Machine learning based quantification of synchrotron radiation-induced x-ray fluorescence measurements-a case study

In this work, we describe the use of artificial neural networks (ANNs) for the quantification of x-ray fluorescence measurements. The training data were generated using Monte Carlo simulation, which avoided the use of adapted reference materials. The extension of the available dataset by means of an ANN to generate additional data was demonstrated. Particular emphasis was put on the comparability of simulated and experimental data and how the influence of deviations can be reduced. The search for the optimal hyperparameter, manual and automatic, is also described. For the presented case, we were able to train a network with a mean absolute error of 0.1 weight percent for the synthetic data and 0.7 weight percent for a set of experimental data obtained with certified reference materials.

Automated summary

This study utilized artificial neural networks (ANNs) for quantifying x-ray fluorescence measurements, using Monte Carlo simulation to generate training data and demonstrating the ability to generate additional data through ANN. Emphasis was placed on comparing simulated and experimental data comparability and reducing the influence of deviations, while also describing the search for optimal hyperparameters.