Machine learning regression algorithms for generating chemical element maps from X-ray fluorescence data of paintings

• Published in: Chemometrics and intelligent laboratory systems Vol. 248; p. 105116
• Main Authors: Ruiz de Miras, Juan, Gacto, María José, Blanc, María Rosario, Arroyo, Germán, López, Luis, Torres, Juan Carlos, Martín, Domingo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.05.2024
• Subjects: Chemical element maps; Machine learning; Random forest; Regression problem; X-ray fluorescence; Random forest; X-ray fluorescence; Chemical element maps; Regression problem; Machine learning
• ISSN: 0169-7439; 1873-3239
• DOI: 10.1016/j.chemolab.2024.105116

Generating chemical element maps of paintings from X-ray fluorescence (XRF) data is a very valuable tool for the scientific community of conservators and art historians. Hand-held XRF scanners are cheap and easily portable but their use provides scans with a few data, so additional analytical tools are needed to obtain reliable chemical element maps from them. Recently, the software tool SmART_Scan was released, which uses an algorithm based on the minimum hypercube distance (MHD) to compute this kind of maps. In this paper, we propose a new methodology to address this problem by using machine learning algorithms for regression as alternative and more accurate techniques than MHD. We tested MHD versus eight machine learning regression algorithms on two paintings with different features. Our results showed that machine learning algorithms Random Forest and kNN significantly outperformed MHD in Mean Squared Error (MSE) and coefficient of determination (R2) for all the experiments. When using experts’ data and a hold-out validation, kNN was the best-ranked algorithm. Random Forest was the best-ranked algorithm when cross-validation was used. We did not find significant differences in average MSE nor in R2 between kNN and Random Forest, so we can conclude that Random Forest is the best-suited algorithm for computing chemical element maps of paintings from XRF data. •Machine learning generated accurate chemical element maps from XRF data of paintings.•ML algorithms generated accurate maps when data from experts were used.•ML algorithms also performed accurately when tested using cross-validation.•Our methodology avoided complex ML algorithms and custom configurations.•Random Forest is the best-suited algorithm for generating composition maps.