Effect of signal-to-noise ratio on the automatic clustering of X-ray diffraction patterns from combinatorial libraries

Abstract

Hierarchical clustering algorithm has been applied to identify the X-ray diffraction (XRD) patterns from a high-throughput characterization of the combinatorial materials chips. As data quality is usually correlated with acquisition time, it is important to study the hierarchical clustering performance as a function of data quality in order to optimize the efficiency of high-throughput experiments. This work investigated the effects of signal-to-noise ratio on the performance of hierarchical clustering using 29 distance metrics for the XRD patterns from Fe−Co−Ni ternary combinatorial materials chip. It is found that the clustering accuracies evaluated by the F1 score only fluctuate slightly with signal-to-noise ratio varying from 15.5 to 22.3 (dB) under the experimental condition. This suggests that although it may take 40–50 s to collect a visually high-quality diffraction pattern, the measurement time could be significantly reduced to as low as 4 s without substantial loss in phase identification accuracy by hierarchical clustering. Among the 29 distance metrics, Pearson χ² shows the highest mean F1 score of 0.77 and lowest standard deviation of 0.008. It shows that the distance matrixes calculated by Pearson χ² are mainly controlled by the XRD peak shifting characteristics and visualized by the metric multidimensional data scaling.