Layer-by-layer decoding of contemporary and historic painting structure and composition using MALDI mass spectrometry imaging and machine learning

Zenodo (CERN European Organization for Nuclear Research) 2026 Dataset Open access

Read full text
Authors: Vaclav Krupicka, Florent Grélard, Landry Blanc, Aleksandra K. Popowich, Jose Luis Lazarte Luna, Nicolas Desbenoît, Julie Arslanoglu, Caroline Tokarski
DOI: 10.5281/zenodo.18234483
Cited by: 0

Abstract

This repository contains the MSIpredictART model used in the above publication: Layer-by-layer decoding of contemporary and historic painting structure and composition using MALDI mass spectrometry imaging and machine learning. MSIpredictART is a predictive model for identification of binder and pigment composition of paint cross-sections based on Least Absolute Schrinkage and selection Operator (LASSO). MSIpredictART can accurately identify with >95% specificity range of commonly occurring historical inorganic pigments and organic binders both oil and protein based.

Fields of Study & Subjects

Cultural Heritage Materials Analysis Mass Spectrometry Techniques and Applications Spectroscopy and Chemometric Analyses

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
13 January 2026
Language
EN
Document type
Dataset