An Optimization-Based Supervised Learning Algorithm for PXRD Phase Fraction Estimation

TL;DR

This paper introduces an optimization-based supervised learning method for estimating phase fractions in powder diffraction data, effective with limited training samples, outperforming traditional machine learning techniques.

Contribution

The authors propose a fixed-point iteration algorithm for phase fraction estimation that requires fewer training samples than existing machine learning methods.

Findings

The method accurately estimates phase fractions with small training datasets.

It outperforms several traditional machine learning algorithms in phase fraction estimation.

The approach is effective for multiphasic powder diffraction spectra.

Abstract

In powder diffraction data analysis, phase identification is the process of determining the crystalline phases in a sample using its characteristic Bragg peaks. For multiphasic spectra, we must also determine the relative weight fraction of each phase in the sample. Machine Learning algorithms (e.g., Artificial Neural Networks) have been applied to perform such difficult tasks in powder diffraction analysis, but typically require a significant number of training samples for acceptable performance. We have developed an approach that performs well even with a small number of training samples. We apply a fixed-point iteration algorithm on the labelled training samples to estimate monophasic spectra. Then, given an unknown sample spectrum, we again use a fixed-point iteration algorithm to determine the weighted combination of monophase spectra that best approximates the unknown sample spectrum. These weights are the desired phase fractions for the sample. We compare our approach with several traditional Machine Learning algorithms.