DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Integrated analysis of X-ray diffraction patterns and pair distribution functions for machine-learned phase identification

Journal Article · · npj Computational Materials

Abstract To bolster the accuracy of existing methods for automated phase identification from X-ray diffraction (XRD) patterns, we introduce a machine learning approach that uses a dual representation whereby XRD patterns are augmented with simulated pair distribution functions (PDFs). A convolutional neural network is trained directly on XRD patterns calculated using physics-informed data augmentation, which accounts for experimental artifacts such as lattice strain and crystallographic texture. A second network is trained on PDFs generated via Fourier transform of the augmented XRD patterns. At inference, these networks classify unknown samples by aggregating their predictions in a confidence-weighted sum. We show that such an integrated approach to phase identification provides enhanced accuracy by leveraging the benefits of each model’s input representation. Whereas networks trained on XRD patterns provide a reciprocal space representation and can effectively distinguish large diffraction peaks in multi-phase samples, networks trained on PDFs provide a real space representation and perform better when peaks with low intensity become important. These findings underscore the importance of using diverse input representations for machine learning models in materials science and point to new avenues for automating multi-modal characterization.

Sponsoring Organization:
USDOE
Grant/Contract Number:
NONE; AC02-05CH11231
OSTI ID:
2315714
Journal Information:
npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 10; ISSN 2057-3960
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (36)

A Machine‐Learning‐Based Approach for Solving Atomic Structures of Nanomaterials Combining Pair Distribution Functions with Density Functional Theory journal February 2023
Underneath the Bragg Peaks journal June 2003
Analysis of short-range order in Cu3Au using X-ray pair distribution functions journal February 2017
Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis journal February 2013
Inverse Design of Solid-State Materials via a Continuous Representation journal November 2019
An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties journal January 2022
Automatic microscopic image analysis by moving window local Fourier Transform and Machine Learning journal March 2020
Machine Learning Pipeline for Segmentation and Defect Identification from High-Resolution Transmission Electron Microscopy Data journal May 2021
Probabilistic Deep Learning Approach to Automate the Interpretation of Multi-phase Diffraction Spectra journal May 2021
Modeling Short-Range Order in Disordered Rocksalt Cathodes by Pair Distribution Function Analysis journal June 2023
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals journal April 2019
Structural Analysis of Molecular Materials Using the Pair Distribution Function journal November 2021
Mastering the game of Go with deep neural networks and tree search journal January 2016
A general-purpose machine learning framework for predicting properties of inorganic materials journal August 2016
Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks journal May 2019
Discovery of new materials using combinatorial synthesis and high-throughput characterization of thin-film materials libraries combined with computational methods journal July 2019
Extracting structural motifs from pair distribution function data of nanostructures using explainable machine learning journal October 2022
Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns journal December 2022
Adaptively driven X-ray diffraction guided by machine learning for autonomous phase identification journal March 2023
Validating neural networks for spectroscopic classification on a universal synthetic dataset journal June 2023
A mobile robotic chemist journal July 2020
Crystallography companion agent for high-throughput materials discovery journal April 2021
Deep convolutional neural networks for Raman spectrum recognition: a unified solution journal January 2017
Toward autonomous design and synthesis of novel inorganic materials journal January 2021
DeepStruc: towards structure solution from pair distribution function data using deep generative models journal January 2023
Pair distribution function analysis for oxide defect identification through feature extraction and supervised learning journal June 2023
The rise of the X-ray atomic pair distribution function method: a series of fortunate events journal April 2019
Neural network based classification of crystal symmetries from x-ray diffraction patterns journal June 2019
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties journal April 2018
Illustrated formalisms for total scattering data: a guide for new practitioners journal February 2021
Robustness test of the spacegroupMining model for determining space groups from atomic pair distribution function data journal May 2022
Classification of crystal structure using a convolutional neural network journal June 2017
Learning Deep Features for Discriminative Localization conference June 2016
Introduction to “This is Watson” journal May 2012
Chemical short range order obtained from the atomic pair distribution function journal January 2002
scikit-image: image processing in Python journal January 2014