Deep learning for enhanced spectral analysis of MA-XRF datasets of paintings.

Recent advancements of noninvasive imaging techniques applied for the study and conservation of paintings have driven a rapid development of cutting-edge computational methods. Macro x-ray fluorescence (MA-XRF), a well-established tool in this domain, generates complex and voluminous datasets that pose analytical challenges. To address this, we have incorporated machine learning strategies specifically designed for the analysis as they allow for identification of nontrivial dependencies and classification within these high-dimensional data, thereby promising comprehensive interrogation.

Layout of ancient Greek papyri through lead-drawn ruling lines revealed by Macro X-Ray Fluorescence Imaging.

The use of lead-drawn ruling lines by ancient scribes for the layout of Greek papyrus rolls was known to us only from classical authors and was postulated by a few scholars in modern times. In situ application of noninvasive Macro X-Ray Fluorescence Imaging Spectroscopy (MA-XRF) to unrolled papyri from Herculaneum, dating from about 200 BC to the 1st century AD, has provided the first direct evidence of such practice in ancient book production. The key experimental proof of periodic lines drawn in lead was gathered by a highly sensitive MA-XRF mobile instrument, which allowed detection of ultra-low trace residues of metals with detection limits that rival synchrotron light instruments.