Our research in Network Science focuses on modelling the complex systems that shape cultural heritage in the digital realm. By harnessing Big Data—ranging from textual archives analysed through Natural Language Processing (NLP) to Earth Observation (EO) imagery—we organise this wealth of information into comprehensive Knowledge Graphs (KGs). These models enable the mapping and analysis of networks connecting sites, artefacts, people, and events, revealing hidden patterns vital for applications such as provenance research, systemic risk assessment, and the fight against illicit trafficking. Ultimately, our aim is to transform diverse and dispersed data into actionable intelligence, strengthening the protection, study, and understanding of global heritage.
Our methodology is inherently interdisciplinary, blending network analysis with machine learning and advanced geospatial techniques. This synergistic approach allows us to move beyond static data points to model the dynamic evolution of cultural systems over time. By simulating how these networks change and respond to external pressures—be it environmental change, socio-political conflict, or an increase in the trafficking of antiquities—we can test historical hypotheses and anticipate future trends. This allows us to identify not only the most critical assets within the heritage network but also its greatest vulnerabilities, ensuring that preservation efforts are both targeted and effective.
Ultimately, this research translates into tangible tools and frameworks for a wide range of stakeholders. We develop decision-support systems that help heritage professionals prioritize conservation efforts and predictive models that can alert authorities to potential threats before they escalate.
