to be processed using conventional, brute force, methods. In this review, we show that having so many materials allows us to use big-data methods as a powerful technique to study these materials and to discover complex correlations. The first part of the review gives an introduction to the principles of big-data science. We show how to select appropriate training sets, survey approaches that are used to represent these materials in feature space, and review different learning architectures, as well as evaluation and interpretation strategies. In the second part, we review how the different approaches of machine learning have been applied to porous materials. In particular, we discuss applications in the field of gas storage and separation, the stability of these materials, their electronic properties, and their synthesis. Given the increasing interest of the scientific community in machine learning, we expect this list to rapidly expand in the coming years.

show abstract

“…Liu et al 21 refined atomic pair distribution functions in a convolutional neural network (CNN) to classify SGs. For similar purposes, Park et al 22 , Vecsei et al 23 , Wang et al 24 , Oviedo et al 25 , and Aguiar et al 26 used powder X-ray diffraction (XRD) 1D curves, for which information such as peak positions, intensities, and fullwidths at half-maximum are mainly treated as the key input descriptors. In addition, Ziletti et al 27 (in a parent work of this study), Aguiar et al 28 , Kaufmann et al 29 , and Ziatdinov et al 30 developed DL models by extracting features from electron-beam based 2D DPs.…”

Section: Introductionmentioning

confidence: 99%

Identification of crystal symmetry from noisy diffraction patterns by a shape analysis and deep learning

et al. 2020

View full text Add to dashboard Cite

The robust and automated determination of crystal symmetry is of utmost importance in material characterization and analysis. Recent studies have shown that deep learning (DL) methods can effectively reveal the correlations between X-ray or electron-beam diffraction patterns and crystal symmetry. Despite their promise, most of these studies have been limited to identifying relatively few classes into which a target material may be grouped. On the other hand, the DL-based identification of crystal symmetry suffers from a drastic drop in accuracy for problems involving classification into tens or hundreds of symmetry classes (e.g., up to 230 space groups), severely limiting its practical usage. Here, we demonstrate that a combined approach of shaping diffraction patterns and implementing them in a multistream DenseNet (MSDN) substantially improves the accuracy of classification. Even with an imbalanced dataset of 108,658 individual crystals sampled from 72 space groups, our model achieves 80.12 ± 0.09% space group classification accuracy, outperforming conventional benchmark models by 17–27 percentage points (%p). The enhancement can be largely attributed to the pattern shaping strategy, through which the subtle changes in patterns between symmetrically close crystal systems (e.g., monoclinic vs. orthorhombic or trigonal vs. hexagonal) are well differentiated. We additionally find that the MSDN architecture is advantageous for capturing patterns in a richer but less redundant manner relative to conventional convolutional neural networks. The proposed protocols in regard to both input descriptor processing and DL architecture enable accurate space group classification and thus improve the practical usage of the DL approach in crystal symmetry identification.

show abstract

Neural network based classification of crystal symmetries from x-ray diffraction patterns

Cited by 79 publications

References 42 publications

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

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

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

Identification of crystal symmetry from noisy diffraction patterns by a shape analysis and deep learning

Contact Info

Product

Resources

About