Validation of non-negative matrix factorization for assessment of atomic pair-distribution function (PDF) data in a real-time streaming context
Materials Science
2020-10-23 v1 Machine Learning
Abstract
We validate the use of matrix factorization for the automatic identification of relevant components from atomic pair distribution function (PDF) data. We also present a newly developed software infrastructure for analyzing the PDF data arriving in streaming manner. We then apply two matrix factorization techniques, Principal Component Analysis (PCA) and Non-negative Matrix Factorization (NMF), to study simulated and experiment datasets in the context of in situ experiment.
Keywords
Cite
@article{arxiv.2010.11807,
title = {Validation of non-negative matrix factorization for assessment of atomic pair-distribution function (PDF) data in a real-time streaming context},
author = {Chia-Hao Liu and Christopher J. Wright and Ran Gu and Sasaank Bandi and Allison Wustrow and Paul K. Todd and Daniel O'Nolan and Michelle L. Beauvais and James R. Neilson and Peter J. Chupas and Karena W. Chapman and Simon J. L. Billinge},
journal= {arXiv preprint arXiv:2010.11807},
year = {2020}
}