Enhancing deep-learning training for phase identification in powder X-ray diffractograms

Abstract

Within the domain of analyzing powder X-ray diffraction (XRD) scans, manual examination of the recorded data is still the most popular method, but it requires some expertise and is time consuming. The usual workflow for the phase-identification task involves software for searching databases of known compounds and matching lists of d spacings and related intensities to the measured data. Most automated approaches apply some iterative procedure for the search/match process but fail to be generally reliable yet without the manual validation step of an expert. Recent advances in the field of machine and deep learning have led to the development of algorithms for use with diffraction patterns and are producing promising results in some applications. A limitation, however, is that thousands of training samples are required for the model to achieve a reliable performance and not enough measured samples are available. Accordingly, a framework for the efficient generation of thousands of synthetic XRD scans is presented which considers typical effects in realistic measurements and thus simulates realistic patterns for the training of machine- or deep-learning models. The generated data set can be applied to any machine- or deep-learning structure as training data so that the models learn to analyze measured XRD data based on synthetic diffraction patterns. Consequently, we train a convolutional neural network with the simulated diffraction patterns for application with iron ores or cements compounds and prove robustness against varying unit-cell parameters, preferred orientation and crystallite size in synthetic, as well as measured, XRD scans.

Machine Learning Automated Analysis of Enormous Synchrotron X-ray Diffraction Datasets

“…Comparing the performance of DNN models trained with and without experimental data inputs (Table ) reveals that using solely synthetic diffraction patterns is insufficient to train models capable of identifying phases from our experimental data, despite being reported in multiple studies. − ,, As shown in Table , most models trained without labeled experimental data exhibit a lower phase identification performance, including lower AUROC, AUPRC, and accuracy values. The only exception is bastnaesite-focused models, with two models having the same AUROC of 0.96.…”

“…All DNN models trained in this study used multiple layers of convolution and maxpooling to extract the features from the 1D XRD pattern. Based on the previously studies, the combination of these two layers improves the accuracy of models. − As shown in Figure S1, the binary classification DNN models determine the existence of phases from input XRD pattern mainly consists of 3 different kinds of layers including a 1d convolution layer, a maxpooling layer, and a fully connected layer. At the start of the model, normalized data points are fed into a 1d convolution layer (input channel of 1, output channel of 4, kernel size of 5, stride size of 1, and padding size of 1) which effectively extracts the features from the input.…”

“…A promising solution to the challenges posed by massive XRD data sets is the use of deep neural network (DNN) based models, which can automatically extract information from XRD patterns. − These models leverage the advantages of combining 1D convolution layers and dense layers to extract and learn features from labeled XRD patterns in the training data set. Several studies have reported using DNN models to extract various types of information from experimental XRD patterns, such as phase identity and ratio, unit cell parameters, and even the ability to distinguish potential perovskite materials. − However, since DNN model training usually requires a large amount of diverse data, a common practice is to generate theoretical XRD patterns from crystallographic structures. − Previous studies have shown that models trained on theoretical XRD patterns can analyze XRD patterns collected from solid samples in ambient environments. − However, it remains unclear whether these models can also accurately and efficiently analyze data collected from the μ-XRD mapping of in situ experiments involving complex mixtures of solids and liquid.…”

Convolutional neural network analysis of x-ray diffraction data: strain profile retrieval in ion beam modified materials

“…In the recent years, NNs have been increasingly used in the field of the characterization of materials using the scattering of x-rays or neutrons. One can cite symmetry identification [16][17][18], space group identification [19][20][21][22][23], phase identification [24][25][26][27], phase and crystallite size quantification [28], lattice parameter prediction [29], classification of 2D diffraction data in single particle imaging [30,31], or in small and wide angle scattering data [32][33][34][35][36][37][38][39][40][41], data correction [42][43][44] or automated analysis of 2D diffraction images [45][46][47][48][49], and phase retrieval with synchrotron coherent x-rays [50][51][52][53][54][55].…”

Interpretable Deep Learning Model for Analyzing the Relationship between the Electronic Structure and Chemisorption Property

“…Machine learning (ML) has been attracting attention over the past few years as one of the most efficient methods of exploring the vast materials space, which is generated by the combination of numerous types of structures and hundreds of elements in the periodic table. This method has been effectively used to a variety of problems in materials science and has successfully achieved structural classification − and prediction of material properties, such as formation energy, bulk moduli, band gap, and adsorption energy, with high accuracy. − To improve the classification or prediction performance, ML models have become more complex, which require numerous trainable parameters. The tens of thousands of parameters making up a single function make it impossible to understand how the model works.…”