Publications
Validating predictions of burial mounds with field data: the promise and reality of machine learning
A pre-trained machine learning model, despite achieving high self-reported success rates, failed to accurately detect burial mounds in satellite imagery when validated against field data. The study found false negative and positive rates of 95–96% and 87–95%, respectively, with true positives accounting for only 5–13%. This challenges the optimistic narrative surrounding machine learning (ML) applications in archaeological prospection, highlighting significant limitations in detecting varied features within heterogeneous landscapes. The research underscores the substantial time, expertise, and resources required to improve model performance, questioning the efficiency of ML over manual inspection methods.
Realization of a Collection of Digital Resources for Cultural Heritage Sites as a Basis for Formation of Skills and Competencies
A web-based application, 'Me and UNESCO,' has been developed to serve as a digital resource for Bulgarian cultural and historical heritage sites under UNESCO protection. This application employs the Understanding by Design pedagogical approach, providing multimedia content that fosters the formation of skills and competencies in users. The platform acts as a database, offering an interactive learning environment that enhances understanding and engagement with UNESCO-protected sites in Bulgaria.
You are here:
World Heritage Explorer > World Heritage Research > World Heritage Sites > Thracian Tomb of Kazanlak