PhD candidate Hongyang Dong and Finden research scientists have developed a regression CNN that performs full profile analysis of powder diffraction data yielding physicochemical information (scale factors, lattice parameters and crystallite size) from multiphase systems. This project was performed in collaboration with National Physical Laboratory, STFC Scientific Machine Learning Group and UCL Department of Chemistry.
The work has resulted in a paper “A deep convolutional neural network for real-time full profile analysis of big powder diffraction data” published in NPJ Computational Materials 7, 74 (2021).
We present Parameter Quantification Network (PQ-Net), a regression deep convolutional neural network providing quantitative analysis of powder X-ray diffraction patterns from multi-phase systems. The network is tested against simulated and experimental datasets of increasing complexity with the last one being an X-ray diffraction computed tomography dataset of a multi-phase Ni-Pd/CeO2-ZrO2/Al2O3 catalytic material system consisting of ca. 20,000 diffraction patterns. It is shown that the network predicts accurate scale factor, lattice parameter and crystallite size maps for all phases, which are comparable to those obtained through full profile analysis using the Rietveld method, also providing a reliable uncertainty measure on the results. The main advantage of PQ-Net is its ability to yield these results orders of magnitude faster showing its potential as a tool for real-time diffraction data analysis during in situ/operando experiments.
You can read the full paper at https://doi.org/10.1038/s41524-021-00542-4