Preparing the past for the future: Curating a daylight simulation model of Hagia Sophia for modern data infrastructures

Digital humanities and artificial intelligence applications rely on structured sets of data and metadata. Larger and more complex data-set as a product of growing computing power and widely available advanced tools demand modern data-management within projects, while scientific transparency, reusability, and interoperability require machine-readable publishing and linking of project data. The latter implies infrastructure for long-term storage and AI-assisted search. This paper examines the interdependency of in-project data-management and publishing and localizes possible applications of artificial intelligence (AI) in this context. It proposes a separation of project-data into five scopes that allow to develop transferable solutions and integration into emerging infrastructures for reuse, search, linking and publishing of data between projects. The paper exemplifies this concept in a non-ideal case-study – the heterogeneous data-set of a light-simulation model of Hagia Sophia – and concludes that AI-applications in this context provide more general, transferable solutions for search and spatial image organisation within the research infrastructure and very specific solutions within a project.