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

IUCrJ ◽  
2021 ◽  
Vol 8 (3) ◽  
Author(s):  
Jan Schuetzke ◽  
Alexander Benedix ◽  
Ralf Mikut ◽  
Markus Reischl
Keyword(s):  
Deep Learning ◽  
Training Data ◽  
Phase Identification ◽  
X Ray Diffraction ◽  
Data Set ◽  
X Ray ◽  
Cell Parameters ◽  
Training Samples ◽  
Reliable Performance ◽  
Diffraction Patterns

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.

An Application of Calculated X-Ray Diffraction Patterns in the Analysis of Reference Powder Data: Trivalent Metal Sulfates

1992 ◽  
Vol 7 (4) ◽  
pp. 215-218 ◽  
Author(s):  
Sidney S. Pollack ◽  
Gregory J. McCarthy ◽  
Jean M. Holzer
Keyword(s):  
Powder Diffraction ◽  
Structure Data ◽  
The Other ◽  
Phase Identification ◽  
X Ray Diffraction ◽  
Trivalent Metal ◽  
Powder Diffraction File ◽  
X Ray ◽  
Cell Parameters ◽  
Diffraction Patterns

AbstractPowder diffraction patterns have been calculated for nine isostructural rhombohedral M2(SO4)3 (M = Sc, Ti, V, Cr, Fe, Ga, Y, Rh, In) phases, and for four isostructural monoclinic M2(SO4)3 (M = V, Fe, In, Tl) phases. The pattern for monoclinic Fe2(SO4)3 is the first reported for this phase. Because structure data are available only for the two Fe2(SO4)3 polymorphs, the powder patterns of the other trivalent metal sulfates were approximated using the structure data of the isostructural Fe phases with the scattering factors and previously determined cell parameters of the various metal sulfates. These calculated patterns are termed an approximation by isostruduralism.The calculated patterns were used to evaluate reference powder data for these phases in the Powder Diffraction File (PDF). All but two of the PDF patterns were found to differ substantially from the calculated patterns in the stronger peaks used for identification, and to be missing weak peaks that may be confused for impurities during phase identification.

scholarly journals Deep learning for visualization and novelty detection in large X-ray diffraction datasets

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Lars Banko ◽  
Phillip M. Maffettone ◽  
Dennis Naujoks ◽  
Daniel Olds ◽  
Alfred Ludwig
Keyword(s):  
Thin Film ◽  
Crystal Structure ◽  
Artificial Intelligence ◽  
Deep Learning ◽  
Novelty Detection ◽  
Structural Similarity ◽  
X Ray Diffraction ◽  
X Ray ◽  
Diffraction Patterns ◽  
Post Hoc

AbstractWe apply variational autoencoders (VAE) to X-ray diffraction (XRD) data analysis on both simulated and experimental thin-film data. We show that crystal structure representations learned by a VAE reveal latent information, such as the structural similarity of textured diffraction patterns. While other artificial intelligence (AI) agents are effective at classifying XRD data into known phases, a similarly conditioned VAE is uniquely effective at knowing what it doesn’t know: it can rapidly identify data outside the distribution it was trained on, such as novel phases and mixtures. These capabilities demonstrate that a VAE is a valuable AI agent for aiding materials discovery and understanding XRD measurements both ‘on-the-fly’ and during post hoc analysis.

scholarly journals Crystallization and preliminary X-ray diffraction analysis of UspE fromEscherichia coli

2014 ◽  
Vol 70 (12) ◽  
pp. 1640-1642 ◽  
Author(s):  
Yongbin Xu ◽  
Chun-Shan Quan ◽  
Xuanzhen Jin ◽  
Xiaoling Jin ◽  
Jing Zhao ◽  
...  
Keyword(s):  
Stress Proteins ◽  
Gel Filtration ◽  
X Ray Diffraction ◽  
Unit Cell Parameters ◽  
Data Set ◽  
X Ray ◽  
Cell Parameters ◽  
E Coli ◽  
Vapour Diffusion ◽  
Induced Genes

Universal stress proteins (Usps) are among the most highly induced genes when bacteria are subjected to several stress conditions such as heat shock, nutrient starvation or the presence of oxidants or other stress agents.Escherichia colihas five small Usps and one tandem-type Usp. UspE (or YdaA) is the tandem-type Usp and consists of two Usp domains arranged in tandem. To date, the structure of UspE remains to be elucidated. To contribute to the molecular understanding of the function of the tandem-type UspE, UspE fromE. coliwas overexpressed and the recombinant protein was purified using Ni–NTA affinity, Q anion-exchange and gel-filtration chromatography. Crystals of UspE were obtained by sitting-drop vapour diffusion. A diffraction data set was collected to a resolution of 3.2 Å from flash-cooled crystals. The crystals belonged to the tetragonal space groupI4122 orI4322, with unit-cell parametersa=b= 121.1,c = 241.7 Å.

X-ray diffraction patterns for BaR2PdO5 (R=Nd, Sm, Eu, and Gd)

1996 ◽  
Vol 11 (1) ◽  
pp. 9-12
Author(s):  
W. Wong-Ng
Keyword(s):  
Materials Characterization ◽  
X Ray Diffraction ◽  
Space Group ◽  
X Ray ◽  
Cell Parameters ◽  
Diffraction Patterns ◽  
The Eu

Calculated patterns for the BaR2PdO5 series, in which X is Pd and R=Nd, Sm, Eu, or Gd, have been prepared for materials characterization until experimental patterns can be determined. These compounds are isostructural to the superconductor related “brown phases” BaLa2CuO5 and BaNd2CuO5, which are tetragonal with space group P4/mbm, Z=4. The cell parameters of the Eu and Gd compounds were derived from the La and Nd analogs. The calculated patterns of these four compounds compared well to an experimental pattern of BaNd2CuO5.

Synthesis and properties of double gadolinium tellurites

2021 ◽  
Vol 103 (3) ◽  
pp. 67-73
Author(s):  
A.A. Toibek ◽  
◽  
K.T. Rustembekov ◽  
D.A. Kaikenov ◽  
M. Stoev ◽  
...  
Keyword(s):  
Phase Analysis ◽  
Solid Phase ◽  
Heat Capacities ◽  
Ceramic Technology ◽  
Phase Method ◽  
X Ray Diffraction ◽  
X Ray ◽  
Cell Parameters ◽  
Temperature Range ◽  
Diffraction Patterns

For the first time, double gadolinium tellurites of the composition GdMIITeO4.5 (MII — Sr, Ba) were synthesized by the solid-phase method. The solid-phase synthesis of samples was carried out from decrepitated gadolinium (III) and tellurium (IV) oxides, strontium, and barium carbonates according to the standard ceramic technology. The synthesis was carried out in the temperature range of 800-1100 °C. The samples obtained were confirmed by X-ray phase analysis. X-ray phase analysis was carried out on an Empyrean instrument in the XRDML Pananalitical format. The intensity of the diffraction maxima was estimated on a 100-point scale. X-ray diffraction patterns indexing of the powder of gadolinium tellurites — alkaline earth metals studied were carried out by the homology method. The reliability and correctness of the results of indexing the X-ray diffraction patterns are confirmed by the good agreement between the experimental and calculated values of the interplanar distances (d) and the agreement between the values of the X-ray and pycnometric densities. It was found that compounds GdSrTeO4.5 and GdBaTeO4.5 crystallize in the monoclinic system and have the unit cell parameters, namely GdSrTeO4.5 — a = 12.7610, b = 10.4289, c = 8.6235 Å, V° = 1141.83 Å3, β = 95.77°, Z = 5, ρrent. = 3.22, ρpikn. = (3.10±0.09) g/cm3; GdBaTeO4.5 — a = 15.7272, b = 15.8351, c = 7.1393 Å, V° = 1769.72 Å3, β = 95.53°, Z = 8, ρrent = 3.71, ρpick = (3.61±0.10) g/cm3. Using the Landiya method, the standard heat capacities of the compounds were estimated from the calculated values of the standard entropies, and the temperature dependences of the heat capacities of the gadolinium tellurites synthesized were determined in the temperature range of 298–850 K.

scholarly journals Bi3+ and Eu3+ Activated Luminescent Behaviors in Non-Stoichiometric LaO0.65F1.7 Structure

Materials ◽  
2020 ◽  
Vol 13 (10) ◽  
pp. 2326
Author(s):  
Sungjun Yang ◽  
Sangmoon Park
Keyword(s):  
Optical Materials ◽  
Emission Spectra ◽  
Lattice Energy ◽  
Host Lattice ◽  
X Ray Diffraction ◽  
Unit Cell Parameters ◽  
X Ray ◽  
Cell Parameters ◽  
Diffraction Patterns ◽  
Cation Sites

Optical materials composed of La1-p-qBipEuqO0.65F1.7 (p = 0.001–0.05, q = 0–0.1) were prepared via a solid-state reaction using La(Bi,Eu)2O3 and NH4F precursors at 1050 °C for two hours. X-ray diffraction patterns of the phosphors were obtained permitting the calculation of unit-cell parameters. The two La3+ cation sites were clearly distinguished by exploiting the photoluminescence excitation and emission spectra through Bi3+ and Eu3+ transitions in the non-stoichiometric host lattice. Energy transfer from Bi3+ to Eu3+ upon excitation with 286 nm radiation and its mechanism in the Bi3+- and Eu3+-doped host structures is discussed. The desired Commission Internationale de l’Eclairage values, including emissions in blue-green, white, and red wavelength regions, were obtained from the Bi3+- and Eu3+-doped LaO0.65F1.7 phosphors.

scholarly journals A deep-learning technique for phase identification in multiphase inorganic compounds using synthetic XRD powder patterns

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Jin-Woong Lee ◽  
Woon Bae Park ◽  
Jin Hee Lee ◽  
Satendra Pal Singh ◽  
Kee-Sun Sohn
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Inorganic Compounds ◽  
Phase Identification ◽  
X Ray Diffraction ◽  
X Ray ◽  
Learning Techniques ◽  
Learning Technique ◽  
Xrd Patterns

AbstractHere we report a facile, prompt protocol based on deep-learning techniques to sort out intricate phase identification and quantification problems in complex multiphase inorganic compounds. We simulate plausible powder X-ray diffraction (XRD) patterns for 170 inorganic compounds in the Sr-Li-Al-O quaternary compositional pool, wherein promising LED phosphors have been recently discovered. Finally, 1,785,405 synthetic XRD patterns are prepared by combinatorically mixing the simulated powder XRD patterns of 170 inorganic compounds. Convolutional neural network (CNN) models are built and eventually trained using this large prepared dataset. The fully trained CNN model promptly and accurately identifies the constituent phases in complex multiphase inorganic compounds. Although the CNN is trained using the simulated XRD data, a test with real experimental XRD data returns an accuracy of nearly 100% for phase identification and 86% for three-step-phase-fraction quantification.

scholarly journals Expression, purification, crystallization and preliminary X-ray crystallographic analysis of Enpp6

2014 ◽  
Vol 70 (6) ◽  
pp. 794-799 ◽  
Author(s):  
Junko Morita ◽  
Kazuki Kato ◽  
Emiko Mihara ◽  
Ryuichiro Ishitani ◽  
Junichi Takagi ◽  
...  
Keyword(s):  
Catalytic Domain ◽  
Crystallographic Analysis ◽  
X Ray Diffraction ◽  
Unit Cell Parameters ◽  
Data Set ◽  
X Ray ◽  
Cell Parameters ◽  
Choline Metabolism ◽  
Protein Molecules ◽  
Membrane Bound

Enpp (ectonucleotide phosphodiesterase/pyrophosphatase) 6 is a membrane-bound glycoprotein that hydrolyzes choline-containing compounds such as lysophosphatidylcholine and glycerophosphorylcholine, and presumably participates in choline metabolism. The catalytic domain of mouse Enpp6 was expressed in HEK293T cells, purified using the TARGET tag/P20.1-Sepharose system and crystallized. An X-ray diffraction data set was collected to 1.8 Å resolution. The crystal belonged to space groupP1, with unit-cell parametersa= 63.7,b= 68.8,c= 69.7 Å, α = 60.6, β = 87.0, γ = 68.1°. Assuming the presence of two protein molecules per asymmetric unit, the solvent content was estimated to be 49.5%.

scholarly journals Crystallization and preliminary X-ray diffraction analysis of AntE, a crotonyl-CoA carboxylase/reductase fromStreptomycessp. NRRL 2288

2014 ◽  
Vol 70 (6) ◽  
pp. 734-737 ◽  
Author(s):  
Lihan Zhang ◽  
Jing Chen ◽  
Takahiro Mori ◽  
Yan Yan ◽  
Wen Liu ◽  
...  
Keyword(s):  
Diffusion Method ◽  
Antimycin A ◽  
X Ray Diffraction ◽  
Unit Cell Parameters ◽  
Data Set ◽  
X Ray ◽  
Cell Parameters ◽  
Vapour Diffusion ◽  
Unsaturated Acyl ◽  
Reductive Carboxylation

AntE fromStreptomycessp. NRRL 2288 is a crotonyl-CoA carboxylase/reductase that catalyzes the reductive carboxylation of various α,β-unsaturated acyl-CoAs to provide the building block at the C7 position for antimycin A biosynthesis. Recombinant AntE expressed inEscherichia coliwas crystallized by the sitting-drop vapour-diffusion method. The crystals belonged to space groupI222 orI212121, with unit-cell parametersa= 76.4,b= 96.7,c= 129.6 Å, α = β = γ = 90.0°. A diffraction data set was collected at the KEK Photon Factory to 2.29 Å resolution.

Crystallization and preliminary X-ray diffraction studies on the N-utilizing substance-B (NusB) from Mycobacterium tuberculosis

2000 ◽  
Vol 56 (1) ◽  
pp. 64-66 ◽  
Author(s):  
B. Gopal ◽  
R. A. Cox ◽  
M. J. Colston ◽  
G. G. Dodson ◽  
S. J. Smerdon ◽  
...  
Keyword(s):  
Mycobacterium Tuberculosis ◽  
Ribosomal Rna ◽  
Diffusion Method ◽  
X Ray Diffraction ◽  
Hanging Drop ◽  
Core Complex ◽  
Unit Cell Parameters ◽  
Data Set ◽  
X Ray ◽  
Cell Parameters

N-utilizing substance B (NusB) is a protein which forms part of a complex assembly in transcriptional antitermination in Mycobacterium tuberculosis. It forms a heterodimer with the product of the NusE gene (identical to the ribosomal protein S10) and mediates the process of transcriptional antitermination by forming the core complex with the nut site of the ribosomal RNA along with other protein factors. NusB has been cloned and overexpressed in Escherichia coli and crystallized using the hanging-drop vapour-diffusion method. The space group is P212121, with unit-cell parameters a = 46.6, b = 64.2, c = 90.1 Å. A native data set complete to 1.6 Å resolution has been collected from a single crystal.

Sign in / Sign up

Export Citation Format

Share Document