Artificial Intelligence Analysis of Macroscopic X-Ray Fluorescence Data: A Case Study of Nineteenth Century Icon

This work comprehensively reviews artificial intelligence (AI) methods for macroscopic X-ray fluorescence (MA-XRF) data analysis of a religious panel painting (icon). ΜΑ-XRF is a powerful analytical imaging technique used to determine the elemental distribution maps of inhomogeneous targets. For the data analysis, we apply clustering algorithms such as k-means, factorization methods such as principal component analysis (PCA) and non-negative matrix factorization (NMF), and basic supervised machine learning methods, such as k-nearest neighbor (k-NN) regression and multilayer perceptron (MLP) regression. The applied AI methods allow for detailed and fast data analysis, providing two-dimensional elemental maps. The methods are beneficial for inexperienced users as they can analyze the MA-XRF data without detailed knowledge of the involved physics.