A cloud platform for atomic pair distribution function analysis: <i>PDFitc</i>

Yang, Long; Culbertson, Elizabeth; Thomas, Nancy K.; Vuong, Hung T.; Kjær, Emil T. S.; Jensen, Kirsten M. Ø.; Tucker, Matthew G.; Billinge, Simon J. L.

doi:10.1107/s2053273320013066

Cited by 31 publications

(23 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We plan to implement DeepStruc as part of PDF-in-the-cloud (PDFitc.org), 37 where the training data can gradually be expanded over time. Combining the PDF conditioning with data from complimentary techniques could prove important for structure determination of more complex systems.…”

Section: Discussionmentioning

confidence: 99%

DeepStruc: Towards structure solution from pair distribution function data using deep generative models

Kjær

Anker

Weng

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Structure solution of nanostructured materials that have limited long-range remains a bottleneck in materials development. We present a deep learning algorithm, DeepStruc, that can solve a simple nanoparticle structure directly from a Pair Distribution Function obtained from total scattering data by using a conditional variational autoencoder (CVAE). We first apply DeepStruc to PDFs from seven different structure types of monometallic nanoparticles, and show that structures can be solved from both simulated and experimental PDFs, including PDFs from nanoparticles that are not present in the training distribution. We also apply DeepStruc to a system of hcp, fcc and stacking faulted nanoparticles, where DeepStruc recognizes stacking faulted nanoparticles as an interpolation between hcp and fcc nanoparticles and is able to solve stacking faulted structures from PDFs. Our findings suggests that DeepStruc is a step towards a general approach for structure solution of nanomaterials.

show abstract

Section: Discussionmentioning

confidence: 99%

DeepStruc: Towards structure solution from pair distribution function data using deep generative models

Kjær

Anker

Weng

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In an actual analysis of an in situ experiment it might be of interest to discover the chemical nature of the components that are appearing and disappearing. If they predominantly represent a single chemical phase it should be possible to identify the components by feeding them to a structureidentifying algorithm, such as the structure-mining approach (Yang et al, 2020) that is available as a web service at https:// pdfitc.org/ (Yang et al, 2021). We uploaded the extracted NMF components through this service.…”

Section: Batch and Streaming Pca/nmf On Experimental Datamentioning

confidence: 99%

Validation of non-negative matrix factorization for rapid assessment of large sets of atomic pair distribution function data

Liu¹,

Wright²,

Gu³

et al. 2021

J Appl Cryst

Self Cite

View full text Add to dashboard Cite

The use of the non-negative matrix factorization (NMF) technique is validated for automatically extracting physically relevant components from atomic pair distribution function (PDF) data from time-series data such as in situ experiments. The use of two matrix-factorization techniques, principal component analysis and NMF, on PDF data is compared in the context of a chemical synthesis reaction taking place in a synchrotron beam, applying the approach to synthetic data where the correct composition is known and on measured PDFs from previously published experimental data. The NMF approach yields mathematical components that are very close to the PDFs of the chemical components of the system and a time evolution of the weights that closely follows the ground truth. Finally, it is discussed how this would appear in a streaming context if the analysis were being carried out at the beamline as the experiment progressed.

show abstract

“…PDFitc.org (Yang et al, 2021) is a cloud based platform containing tools that can, given a user-uploaded measured PDF, automatically find candidate structures for subsequent fitting (structureMining app) (Yang et al, 2020), predict the space group of the structure that produced the PDF (spacegroupMining app) (Liu et al, 2019), and find the similarity between PDFs in a set (similarityMapping app). It has an easy to navigate interface that can be utilized on all of the popular web browsers (e.g.…”

Section: Pdfitc Interfacementioning

confidence: 99%

“…To address these issues we have developed a cloud-hosted, web-based, application, described herein, for doing NMF decomposition of powder diffraction and PDF datasets. This application, called nmfMapping, has been implemented as a service on the PDFitc cloud platform at pdfitc.org (Yang et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

nmfMapping: a cloud-based web application for non-negative matrix factorization of powder diffraction and pair distribution function datasets

Thatcher¹,

Liu²,

Yang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

A cloud-hosted web-based software application, nmfMapping, for carrying out a nonnegative matrix factorization of a set of powder diffraction or atomic pair distribution function datasets is described. This app allows structure scientists to rapidly find trends in sets of related data such as from in situ and operando diffraction experiments.The application is easy to use and does not require any programming expertise. It is available at the pdfitc.org website.

show abstract

A cloud platform for atomic pair distribution function analysis: PDFitc

Cited by 31 publications

References 37 publications

DeepStruc: Towards structure solution from pair distribution function data using deep generative models

DeepStruc: Towards structure solution from pair distribution function data using deep generative models

Validation of non-negative matrix factorization for rapid assessment of large sets of atomic pair distribution function data

nmfMapping: a cloud-based web application for non-negative matrix factorization of powder diffraction and pair distribution function datasets

Contact Info

Product

Resources

About