REPAINT · Computational investigation of degradation processes in historical paintings using DFT and AI

This project focuses on understanding of pigment degradation in 19th to 20th-century paintings caused by environmental factors such as humidity, temperature, and pollutants. By integrating advanced computational techniques, density functional theory (DFT), ab initio molecular dynamics (AIMD) simulations, and artificial intelligence (AI), the research aims to provide a detailed understanding of how these factors affect the chemical stability and degradation pathways of historical pigments at a molecular level. Static DFT calculations will be used to explore the electronic and optical properties of pigments, while AIMD simulations will examine how environmental conditions affect their degradation by revealing the structural changes. Using these computational results, AI models will be developed to predict how pigments degrade based on their composition and environmental conditions by capturing changes over time that static methods can't fully show. This approach will include a comparative study of pigments from different artworks to enhance the robustness of predictive models. The project aims to advance materials science and conservation by creating a comprehensive database that will offer data-driven guidelines to help extend the life of valuable historical artworks. This interdisciplinary approach aims to benefit both the scientific community and conservation professionals by representing an important step forward in the preservation of cultural heritage for future generations.